User Manual

AcaStat User Manual
Version 6.1
© Copyright 2009, AcaStat Software.

All rights Reserved.
http://www.acastat.com
Table of Contents
INTRODUCTION .......................................................................................................................... 5
PURPOSE.................................................................................................................................... 5
GETTING HELP ............................................................................................................................ 5
ACADEMIC APPLICATION .............................................................................................................. 5
INSTALLATION ............................................................................................................................. 5
UNINSTALLING ACASTAT ............................................................................................................. 6
ACASTAT STARTUP SCREEN ....................................................................................................... 6
UPDATES .................................................................................................................................... 7
CALCULATOR .............................................................................................................................. 7
OPTIONS PANEL .......................................................................................................................... 8
DATA GRID .................................................................................................................................. 9
Rows ...................................................................................................................................... 9
Columns................................................................................................................................. 9
Cells ..................................................................................................................................... 10
Entering data ....................................................................................................................... 10
Editing data .......................................................................................................................... 10
Right-Click Support .......................................................................................................... 10
Spreadsheet and Data File Limits .................................................................................... 10
Split Data Module ................................................................................................................ 12
Importing Data ..................................................................................................................... 13
Pasting Table Data ........................................................................................................... 13
Copying data from Microsoft Access ................................................................................ 14
Importing Text Data Files ................................................................................................. 14
Tips on using a spreadsheet application to create a csv or txt file ................................... 15
Example of Import Error ................................................................................................... 15
Exporting Data ..................................................................................................................... 15
Sending Data to Excel ...................................................................................................... 15
Saving as a Text File ........................................................................................................ 16
SYLK Errors ..................................................................................................................... 16
Changing Variable Names ............................................................................................... 16
Find Cell Contents ............................................................................................................... 16
Find and Replace................................................................................................................. 16
Adding/Deleting Rows and Columns ................................................................................... 17
Add/Delete Rows ............................................................................................................. 17
Add/Delete Columns ........................................................................................................ 17
Using a Weight Variable ...................................................................................................... 17
Formatting Variables ............................................................................................................ 18
Variable Name ................................................................................................................. 19
Variable Label .................................................................................................................. 19
Change Decimals ............................................................................................................. 19
Value Labels .................................................................................................................... 19
Missing Values ................................................................................................................. 19
Recoding Values.................................................................................................................. 19
Date Values as Controls .................................................................................................. 19
Computing New Variables ................................................................................................... 20
Comparing Dates ................................................................................................................. 22
AcaStat User Manual 2

Combining Two Variables .................................................................................................... 23
Trimming Extreme Values ................................................................................................... 24
STATISTICAL PROCEDURES .................................................................................................. 25
Variable Control Panel ......................................................................................................... 25
Dependent Variable ......................................................................................................... 25
Independent Variable ....................................................................................................... 25
Control Variable ............................................................................................................... 25
Creating Data Subset with Controls ................................................................................. 26
Statistical Procedures .......................................................................................................... 26
Frequencies ..................................................................................................................... 26
Descriptives ...................................................................................................................... 26
Explore ............................................................................................................................. 26
Crosstabulation ................................................................................................................ 26
Pearson Correlation ......................................................................................................... 27
Regression ....................................................................................................................... 27
List Variables .................................................................................................................... 27
Diagnostic Accuracy ......................................................................................................... 27
T-tests of means .............................................................................................................. 28
Analysis of Variance (ANOVA) ......................................................................................... 28
Summary Report .............................................................................................................. 28
Simulation ............................................................................................................................ 31
Random Sample .............................................................................................................. 31
Repeated Random Sampling ........................................................................................... 31
Appraisal Ratios................................................................................................................... 31
Project Notes ....................................................................................................................... 32
Data File Information ........................................................................................................... 32
OUTPUT ..................................................................................................................................... 33
Page Breaks..................................................................................................................... 34
Printing ............................................................................................................................. 34
Exporting .......................................................................................................................... 34
Copying and Pasting Output ............................................................................................ 34
Converting Output to Tab Delimited ................................................................................. 34
CHARTS ..................................................................................................................................... 35
SUMSTATS ................................................................................................................................ 36
SUMSTATS TIPS ........................................................................................................................ 36
t-test Module ........................................................................................................................ 37
One Sample Mean ........................................................................................................... 37
Two Sample Means ......................................................................................................... 37
ANOVA Module ................................................................................................................... 37
Z-test Module ....................................................................................................................... 37
One Sample Proportion .................................................................................................... 37
Two Sample Proportions .................................................................................................. 37
Chi-square Module .............................................................................................................. 37
Margin of Error for Means Module ....................................................................................... 38
Margin of Error for Proportions Module ............................................................................... 38
Standardized Score Module ................................................................................................ 38
Diagnostic Accuracy Module ............................................................................................... 38

Power Module ...................................................................................................................... 39
GLOSSARY ................................................................................................................................ 40
How Glossary Works ........................................................................................................... 40
Glossary File System ........................................................................................................... 41
Searching Records .............................................................................................................. 41
Limitations............................................................................................................................ 41
File Menu Items ................................................................................................................... 41
New File ........................................................................................................................... 41
Open File.......................................................................................................................... 41
Save File As ..................................................................................................................... 41
Add Records from Other Files .......................................................................................... 42
Import ............................................................................................................................... 42
Export ............................................................................................................................... 42
Print .................................................................................................................................. 42
Edit Menu Items ................................................................................................................... 42
Add Note .......................................................................................................................... 42
Save Note ........................................................................................................................ 42
Delete Note ...................................................................................................................... 43
Copy ................................................................................................................................. 43
Paste ................................................................................................................................ 43
Search .............................................................................................................................. 43
Reset Search ................................................................................................................... 43
PRACTICE DATA FILES ........................................................................................................... 44
Repair Practice Data Files ................................................................................................... 44
Practice (csv) Delimited Data Files ...................................................................................... 44
MANUALS (PDF) ....................................................................................................................... 45
User Manual ........................................................................................................................ 45
Student Workbook ............................................................................................................... 45
Applied Statistics Handbook ................................................................................................ 45
REVIEW OF FEATURES ........................................................................................................... 46
Data Grid ............................................................................................................................. 46
SumStats ............................................................................................................................. 47
Output Log ........................................................................................................................... 47
Glossary............................................................................................................................... 47
Handbook ............................................................................................................................ 47
SYSTEM REQUIREMENTS ....................................................................................................... 48
PURCHASE INFORMATION ..................................................................................................... 49

Introduction
Purpose
AcaStat provides students, teachers, researchers, and managers with an inexpensive and easy
to use data analysis tool and instructional aid. AcaStat combines several modules into one
convenient package. These modules include Data Grid, Charts, SumStats, Glossary, and the
Research Methods Handbook.
Getting Help
Both application and statistical help are provided throughout the AcaStat modules. Click on any
help button to get help on the current module.
In addition to application help, statistical help is provided in three formats:
9 The Research Methods Handbook is available in html format in the Handbook module.
9 A glossary is provided for statistical terms and definitions. You can add to this glossary or
create your own note database.
9 An Applied Statistics Handbook is provided in pdf format for Licensed Edition (LE) versions.
Academic Application
For those interested in using AcaStat as part of their academic teaching/learning, an excellent
companion text would be Hubert M. Blalock Jr.'s text Social Statistics, 2nd Edition (McGraw-Hill
Publishing Company). Most of the formulas used in the statistics Handbook are consistent with
Blalock. Practice problems are provided for most of the statistical methods contained in the
Handbook. When conducting manual calculations, students should round each calculation to
three decimal places (e.g., 1.5865 should be rounded to 1.587) to obtain results consistent with
the Handbook.
Installation
Download AcaStat from http://www.acastat.com. The software is downloaded in a self-extracting

file. Save the software to your hard drive and double-click on the file to begin the installation
process. Some installations require a 1.5 megabyte download of installation software. This will
be done automatically during the installation and will require an internet connection. Software
purchased on a CD does not require an internet connection.

