Statistical Treatment 2-20-18

Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 3

Statistical Treatment

Likert items are used to measure respondents’ attitudes to a particular question


or statement. In this research, likert scale is used to determine the interval of frequency
classification. The scales that will be used are shown below.

Table 2: Interval and Its Corresponding Agreement Level


Interval Agreement
4.51 - 5.00 Strongly Agree
3.51 - 4.50 Agree
2.51 - 3.50 Neutral
1.51 - 2.50 Disagree
1.00 - 1.50 Strongly Disagree

Analysis of likert scale utilizes descriptive statistics specifically, mean, median and
interquartile range. Additional data analysis procedures include skewness.
The weighted arithmetic mean is used to identify the central position within the
set of data gathered in the questionnaire. Each quantity to be averaged is assigned a
weight, which determines the relative importance of each quantity on the average.

Mean is used by researchers to understand the data set by getting a


representative sample. This will be computed using the formula:

∑𝑛𝑖=1(𝑤𝑖 𝑥̅𝑖 )
𝑥̅𝑤 = 𝑛
∑𝑖=1(𝑤𝑖 )

Where as
𝑥̅𝑤 is the weighted mean variable
𝑤𝑖 is the allocated weighted values
𝑥̅𝑖 is the observed values

The median is the middle score for a set of data that has been arranged in order
of magnitude. Through median, researchers determine what the average respondent’s
answer, or in other words, the likeliest response. The median, also, is less affected by
outliers and skewed data. It is computed using the equation below:
ℎ 𝑁
𝑀𝑒𝑑𝑖𝑎𝑛 = 𝑙 + ( − 𝑐)
𝑓 2

Where as
l is the lower class boundary of the median class
h is the size of the median class interval
f is the frequency corresponding to the median class
N is the total number of observation
c is the cumulative frequency preceding median class

The interquartile range (IQR) is a measure of where the “middle fifty” is in a data
set. Where a range is a measure of where the beginning and end are in a set, an
interquartile range is a measure of where the bulk of the values lie.
By using IQR, researchers are able to test the dispersion of data. It will show
whether the responses are clustered together or scattered across the rage of possible
responses.

The interquartile range formula is the first quartile subtracted from the
third quartile:

IQR = Q3 – Q1.

Formula for Quartile is:

ℎ 𝑁
𝑄𝑖 = 𝑙 + ( − 𝑐) ; 𝑖 = 1, 2, 3
𝑓 4

Where as

l is the lower boundary of the Quartile group


h is the with Quartile group
f is the frequency of Quartile group
N is the total number of observations
c is the cumulative frequency preceding Quartile group

Through the given statistical measurements above, analysis of the attribute


ratings can be made. This will assess the awareness of the students on the topics on
ethics in certain accounting subjects and the students' perception on committing
unethical behavior themselves in the practice.

2
To determine if there is a normally distributed continuous independent variable,
a one-way ANOVA is used. Hence, to test for differences in student’s perceptions about
the possibility of them commit unethical behavior in their future profession among the
three year levels, researchers use a One-way ANOVA (as the samples are independent).
All comparison is tested at p=.05

Skewness is used to determine the asymmetry of the probability distribution of


a real-valued random variable about its mean. In this case, the real-valued random
variable would be the test scores on part 1 of the questionnaire. The skewness value
can be positive or negative, or undefined.

Using skewness, researchers determine the degree to which a statistical


distribution is not in balance around the mean (is asymmetrical or lopsided). It is
calculated as:
3
𝑁
[(𝑁 − 1)(𝑁 − 2)] (𝑥̅𝑗 − )
𝑆𝑘𝑒𝑤𝑛𝑒𝑠𝑠 = ∑
𝑁 𝜎𝑥3
𝑗=1

Where:
xj is the observation j,
N is the total number of observations,
is the Average, and
σx is the Sample Sigma.

The data on factors that influences respondents’ ethical behavior in an ordinal


scale that will be gathered from the questionnaire will be summarized as the
percentage of respondents who fall in each factor using the formula:
𝑓
% = (n)x 100

Where f is the frequency distribution of the respondent per factor while n is the
total number of respondents.

You might also like