Qunatitative Analysis

Download as pdf or txt
Download as pdf or txt
You are on page 1of 30

QUANTITATIVE ANALYSIS

for
Business Research
QUANTITATIVE METHODS
• Includes both tools for collecting data and tools for analyzing
data
• A process of using numerical data to make decisions
• The process of collecting and evaluating measurable and
verifiable data such as revenues, market share, and wages in order
to understand the behavior and performance of a business
QUANTITATIVE METHODS vs
STATISTICAL METHODS
Both are essential components of research, but differ on the purpose and
involve different approach

Statistical methods is the study of data to find trends and patterns while
Quantitative methods is the use of the data to make decision

Statistical analysis are used to conduct quantitative analysis


QUANTITATIVE METHODS
DESCRIPTIVE INFERENTIAL
• Describe your data set • Make inferences about the
• Don’t aim to make predictions population
about the entire population

What will you use in your research?


ESSENTIAL WAYS TO CHOOSE THE
RIGHT STATISTICAL TEST
1. Research Question

• Clearly define your research objectives

• The nature of your research questions and research hypothesis will


heavily influence which statistical methods and techniques you should
use
ESSENTIAL WAYS TO CHOOSE THE
RIGHT STATISTICAL TEST
1. Research Question

“ Are you interested in understanding the attributes or


characteristics of your sample?”

“ Are you interested to understand differences between groups or


relationship between variable?”
ESSENTIAL WAYS TO CHOOSE THE
RIGHT STATISTICAL TEST
2. Identify the research variables

• Identify the variables


• Independent variables (the variable(s) you are manipulating or comparing)
• Dependent variables (the outcome you are measuring)
• Determine the number of variables or groups you are studying
• Two groups
• More than two groups
• Two or more variables
ESSENTIAL WAYS TO CHOOSE THE
RIGHT STATISTICAL TEST
2. Identify the research variables

Determine the nature of your data


• Categorical
• Continuous
ESSENTIAL WAYS TO CHOOSE THE
RIGHT STATISTICAL TEST
2. Identify the research variables

Identify the Scale and Levels of Measurement


Nominal
• Qualitative Data
• classificatory scale
Ordinal
• Qualitative data
• classificatory with ordering scale
ESSENTIAL WAYS TO CHOOSE THE
RIGHT STATISTICAL TEST
2. Identify the research variables

Identify the Scale and Levels of Measurement


Interval
• Quantitative Data
• has the properties of the nominal and ordinal levels
Ratio
• Quantitative Data
• highest level of measurement
ESSENTIAL WAYS TO CHOOSE THE
RIGHT STATISTICAL TEST
Why levels of measurement is important?
-determines how you can analyze your data.
The different levels limit which descriptive statistics you can use to get an
overall summary of your data, and which type of inferential statistics you can perform
on your data to support or refute your hypothesis.
In many cases, your variables can be measured at different levels, so you have to
choose the level of measurement you will use before data collection begins.
ESSENTIAL WAYS TO CHOOSE THE
RIGHT STATISTICAL TEST
3. Check Assumptions

Ensure that your data meet the assumptions of the statistical test
• Normality of Data
• Homogeneity of Variance
• Independence of Observation
ESSENTIAL WAYS TO CHOOSE THE
RIGHT STATISTICAL TEST
3. Check Assumptions

• If the parametric assumptions can be met, the parametric methods are


preferred.
• When parametric assumptions cannot be met, the nonparametric
methods are a valuable tool for analyzing the data.
What Statistical Test to use?
STATISTICAL TEST
Level Measures of Central tendency Measures of variability
Understanding
the attributes or Nominal • Mode • None
characteristics
• Mode • Range
Ordinal
• Median • Interquartile range
• Range
• Mode
• Interquartile range
Interval • Median,
• Standard deviation
• Arithmetic mean
• Variance
• Range
• Mode
• Interquartile range
Ratio • Median,
• Standard deviation
• Arithmetic mean
• Variance
STATISTICAL TEST
Difference With 1 group
between
Groups
1 sample t-test
-to determine whether the mean of a single sample is
significantly different from a known population mean