Uninstalling AcaStat
Use the Windows Control Panel option ADD/REMOVE programs to uninstall this software. Files
that you have created or changed cannot be removed by the ADD/REMOVE option. These files
can be easily removed by manually deleting them from the hard drive by using Explorer or My
Computer to highlight and delete the 'AcaStat’ program folder in the 'C:\Program Files'
subdirectory.
AcaStat Startup Screen
AcaStat starts by displaying the Quick Tips tab. There are also tabs for Data Grid, Output,
Charts, Glossary, and Handbook. In addition, a control panel contains Statistical Procedures
options, SumStats, File Information, and Help Index. Use the Statistical Procedures panel to
select and run summary statistics, basic descriptive and inferential statistics, and
crosstabulations. The Output tab will automatically display the results for the current analysis or
a log of all analyses since you opened AcaStat. The output from all procedures except
Summary Reports will be automatically appended to the Output Log.
The Option pull-down menu allows you to hide all tabs except Output. These tabs will
automatically reappear when you restart AcaStat.

Updates
The Help menu contains an option to check for updates. AcaStat will connect with the Internet
and automatically compare your installed version with the version of the update, if any. If a
newer update is available, the appropriate files are downloaded to your computer.
Calculator
A pop-up calculator is available on the toolbar. It is a stay-on-top design that remains in view
when using AcaStat. The calculator allows copying of data in the result field or memory storage
field.

Options Panel
The options panel allows you to change output settings and the location of data files and
glossary file. Some changes may not be complete until you close and reopen AcaStat.

Data Grid
The Data Grid creates, imports, and exports delimited data files. The data spreadsheet displays
data from a previously created data file or data you are currently entering into Data Grid.
Opening or importing a new file will replace the current contents.
Rows
Each row represents one record or case and is the unit of analysis for your procedures. If your
data contain information on individuals, each row represents one person (observation). If your
data contain information on cities, each row represents one city.
Columns
Each column represents data for all records regarding one variable or characteristic. If a column
contains information on personal income in U.S. dollars, all data in that column should represent
the income for each person (row) in the data file.

Cells
Each cell represents a value for one observation of a single variable. It can contain string data
(words) or numerical data (numbers). Most data files use numerical data to represent words. As
an example, for the variable sex, you could code Male as "0" and Female as "1". This makes
data entry much easier since you only have to enter one number instead of typing a word. It
also simplifies recoding variables and identifying controls.
Entering data
To enter data, point and click on a cell and begin typing. Pressing the Enter key will save the
entry and move the data entry point to the next row. Pressing the right arrow key will save the
entry and move the data entry point to the right. Pressing Escape (Esc) will cancel the data you
are entering.
Editing data
To edit data, double-click on the cell and begin typing. Please note that pressing any of the
arrow keys will save the entry and move the data entry point to the relevant cell. Pressing the
Enter key will save the entry and move the data entry point to the next row. Pressing Escape
(Esc) will cancel the data you are entering.
Right-Click Support
Click the right mouse button in the spreadsheet to select from several edit options to include
adding and removing columns and rows and formatting variables.
Spreadsheet and Data File Limits
The Data Grid spreadsheet edit capacity is limited to 200,000 cells (more than sufficient for
most analyses). This is calculated by multiplying the number of columns (variables) by the
number of rows (observations). The edit capacity is also limited to 300 variables (columns).
Note: Although we strongly recommend you keep files under the edit capacity, you may import
larger files but only the first 100 records will be displayed in the spreadsheet. If you import a file
with more than 300 variables, the data grid will only display the first 300 variables, although all
variables and observations will be available for analysis. You will not be able to edit larger files
in the Data Grid, but can conduct recode operations and compute new variables. The file
capacity will be limited by the amount of memory available on your computer. AcaStat has been
tested on data files containing 50,000 observations and 200 variables. If you have large files, it
is recommended that you reduce them by limiting the number of variables. A Split Data module
is provided under the Data pull-down menu for creating duplicate files (same number of
observations) with fewer variables.
The table below gives some approximations of the maximum allowed when one considers the
number of variables (Var) and observations (Obs) in one data file. Data sets exceeding these
limits should be created in another program (we recommend spreadsheet software) and saved

as comma or tab delimited text files. Use the AcaStat import procedure to open the files for
analysis.
Obs Var Obs Var Obs Var Obs Var Obs Var
20000 10 3845 52 2127 94 1470 136 1123 178

16666 12 3703 54 2082 96 1448 138 1110 180
14285 14 3570 56 2040 98 1428 140 1098 182
12499 16 3447 58 1999 100 1407 142 1086 184
11110 18 3332 60 1960 102 1388 144 1074 186
9999 20 3225 62 1922 104 1369 146 1063 188
9090 22 3124 64 1886 106 1350 148 1052 190
8332 24 3029 66 1851 108 1332 150 1041 192
7691 26 2940 68 1817 110 1315 152 1030 194
7142 28 2856 70 1785 112 1298 154 1019 196
6666 30 2777 72 1753 114 1281 156 1009 198
6249 32 2702 74 1723 116 1265 158 999 200
5881 34 2631 76 1694 118 1249 160 989 202
5555 36 2563 78 1666 120 1234 162 979 204
5262 38 2499 80 1638 122 1219 164 970 206
4999 40 2438 82 1612 124 1204 166 961 208
4761 42 2380 84 1586 126 1189 168 951 210
4544 44 2325 86 1562 128 1175 170 942 212
4347 46 2272 88 1537 130 1162 172 934 214
4166 48 2221 90 1514 132 1148 174 925 216
3999 50 2173 92 1492 134 1135 176 916 218

Split Data Module
Use split data to create a new data file that only contains variables you select from the current
file. This feature allows you to reduce the size of large data files to increase analysis speed and
improve data editing capacity. The new file retains variable formatting.
To use the split data module, click the Data pull-down menu in the Data Grid tab and select the
Split Data File option. A list of all the variables in the current data file will be provided. Select a
variable from the current file list you wish to include in the new file and click the right arrow
button. Continue adding variables until you are satisfied with the content of the new data file.
To remove a variable from the new file list, select the variable and click the left arrow button.
Double-click 'None' to reset the new file list.

Importing Data
You can import data from text data files or by pasting data copied from a word processor,
spreadsheet, or database table.
Pasting Table Data
To paste data from a table, use your mouse to select and copy data in a word processor,
spreadsheet, or database table. In Data Grid, select "File/Import/Paste Data". A Data Import
module will display a portion of the data you copied and will provide options for indicating how
the variables are delimited. Click OK to import the data. This replaces all data in the current
Data Grid spreadsheet. You may also copy and paste individual cells, rows, and columns. Use
the routine copy and paste functions for these procedures.

Copying data from Microsoft Access
1. Click Table
2. Click Edit/Select All Records
3. Click Edit/Copy
4. Open Data Grid and use "File/Import/Paste Data"
Importing Text Data Files
To import a text file into Data Grid, click "File/Import Data" to select the data file. A Data Import
module will display a portion of the data in the file and will provide options for indicating how the
variables are delimited. You can create or export these text files from most software packages
to include word processors, spreadsheets, databases, and statistical packages.
Data Grid primarily uses either comma separated value (csv) or tab separated value (txt) files,
but you can use almost any delimiter. If the one you choose doesn't work, try another. If the first
character in the file is not numerical, Data Grid will assume the first row in this file contains the
variable labels and will analyze the data from row 2 on. You can change this by deselecting the
checkbox.
If the data file is large, it may take a few moments for Data Grid to read all the data. Once read,
the data will be displayed in the spreadsheet and variable names (column headings) will be
visible in the list boxes, if they are contained in the first row of the data. Otherwise, Data Grid
names the variables sequentially V1, V2, etc. You can edit data in the spreadsheet by double-
clicking on a cell. After importing data, you should save the file as an AcaStat system file. This
will increase loading speed and retains variable formatting.

Tips on using a spreadsheet application to create a csv or txt file
The first row in the spreadsheet should contain a column label to represent the data in that
column (keep the labels 8 characters or less). These labels represent the variable names and
help identify columns when imported into the Data Grid (see example of spreadsheet format
below).
A B C D
1 AGE SEX INCOME
2 23 M 46000
3 45 F 55000
Example of Import Error
When creating a comma separated value file, make sure all commas have been removed from
the cell contents before creating the file. If they are not removed, Data Grid's import procedure
will assume the comma is an extra variable. This will cause the cell contents in Data Grid to be
out of alignment with the column. You can see below that data in rows two and three do not line
up with the appropriate columns.
AGE SEX INCOME V4

1 65 M 33000
2 23 M
3 46000 45 F
Exporting Data
You can export data to text data files or to a Microsoft Excel spreadsheet (Excel must be
installed on your computer).
Sending Data to Excel
If you have Microsoft Excel software installed, select "File/Export Data/To Excel Spreadsheet".
Excel will automatically open and Data Grid will populate the spreadsheet with the contents of
the Data Grid. Don't forget to save the Excel file when done. This operation requires Excel97 or
later versions. Large data file exports should be accomplished by saving to a text data file
rather than a direct export to Excel.

Saving as a Text File
Click "File/Export Data" to save the data in the Data Grid datasheet as either a comma or tab
separated (delimited) file. Exported files can be easily read by other software packages.
Exporting data will loose any formatting you have created for variable labels, value labels, and
missing values. If you open the exported file in a common spreadsheet, the first row will list the
variable names and the remaining rows will contain the data (one row for each record). Each
column represents the data for one variable.
SYLK Errors
Sometimes using a spreadsheet to open a text file exported from Data Grid (or from another
software package) results in a SYLK error. If this occurs, try the following: a) open the file in a
word processor or AcaStat's Output Log, b) select and copy the contents, and c) paste the
contents into the spreadsheet. If you have Microsoft Excel software installed and the file is not
large, use "File/Export Data/To Excel Spreadsheet".
Changing Variable Names
You may rename the variable names by clicking on any cell in the column you wish to rename
and selecting the "Format" button on the toolbar (you may also use the "Variable Format" pull-
down menu) or click the right mouse button to display a menu. This will open the format screen
that will allow variable name changes. Keep variable names short by limiting them to 8
characters or less; e.g. "FamInc", not "Family Income."
Find Cell Contents
Use Find to search cell contents within one variable (column). This feature is most useful for
finding specific observations or data. Cells with a match are bolded. Click find again to locate
the next match. Click reset to remove the bolding.
Procedure
9 Select the variable you wish to search by clicking on the variable name in the listbox.
9 Enter the value or string you wish to search for.
9 Click the "Find" button.
Find and Replace
Use find and replace to change cell contents within one variable (column). This feature is most
useful for correcting data entry errors or changing string contents to values (e.g., to change
“Male” and “Female” strings so that all “Male” strings are coded as the value 1 and all “Female”
strings are coded as a value 2). An Undo button will appear after you conduct a replace
operation. Clicking this button will return the cell contents to the immediate proceeding value. It
is recommended that you conduct search and replace operations on a duplicate variable so you
do not disturb the original variable. Use the Compute procedure to duplicate a variable.

Procedure
9 Select the variable you wish to search by clicking on the variable name in the listbox.
9 Enter the value or string you wish to search for.
9 Enter the value you wish to use to replace the search parameter.
9 Click the "Replace" button.
Adding/Deleting Rows and Columns
The data spreadsheet automatically begins new data files with 20 columns and 1000 rows.
Add/Delete Rows
To add rows, click the Edit pull-down menu and select "Add Rows." Ten empty rows will be
added to the bottom of the spreadsheet. To delete a row, select the rows you wish to delete,
click the Edit pull-down menu, and select "Delete Rows." All data contained in the deleted
row(s) are lost.
Add/Delete Columns
To add a column, click the Edit pull-down menu and select "Add Columns." One empty column
will be added to the far right of the spreadsheet. To delete a column, select the columns you
wish to delete, click the Edit pull-down menu, and select "Delete Columns." All data contained in
the deleted column are lost.
Using a Weight Variable
Click the Data pull-down menu and select ‘Use

Weight Variable’ to identify a variable for
weighting observations. Weights are often
used to compensate for over or under
sampling and also for producing population
values from a random sample. The weights
are used in the frequency and descriptive
procedures. Weights will not be applied to any
other procedures. Only one weight can be
selected at a time.

Formatting Variables
To make output easier to interpret, create variable names and assign short explanatory labels to
variable names and values. Formatting information will be saved with the AcaStat data file and
can be changed at any time. Click the Copy Format button to copy and paste the formatting into
another similarly coded variable (e.g., 1=yes and 2=no). If data are exported, the formatting
information will not be exported.

Variable Name
Data Grid limits variable names to 8 characters. Since this is what is used to represent a column
in the variable list boxes, it is important to create short but meaningful variable names. As an
example, level of education could be named DEGREE or EDUC.
Variable Label
Use variable labels to create a more detailed description of the variable. The variable label is
only used for creating output. Using the above example, DEGREE could be labeled
"Respondent's highest degree."
Change Decimals
Specify the number of decimals displayed (and stored) for the selected variable. This option will
permanently change the data file when the file is saved.
Value Labels
Use value labels to create a more detailed description of the values used in a variable. The
value label is only used for creating output. If, for instance, education was coded 0 through 4 to
represent five general categories, the values would be more meaningful if coded as the
following: 0="< High School", 1="High school", 2="Junior college", 3="Bachelor", 4="Graduate".
Without labels, the output would show the values 0 through 4.
Missing Values
Identify up to four values or strings (words) to be excluded from the statistical analysis (blank
cells are always considered missing). Values that are less than (<) or greater than (>) a set
value can also be set as missing. Only numerical entries are useful for these two missing value
conditions.
Recoding Values
Data Grid can use the values of one variable to create a new variable. This is most useful when
there are several categories in a variable that can be combined into more meaningful
subgroups. An example would be taking years of education and recoding the years into less
than high school, high school, some college, and college graduate.
Date Values as Controls
Since statistical procedures require that all controls have numerical values, date values should
be recoded into numerical values (e.g., a value of 1 might be used to represent all observations
with a specific date, before a date, or after a date).