Example:
A company wants to assess whether the average customer
satisfaction scores for their product is significantly different from
a benchmark score of 80
STATISTICAL TEST
Difference
between Parametric Test Nonparametric Test
Groups Conditions/
Purposes Non-normal
Normal Distribution
Distribution
One sample z-test (if 𝜎 is known)
Compare a mean
and
with Wilcoxon test
One sample t-test (if 𝜎 is
standard value
unknown)
STATISTICAL TEST
Difference With 2 independent group
between
Groups
Independent sample t-test
- Test whether there is a significant difference between the means
of two groups on a particular variable
Example:
Suppose a company wants to compare the effectiveness of two
different training programs (Program A and Program B) in
improving employee productivity.
STATISTICAL TEST
Difference Nonparametric
between Parametric Test
Conditions/ Test
Groups
Purposes Non-normal
Normal Distribution
Distribution
Two independent samples z-
test
Compare two (if 𝜎1 𝑎𝑛𝑑 𝜎2 are known)
means of and Mann-Whitney test
unpaired data sets Two independent samples t-
test
(If 𝜎1 𝑎𝑛𝑑 𝜎2 is unknown)
STATISTICAL TEST
Difference With 2 dependent group
between
Groups
Independent sample t-test
- Test whether there is a significant difference between the means of
two variables measured on the same subjects or entities under
different conditions or time points.
Example:
•Suppose a company wants to assess whether a new training program
has a significant effect on employee performance.
STATISTICAL TEST
Difference
between Nonparametric
Groups Parametric Test
Conditions/ Test
Purposes Non-normal
Normal Distribution
Distribution
Compare two
means of Paired-sample t-test Wilcoxon test
paired data sets
STATISTICAL TEST
Relationship
between
Correlation
Variables -assess the relationship between two variables and the strength
and direction of that relationship

Example:
Correlation can be used to determine if there is a relationship
between advertising spending and sales revenue
STATISTICAL TEST
Relationship
between Parametric Test Nonparametric Test
Variables Conditions/
Purposes Non-normal
Normal Distribution
Distribution
Find the
relationship
Pearson’s correlation Spearman’s correlation
between two
variables
STATISTICAL TEST
Relationship Level Nonparametric
between
Variables
Variable 1 Variable 2 Correlation
Contingency coefficient
Phi and Craver’s V
Nominal
Nominal Lambda
Uncertainty coefficient
Interval Eta
Spearman’s rho
Gamma, Somers’d
Ordinal Ordinal
Kendalls tau-b
Kendalls tau-c
STATISTICAL TEST
Relationship Regression
between
Variables -understanding the relationships, predicting outcomes,
optimizing decision-making and managing risks
-can be used to gain valuable insight that drive strategic
initiatives and improve performance

Example:
Regression can be used to predict future sales revenue based on
factors as advertising expenditure, economic indicators and
seasonality
STATISTICAL TEST
Relationship Parametric Test Nonparametric Test
between
Conditions/
Purposes Non-normal
Variables Normal Distribution
Distribution
Predict the values
Simple linear or
of one variable Spearman’s correlation
nonlinear regression
from another
Find the
Multiple regression Kendall’s coefficient of
relationship among
(linear/nonlinear) concordance
several variables
STATISTICAL TEST
Relationship
Level
Regresion
between Variable 1 Variable 2
Variables
Linear Regression (1
Nominal
independent)
Ratio
Continuous Interval
Multiple Linear Regression (2 or
more independent)

Nominal Logistic Regression


Ratio
Binomial
Interval
SOFTWARES USED FOR DATA
ANALYSIS
FREE SOFTWARES
JAMOVI
-is a user-friendly statistical software package designed for both beginners and
experienced researchers

R
-a powerful and widely-used programming language and software environment
for statistical computing and graphics

EXCEL
is a widely used spreadsheet software developed by Microsoft, known for its versatility
and range of functions
SOFTWARES USED FOR DATA
ANALYSIS
OTHER SOFTWARES

SPSS
(Statistical Package for the Social Sciences) is a comprehensive software
package used for statistical analysis in various fields, particularly in social
sciences
--THANK YOU--

You might also like