Procedure
9 Select the variable you wish to change by clicking on the variable name in the listbox.
9 Select the operation you wish to perform by clicking on a radio button. For coding less than
12 years of education, select the "<" button.
9 Enter the value you wish to use as the basis for the recode. For the above example, enter
12.
9 Enter a variable name for the new variable you are creating (limited to 8 characters).
Example "Edufmt" for formatted education.
9 Enter the new variable's value that will be used to represent the old values. For our
example, use 1 to represent anyone with less than 12 years of education.
9 Click the "Run Recode" button.
A new column will be added to the Data Grid that has the assigned variable name and the
recoded value. Repeat the process until all values needed for the new variable have been
recoded.
Data Grid has been designed so the impact of each recode is visible. Using education as an
example, any cell in the original education column with a value less than 12 should have the
value of "1" on the same row in the new column labeled "EduFmt." Compare the education
column to the EduFmt column to ensure the recode worked as planned.
Computing New Variables
Data Grid can create a new variable by mathematically manipulating the values of the original
variable. This is most useful when transforming a variable by squaring or taking the square root
of the original values. It is also be useful for applying a constant to all observations in a variable
to remove negative numbers or to develop an index. The Compute procedure can also be used
to create an exact duplicate of a variable or create a new variable that represents the natural log
of another variable’s values.
Procedure

9 Select the variable you wish to use for the compute from the variable name in the listbox.
Example "AgeSq" for squaring age in years.
9 Select the operation you wish to perform by clicking on a radio button.
9 Enter the value you wish to use in the compute statement. Note that ^2=square and
^.5=square root.
9 Click the "Run Compute" button.
A new column will be added to the Data Grid with the variable name and the computed values
for all observations.

Comparing Dates
Use Compare Dates to calculate the difference between two dates. This feature creates a new
variable that contains the number of days between the two selected date variables. If Var2 is
later in time than Var1, the number of days is positive. If it is earlier in time, the number of days
is negative.
Procedure
9 Select the variable you wish to use for the first date from the variable name in the listbox
and click the Var1 button.
9 Select the variable you wish to use for the second date from the variable name in the listbox
and click the Var2 button.
9 Click the "Compute" button.

Combining Two Variables
Use Combine Two Variables to create a third variable that is a mathematical combination of two
other variables. This feature creates a new variable that contains the result of the computation.
Repeat the operation to systematically combine several variables into one.
Procedure
9 Select the first variable you wish to use from the variable name in the listbox and click the
Var1 button.
9 Select the second variable you wish to use from the variable name in the listbox and click
the Var2 button.
9 Select the operation you wish to perform by clicking on a radio button.
9 Click the "Compute" button.

Trimming Extreme Values
Data Grid can create a new variable that excludes extreme observations. This is useful for
excluding extreme values (outliers) from a variable that are biasing the statistical analysis.
Trimming extreme values should be done cautiously, since meaningful information may be
excluded with this operation. This caution is especially important for random samples where
extreme values are an expected and necessary contribution to sample variation.
Procedure
9 Select the variable you wish to trim from the variable name in the listbox.
9 Enter the lower cutpoint. (excludes all values less than the entry)
9 Enter the upper cutpoint. (excludes all values greater than the entry)
Example "AgeTrim".
9 Click the "Run Trim" button.
A new column will be added to the Data Grid that has the assigned variable name and blank
cells where the extreme values would normally be located. All other cells will contain the data
from the original variable.

Statistical Procedures
Use Statistical Procedures control panel to select variables and the type of analysis.
Variable Control Panel
Use the Variable Control Panel to select the

variables you wish to use in the analysis. As an
example, to produce frequencies tables for the
variables sex and race, select the sex variable in
the variable listbox and click the arrow button to
place the variable in the “Analysis Variable”
listbox. Use the same procedure to select and
place the race variable in the listbox. Clicking the
Run Procedure toolbar button will produce
frequencies for both variables. Output from the
analyses will be displayed automatically and
recorded in the Output Log.
Dependent Variable
For any procedure, you must select an analysis or

dependent variable. The topmost variable listbox
is used for all univariate analyses (Frequencies
and Descriptives).
Independent Variable
With the exception of the Frequencies,

Descriptives, and List Variables procedures, an
independent variable must also be selected
(second listbox from top). In the case of t-tests,
subgroup values must also be indicated for the
independent variable so AcaStat compares the
correct groups.
Control Variable
A control can be established for all procedures. This limits the analysis to a specific subgroup.
As an example, if interested in the correlation between income (dependent variable) and
education (independent variable) for females only, locate the Sex variable name from the
variable listbox, click the arrow button to place the variable into the control box, and click the "="
button and indicate the value used for females. This would result in a correlation procedure that
excludes all males. The control is normally a value (number) not a string (character) for “>”, “<”,
and “<>” operators. If a string variable is used as a control, use the “=” operator or use the

Compute option (Variable Format pull-down menu) to create a duplicate of the variable and then
use “Replace Cell Contents” (Edit pull-down menu) to replace strings with values.
The "All Missing" option limits the analysis to records that have missing data for the control
variable. The "No Missing" option limits the analysis to all records that have valid entries for the
control variable.
Note: Please remember to click the arrow button to remove the control variable before running
another procedure.
Creating Data Subset with Controls
The control feature can be used to create a subset of the data based on the current file and the
control settings. Select a control without any analysis variables and click the run procedure
button. This will replace the current data with a subset that matches the control specification
(such as only selecting cases where sex=1). This procedure replaces the current data in the
Data Grid. Unsaved data will be lost (this operation does not affect saved files).
Statistical Procedures
You must select one of the statistical procedures to produce output.
Frequencies
This produces a listing of all the values in a variable, the number of times they occur in the variable, and
the percent of cases represented in each value. Frequencies can be produced on numerical and string
data.
Descriptives
Calculates measures of central tendency (mean, median) and variation (variance, standard deviation).
Descriptives requires numerical data.
Explore
Explore descriptive statistics (sum, count, mean, sample standard deviation, standard error,
95% confidence interval) for each subgroup in the selected categorical variable(s). Explore
requires numerical data.
Crosstabulation
This is a very useful procedure for representing the association between two categorical variables via a
contingency table. Each cell in a contingency table represents a subgroup. For each cell, count, row
percent, column percent, and total percent are reported. This procedure also automatically produces a
chi-square statistic. Crosstabulations are easiest to interpret when the number of rows and columns in the
contingency table are 5 or less.

Pearson Correlation
Calculates the Pearson correlation coefficient to represent the association between two interval/ratio level
variables. For multiple comparisons, a correlation matrix can be display.
Regression
Calculates simple regression (one independent variable) or multiple regression (two or more independent
variables). Ordinary least squares regression requires interval/ratio level dependent variables and logistic
regression requires a dichotomous dependent variable. As an option, ordinary least squares regression
will produce residuals for each observation and summary statistics for the observations included in the
model. Logistic regression will produce predicted values and summary statistics.
List Variables
This procedure will list the values of observations for up to seven variables. List all the observations or
set a maximum number of observations in the Max Obs box. As an example, if the data file had 1000
observations, a Max Obs value of 50 would list the first 50 observations in the data file.
Diagnostic Accuracy
Diagnostic accuracy compares a test result to a dichotomous reference standard. It is used to evaluate
the sensitivity and specificity of a diagnostic test. The reference variable can only be two values (usually 0
for non-disease and 1 for disease). This represents the gold standard to compare to the test results.
Each cell in the table holds counts. The test variable can be nominal, ordinal, or interval/ratio. The lowest
value for the reference standard must always represent non-disease or the output will be incorrect. The
cutpoint (T+ >) represents the point beyond which the test is positive (disease indicated). As an example,
if possible test results range from 1 to 4, a cutpoint of 1 means a positive test is indicated by a value of 2,
3, or 4. You should carefully evaluate the sensitivity and specificity for one cutpoint to ensure you have
configured the data properly before interpreting the results.
Definitions of abbreviations used in the output
Sn Sensitivity:
The proportion of diseased cases with a positive test.
Sp Specificity:
The proportion of non-diseased cases with a negative test.
PPV Positive Predictive Value:
The proportion of cases with a positive test that have the disease.
NPV Negative Predictive Value:
The proportion of cases with a negative test that do not have the disease.
LR+ Positive Likelihood Ratio:
A positive ratio greater than 1 indicates the diagnostic test increases the odds of identifying disease
Sn/(1-Sp).
LR- Negative Likelihood Ratio:

A negative ratio less than 1 indicates the diagnostic test increases the odds of correctly identifying
disease absence (1-Sn)/Sp.
K Kappa:
The level of agreement beyond chance for a 2x2 table at the cutpoint.
T-tests of means
Used to test for the difference between two sample means. For t-tests, the dependent variable must be
an interval/ratio level variable to produce the means for analysis. The independent variable must be a
nominal or ordinal level variable (often it will be a dichotomous variable such as sex: 1=male, 2=female).
Values representing the comparison groups for the independent variable must be entered. These values
are used to separate the dependent variable into two groups. Be careful to use the correct values or there
may be an error reported that indicates there are not enough cases to compute the t-test. If there are
more than two values in the independent variable, you may select the two subgroups you are interested
in testing. The other subgroups will be excluded from the analysis.
Analysis of Variance (ANOVA)
Used to test for the difference between two or more sample means. Like t-tests, the dependent variable
must be an interval/ratio level variable to produce the means for analysis. The independent variable must
be a nominal level variable (e.g.: race: 1=white, 2=black, 3=Asian, 4=Hispanic. or ordinal (political
ideology: 1=conservative, 2= moderate, 3=liberal). ANOVA optional output includes summary statistics for
each subgroup and the Bonferroni post hoc test for multiple comparisons. Charts are not provided for the
ANOVA procedure.
Summary Report
Summary report creates a table of summary statistics that can be printed or exported. This is a
very useful option for displaying survey data and market research results in a format more
understandable for those not use to interpreting contingency tables or standard descriptive
statistics output. The categorical option will produce counts and column percents for each
category contained in the columns by each category available in the rows. For continuous data,
the report will produce summary statistics for each row variable when controlling for the column
category. More than one column variable can be used but it is important to select column
variables that are categorical, otherwise the table may be too large to print or interpret.
Summary reports are sensitive to missing data, so carefully review the data before and after
analysis. It is especially important that the first dependent variable (rows variable) contain data
for all the values of the independent variable (columns categories). If this is an issue, use the
following procedure to create a placeholder variable:
1) Add a blank column to the spreadsheet
2) Right click a cell in the column and select “Replace Cell Contents” (also under the Edit
menu)
3) Click the list name of the blank column you created and enter the value 1 in the field
labeled “Replace with this value or string”. Click the Replace button and then close

4) When setting up the variables for the summary reports, select the placeholder variable
you created as the first row variable. Then add the row variables you wish to analyze.
5) After running the procedure, delete the placeholder variable from the report.
When a summary report is created, the Analysis Output tab will display the results in a
spreadsheet. Edit the data in the spreadsheet, format column widths, delete rows and columns,
and edit headers and footers for printed output. The summary report can also be exported to
Word or Excel or copied and pasted into other software. The spreadsheet allows right-click
mouse support.
Note: The summary report procedure is the only procedure that does not append the results to
the Output Log unless it is converted to tab output (Edit menu). This conversion, where tabs are
inserted in place of the spreadsheet columns, is appended to the output log.

Summary Report for Categorical Data
Summary Report for Continuous Data

Simulation
Two simulation procedures can be used for manipulating data in the spreadsheet. They were
designed to help students develop a better understanding of random sampling. The Random
Sample option creates a random sample from a larger data file. If you assume the larger data
file represents the entire population, a smaller random helps students discover how summary
sample measures such as means and proportions will vary from population parameters.
The Repeated Random Sampling procedure conducts multiple random samples to build a data
set that reflects summary measures for each random sample. This procedure helps students
test the Central Limit Theorem:
Central Limit Theorem
As sample size increases, the sampling distribution of means approximates a

normal distribution and is close to normal at a sample size of 30.
Random Sample
This procedure is used to create a data file that is a randomly selected subset of the current
spreadsheet. Enter the number of observations desired. Please note that the number of
observations must be less than total number of records in the current data. Click CREATE
SAMPLE to replace the current data with a random sample.
Repeated Random Sampling
This procedure creates repeated random samples from the current spreadsheet. For each
sample (iteration), the mean and standard deviation are computed and placed into the
spreadsheet. This results in a new data file where each row represents the summary statistics
for one random sample.
Enter the number of observations (sample size) and the number of random samples (iterations)
desired. Please note that the sample size must be less than the total number of records in the
current data. Click RUN ITERATIONS to replace the current data with a sampling distribution.
Appraisal Ratios
Use the Module pull-down menu to set which statistical procedures are available. The Statistics
Module is the default and provides all the statistical analyses available in AcaStat except
Appraisal Ratios. The Appraisal Module provides an additional procedure that is used to
determine tax assessment values of real estate. Selection of the Appraisal Module also
changes the contents of the Glossary and the output of certain procedures.
When the Appraisal Module is selected, the Appraisal Ratios statistical procedure will be visible
in the procedure list. Use of this procedure requires data on the market (selling) price and the
assessment value of homes to compute ratios and other statistics. A practice data file “Tax
Assessments” is included with AcaStat.

Some statistical procedures are hidden when the Appraisal Module is active. To access these
procedures, re-activate the Statistics Module through the Module pull-down menu.
Project Notes
The Project Notes and Data File

Information panel provides information to
help monitor the size of the data file and
the contents of the data grid (spreadsheet).
There is also a text box for keeping brief
project notes and comments.
Use the Notes textbox to keep project and

progress notes. The notes are saved with
the data file. To limit the impact on the size
of the data file, the notes field is limited to
3000 characters (about one 8.5 x 11 page
of text). Additions or changes to the notes
will be lost if the data file is not saved
before exiting. Since saving Project Notes
also saves the contents of the current data
file, make sure the current configuration of
the spreadsheet is acceptable. When in
doubt, simply create a different file name
when saving. Click the print button to print
the project notes.
Data File Information
The Data File Information control panel

contains information about the spreadsheet
and current data file. If using a saved
AcaStat data file, information is provided on
when the data file was last modified and file
size. Information is also provided on the
number of variables and observations as
well as the remaining capacity of the
spreadsheet.

Output
The Output tab displays the results of the analysis in a text window for editing, printing, and/or
saving as a text file. Each time a statistical procedure is run, the results are automatically sent
to the output log. Each subsequent transfer of results will be appended to previously appended
results creating a complete record of the analyses. The Output tab can also be used to view and
create csv data files. Closing the output log does not erase the contents. Click the "Clear"
button to erase all output. If Microsoft Word installed on the host computer, click the Word icon
on the toolbar to export the output to Word. This procedure automatically formats the output
and places each analysis on a separate page.
There are two output view options. Most Recent Output displays only the results of the most
recent statistical procedure. Output log displays the output from multiple statistical procedures.
It is important to remember that the output log contains all the analyses created, so the most
recent analysis is at the end of the log. The toolbar displays the output option available if
clicked, so when viewing Most Recent Output the toolbar button will display “Output Log” to
indicate clicking the button will display the entire output. In turn, when viewing Output Log, the
toolbar button will display the caption “Most Recent Output.”

Page Breaks
A page break will be inserted after each procedure and is marked in the document as "<page
break>". This is used to indicate where a new page should be printed when printing the results.
Deleting the "<page break>" notation will stop a new page from being printed. Adding this
notation will cause AcaStat to print a new page at the point where you inserted the notation.
Printing
By default, AcaStat prints a date and time header and a Notes section on each page printed.
Use the Options pull-down menu to deactivate the default settings.
Exporting
The contents of the Output tab can be exported to Microsoft Word (Word97 and newer) by
clicking on the Word icon in the toolbar. The contents of the Output tab can also be exported to
Microsoft Excel (Excel97 and newer) by clicking on the Excel icon in the toolbar.
Copying and Pasting Output
The Output tab uses a Courier New font. When copying and pasting the results into another
document (which we recommend for editing and including with a report), make sure the font of
the output is set to Courier New or the tables may not align properly. Some word processing
software will format the pasted text to match that software’s default font setting. This will cause
the pasted text to become misaligned.
It is important to remember that the output log contains all the analyses created, so scroll to find
the most recent analysis.
If the Summary Report procedure is used, the Output Tab will display a spreadsheet table. Edit
cell contents, format the width of columns, format the header and footer for printing, copy and
paste into other software, or export to Microsoft Word or Excel. Right-click mouse support is
provided. The summary report procedure is the only procedure that does not append the
results to the output log unless it is converted to tab delimited output (Edit menu). This
conversion is appended to the output log and is best used for copying and pasting output into a
spreadsheet.
Converting Output to Tab Delimited
This option located under the Edit menu will convert all output tables into a tab delimited format.
The conversion improves copying and pasting output into spreadsheets such as Excel or
Quattro Pro.

Charts
Use the Charts tab to produce histograms, scattergrams, column, and pie charts. Charts are
produced for single comparisons (one dependent variable and, when relevant, one independent
variable).
If a chart is visible, click the chart. This will open the chart in a separate form to enlarge, copy,
and print. Resize the chart form to enlarge or shrink an image (this may impact the axis label
formatting). If pasting the graph into other software, copy the chart and then use the “Edit/Paste
Special” pull-down menu in the software you wish to paste the graph. Select the “bitmap”
option.

SumStats
SumStats is designed for analyzing summary statistics. Summary statistics are developed from
raw data by programs such as AcaStat, SAS, and SPSS. Without access to the raw data, it is
difficult to conduct statistical comparisons of means, counts, and percentages. SumStats solves
this problem by allowing the use of summary data to calculate basic significance tests and other
common descriptive calculations.
Most statistics courses use summary statistics to teach the fundamentals. SumStats is very
useful for checking the results of hand calculations.
SumStats Tips
Module specific instructions are presented as you click on a new module.

Instructions are replaced with summarized results from a calculation.
Use the ENTER key to move between boxes.
Pressing the ENTER key in the last box requiring data automatically calculates results.
Analyses are automatically appended to the Output Log.
Use copy and print buttons to print or paste the analysis results for the current procedure.
Entering a label is not required but is useful for interpreting output.

t-test Module
One Sample Mean
To use the t-test module for one sample mean, enter the data in the boxes as indicated and
click the calculate button. The population mean is the hypothetical mean that is used to
compare to the sample mean. If left blank, SumStats will assume it is 0.
This module may also be used for paired t-tests. For a paired t-test, collect the difference for
each case between Var1 and Var2 and calculate the mean and standard deviation for this
difference. Enter this information into the relevant One Sample Mean boxes and enter 0 for the
population mean. This will test the null hypothesis that the paired difference between the means
of Var1 and Var2 is not significantly different from zero.
Two Sample Means
To use the t-test module for two sample means, enter the data in the boxes as indicated and
click the calculate button. P-values will be provided for samples with equal and unequal
variance.
ANOVA Module
Enter the data in the boxes as indicated and click the Run Procedures button. Each column
represents one sample distribution. You must start with the left column. At least two columns
(the two left columns) must have data for SumStats to compute statistics.
Z-test Module
One Sample Proportion
To use the Z-test module for one sample proportion, enter the data in the boxes as indicated
and click the calculate button. The population proportion is the hypothetical proportion that is
used to compare to the sample proportion. If left blank, SumStats will assume it is 0.
Two Sample Proportions
To use the Z-test module for two sample proportions, enter the data in the boxes as indicated
and click the calculate button. It is important to remember that, when comparing percentages,
first convert them to proportions (e.g., 75% = .75).
Chi-square Module
To use the Chi-square module, enter frequencies (counts) in the boxes and click the calculate
button. The columns represent one variable with up to five subgroups (e.g., Protestant, Catholic,
and Muslim are subcategories for the variable "Religion"). The rows represent a second variable
with up to five subgroups. Start with the left column. At least two columns (the two left columns)
and two rows (the top two rows) must have data for SumStats to compute statistics.

Margin of Error for Means Module
Enter the sample size (n), mean, and standard deviation (std dev) and click the calculate button
to estimate the margin of error. SumStats will produce 90%, 95%, and 99% confidence intervals
(in order from top to bottom).
Margin of Error for Proportions Module
Enter the sample size (n) and the proportion and click the calculate button to estimate the
margin of error. SumStats will produce 90%, 95%, and 99% confidence intervals (in order from
top to bottom).
Standardized Score Module
To use the standardized score module, enter one score from a distribution of scores in the first
box. Enter the mean of the distribution in the second box. Enter the standard deviation of the
distribution in the third box. Click the calculate button and the z-score will be calculated and its
relative location in a normal distribution will be noted in the graph.
Diagnostic Accuracy Module
This module is used to evaluate the accuracy of a diagnostic test in identifying disease
presence or absence. The 2x2 grid uses counts from a crosstabulation between known disease
status and the diagnostic test results for that disease for each patient. To use this module, enter
the counts in the relevant boxes and click Run Procedure.
If the counts are not already provided, counts can be produced by:
a) creating a data file in Data Grid where the rows represent patients and there is one column
for known disease status ( 0=No, 1=Yes) and one column for test results (0=Neg, 1=Pos);
b) running the crosstabulation procedure where the test variable (column) is the dependent
variable and the disease status is the independent variable; and,
c) entering the counts from the Crosstabulation into this module.
There is also a Diagnostic procedure in Data Grid for creating diagnostic accuracy statistics
using a raw data file.

Power Module
Four criteria are used to estimate the appropriate sample size for a study. Sometimes called a
power analysis, the primary goal is to collect enough cases to ensure you don't make a Type II
error (Beta). Beta is the probability of not rejecting a null hypothesis when it should have been
rejected. Power is 1- beta and is defined as the probability of correctly finding statistical
significance. A common value for power is .80 or an 80% chance that a random sample will find
a statistically significant difference when there truly is a difference in the population. SumStats is
focused specifically on 2-tailed tests between two independent random samples (means and
proportions). There are many other approaches and equations for estimating sample size.
To use the power module, select the statistical significance (alpha) and statistical power (1-
Beta). If you are comparing two proportions, use the z-test sample boxes. Enter the expected
proportion for each sample and click the calculate button. If you are comparing two means, use
the t-test sample boxes. Enter the expected difference between the two sample means and the
estimated pooled variation (standard deviation) and click the calculate button. SumStats will
present the total sample size needed given your assumptions. Note that the sample size is the
total of both samples.

Glossary
Glossary provides a convenient location to store notes, definitions, and other reference
information. Create and share your database with other Glossary users. You can also add the
records from multiple files to create one list of notes.
AcaStat includes a statistical term glossary named "StatNotes.sn1". Edit or add new terms to
the glossary. Create new Glossary files for recording project notes or storing output from
analyses (copy from the Output Log). IF YOU EDIT STATNOTES.SN1, YOU SHOULD SAVE
IT UNDER A DIFFERENT NAME. DURING ROUTINE AUTOMATIC UPDATES AN
UPDATED STATNOTES FILE MAY DOWNLOADED WHICH WILL REPLACE THE
STATNOTES FILE ON YOUR COMPUTER.
How Glossary Works
A list of the contents will be displayed to the left. Clicking an item in the list will display that
record's contents. To edit the record, start typing in the relevant field. Changes are
automatically saved when you click on another item. To create a new record, click the Add
button on the toolbar. When done entering information, click Save on the toolbar.

Glossary File System
When you create a new file, Glossary establishes a file named "Temp" with the extension ".sn1"
(e.g. "Temp.sn1"). Always save the Temp file under a different name before closing Glossary or
creating another new file.
Searching Records
Glossary provides a search option for doing a keyword search of the active record set. Records
with any match of the keyword (case insensitive) will be listed. Click on an item in the list to
display the record. The items listed in the search can be edited or deleted. Improve the search
potential by inserting common keywords at the end of a note. This will ensure that a search will
find similar subjects.
Limitations
Glossary limits the number of characters per field. When the limit is reached, the field will stop
allowing keyed entries. It is important to remember that spaces count as one character and
paragraph returns count as two. The status bar at the bottom of the form will track the number
of characters used.
The limitations of each field are as follows:
Subject : 60 characters
Note Text : 3000 characters (about one 8.5 x 11 page of text)
File Menu Items
New File
Creates a new file called "Temp.sn1". Save this file under a different name to keep the
contents.
Open File
Opens an established Glossary file.
Save File As
Save a copy of the current file under a different name.

Add Records from Other Files
Select and add the contents of another Glossary file to the current file. This operation combines
notes entered in other files into one convenient and searchable database.
Import
Use Import to create a new Glossary file that is populated with text created in other software.
There are two options: a) paste the text into a new file or b) import a tab delimited text file. Both
options work very well with spreadsheets.
Formatting is very important. The text must be contained in two columns. The first column
should contain the subject and the second column should contain the descriptive text. Each row
represents one record (subject). Once the text is formatted into the two columns, copy and
paste the cell contents into Glossary using the Import option or save the file as a tab delimited
text file for importing.
Export
Export will put the contents of the current Glossary file into a tab delimited text file. This file can
be easily imported into other software. Exported files will have all paragraph returns removed
from the descriptive text. As a result, if the descriptive text in Glossary was separated into
several paragraphs, the resulting exported text file will combine these into one paragraph.
Print
Prints only the contents of the current record.
Edit Menu Items
Add Note
Creates a new record. Enter a subject label that will appear in the listing. Enter text in the
space provided below the subject field.
Save Note
Saves the contents of the current record. By default, Glossary will sort the items in the list box
and return to the first record.

Delete Note
Deletes the current note from the database.
Copy
Copies the currently selected text (shortcut [ctrl key + c]).
Paste
Pastes previously copied text into the field where your cursor is currently residing (shortcut [ctrl
key + v]).
Search
Search records for a keyword or phrase. Records with a match will be displayed in the list box.
Clicking on an item in the list box will display the record. The items listed in the search can be
edited or deleted.
Reset Search
Click the Reset button to reveal the original list of records.

Practice Data Files
Data Grid data files are delimited text files but differ from import/export files in that they are
configured to store variable labels, value labels, and missing values. There are several
instructional data files provided with AcaStat. For any AcaStat formatted data file, a complete
listing of variables is available by clicking the Data pull-down menu and selecting "Create Data
Dictionary". Background information on the data, if previously entered and saved, can also be
seen in the Project Notes tab.
Repair Practice Data Files
If a practice file becomes damaged or altered, replace the damaged file with an original version
by clicking the Options pull-down menu and selecting "Repair Sample Data Files". If a practice
data file has been deliberately altered, rename the file so this operation does not accidently
replace the altered version.
Practice (csv) Delimited Data Files
Fictitious data are provided in one comma separated value (csv) file for practicing data
importing.
File Name: "Income&Sex.cvs”

Location: AcaStat program folder, “\Data” subfolder
Fictitious Data (n=30)
VARIABLE NAME DEFINITION

RECORD Record number
INCOME Annual income in US$
EDUC Years of education
SEX 0=Male, 1=Female
To see what a comma or tab delimited text file looks like, open one of the csv or txt data files in
the Output tab.

Manuals (pdf)
AcaStat has three manuals: User Manual, Student Workbook, and the Applied Statistics
Handbook. They are electronic files in Adobe Acrobat Reader (pdf) format. To read these
files, Adobe Acrobat Reader version 6.0 or later must be installed on the host computer.
Acrobat Reader is a free download from Adobe. For more information, visit
http://www.adobe.com for download information. Version 8 is included on the AcaStat CD
purchase option.
Each manual includes an active contents page and can be viewed electronically or printed as
reference material. The Student Workbook and the User Manual are available as free
downloads from the AcaStat.com web site (www.acastat.com/pdfdocs.htm). If the manuals are
installed in the application folder (C:\Program Files\AcaStat-6), they can be opened through the
AcaStat Documentation menu. All AcaStat manuals are copyright protected.
User Manual
The User Manual contains instructions on how to use AcaStat. The content is similar to what is
contained in AcaStat help but includes screenshots of AcaStat modules.
File Name: UserManual.pdf

Availability: AcaStat CD, Website http://www.acastat.com/pdfdocs.htm
Student Workbook
The Student Workbook contains over 20 lessons designed to introduce basic statistical
concepts while also demonstrating the functionality of Data Grid, Stat Procs, and SumStats.
File Name: Workbook.pdf

Availability: AcaStat CD, Website http://www.acastat.com/pdfdocs.htm
Applied Statistics Handbook
The Applied Statistics Handbook is not available in the Special Edition version of AcaStat. It
contains formulas, definitions, and examples, of both hand calculations and annotated output
from analytical software. It is designed to be a quick reference resource (not a complete
statistical text). The Applied Statistics Handbook can be opened through the Documentation
pull-down menu in AcaStat. Purchase of the Licensed Edition of AcaStat is required. The
Applied Statistics Handbook is a much expanded version of the html Research Methods
Handbook included with the AcaStat program.
File Name: Statbook.pdf

Availability: Licensed Edition only of AcaStat.

Review of Features
AcaStat includes two data analysis modules (Data Grid, SumStats, and Charts) and three
support modules containing analysis output (Output Log) and instructional material (Glossary
and Handbook). Designed to provide students, teachers, researchers, and managers with an
inexpensive and easy to use tool for basic data exploration. Special pricing and site license
waivers are available for instructors adopting AcaStat for course work. Printable manuals
include a Student Workbook with over 20 lessons, an Applied Statistics Handbook, and an
AcaStat User Manual.
Data Grid
Analyze raw data with this spreadsheet design. Produces basic descriptive and inferential
statistics, and creates crosstabulations and summary reports. Includes the features listed
below. Export data directly to Excel. Run random sampling simulations.
Feature Details
Spreadsheet create data files, maximum edit capacity 200,000 data cells
Import Data import delimited text files, paste tables from other software
Data formatting create variable and value labels, set missing values
Variable Recode compute, combine, and recode variables
Paste Data copy and paste data from spreadsheets, documents, and database
tables
Export Data export comma and tab delimited value text files
Output Log edit output, save as text file, print, copy, paste
Statistics
Univariate summary statistics frequencies (count, percent, total)
mean, median, variance, standard deviation
Crosstabulations count, row %, col %, total %
List observations
Diagnostic accuracy sensitivity, specificity, predictive values, and likelihood ratios
Summary reports percentages, counts, means, sum, standard error, 95% CI
Two sample t-test of means
One-way ANOVA summary statistics and Bonferroni post hoc analysis
Chi-square Cramer’s V, Pearson C, Lambda, Kappa, Fisher’s, odds ratio
Pearson correlation correlation matrix
Simple regression
Multiple regression OLS and Logistic
Appraisal ratios ratios, price-related differential, coefficient of dispersion, coefficient of
variation
Graphing Features histogram, scattergram, column, and pie charts (enlarge, print, copy)
Simulation repeated random sampling to introduce the concept of sampling

distributions.

SumStats
Analyze summary statistics (means, proportions, counts) to develop confidence intervals and
conduct basic significance tests. Includes the features listed below. SumStats provides
summary instructions and interpretations of output alongside the calculator.
Feature Details
Statistical Tests
one and two sample t-test of means
one-way ANOVA (4 sample)
one and two sample z-test of proportions
chi-square (5x5 table)
Margin of Error-Mean 90%-95%-99% confidence intervals, margin of error, upper limits, lower
limits
Margin of Error-Proportions 90%-95%-99% confidence intervals, margin of error, upper limits, lower
limits
Standardized Scores z-score, graphic representation on normal distribution
Diagnostic Accuracy sensitivity, specificity, positive predictive value, negative predictive value,
positive likelihood ratio, negative likelihood ratio
Sample Estimator power analysis for the difference between two proportions (z-tests) and two
means (t-tests)
Output Log
Automatically stores all Data Grid and SumStats analyses for viewing, printing, and saving, and
keeps a running record of all analyses. Print, save as text file, or use the one-click export to
send directly to Microsoft Word.
Glossary
Note database for easy storage and retrieval. A statistics glossary of terms and definitions is
provided. Edit and add new terms and definitions. Create your own database of terms or notes
or store output from analyses.
Handbook
HTML statistics reference. Outlines hypothesis testing and provides formulas and examples of
hand calculations for common statistical tests. Hyperlinked to SumStats modules for easy
reference. Includes quick links to document webpage and links to websites providing reference
material on statistics and research methods.

System Requirements (recommended minimum)
Windows95/98/NT/XP/2000/Vista
Pentium 700mhz/128 mb RAM
Download file size 15 MB; Installed size 30 MB
Install on host computer hard drive
AcaStat Software
43584 Merchant Mill Terrace
Leesburg, VA 20176 USA
[email protected]
http://www.acastat.com

Purchase Information
Prices include shipping and are subject to change. Most CD-ROM orders are shipped the
next business day. Special orders, quantity discounts, and site licenses are
available. Questions? Contact AcaStat Software via e-mail at [email protected].
On line Orders (Credit Card)
Visit http://www.acastat.com for credit card orders, current prices, and site license
purchases and renewals.
Mail orders (check, money-order, or purchase order/invoice)
AcaStat Software Mail Order Form
Name:_________________________________ E-Mail: ______________________
Organization/School: _________________________________________________
Street: ________________________________ Phone: _____________________
City: __________________________________ State/Province: ____________
Country: _______________________________ Postal Code: _______________
Download - Retail $29.95 ea ____ x 29.95 = __________
Download – Academic $19.95 ea ____ x 19.95 = __________
Add Mini CD $10.00 ea ____ x 10.00 = __________
Subtotal = __________
Virginia residents add 5% sales tax (subtotal x .05) = __________
Total = __________
Make Check or Money Order Payable to:
AcaStat Software
43584 Merchant Mill Terrace
Leesburg, VA 20176 USA

User Manual

Uploaded by

Copyright:

Available Formats

User Manual

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

User Manual

Uploaded by

Copyright:

Available Formats

AcaStat User Manual

© Copyright 2009, AcaStat Software.

AcaStat User Manual 2

AcaStat User Manual 3

AcaStat User Manual 4

In addition to application help, statistical help is provided in three formats:

Download AcaStat from http://www.acastat.com. The software is downloaded in a self-extracting

AcaStat User Manual 5

AcaStat Startup Screen

AcaStat User Manual 6

AcaStat User Manual 7

AcaStat User Manual 8

AcaStat User Manual 9

Spreadsheet and Data File Limits

AcaStat User Manual 10

20000 10 3845 52 2127 94 1470 136 1123 178

AcaStat User Manual 11

AcaStat User Manual 12

Pasting Table Data

AcaStat User Manual 13

Importing Text Data Files

AcaStat User Manual 14

Example of Import Error

AGE SEX INCOME V4

Sending Data to Excel

AcaStat User Manual 15

Changing Variable Names

Find Cell Contents

Find and Replace

AcaStat User Manual 16

Adding/Deleting Rows and Columns

Using a Weight Variable

Click the Data pull-down menu and select ‘Use

AcaStat User Manual 17

AcaStat User Manual 18

Date Values as Controls

AcaStat User Manual 19

Computing New Variables

AcaStat User Manual 20

AcaStat User Manual 21

AcaStat User Manual 22

AcaStat User Manual 23

AcaStat User Manual 24

Variable Control Panel

Use the Variable Control Panel to select the

For any procedure, you must select an analysis or

With the exception of the Frequencies,

AcaStat User Manual 25

Creating Data Subset with Controls

You must select one of the statistical procedures to produce output.

AcaStat User Manual 26

Definitions of abbreviations used in the output

The proportion of diseased cases with a positive test.

The proportion of non-diseased cases with a negative test.

PPV Positive Predictive Value:

NPV Negative Predictive Value:

LR+ Positive Likelihood Ratio:

LR- Negative Likelihood Ratio:

AcaStat User Manual 27

Analysis of Variance (ANOVA)

Name:___________ E-Mail:

Street: ____________ Phone: _

City: ______________________ State/Province:

Country: _________________ Postal Code: _

Download - Retail $29.95 ea x 29.95 = ______