BUSI 820 ASSIGNMENT 4
QUANTITATIVE ANALYSIS: EVIDENCE FOR RELIABILITY AND VALIDITY
Quardarrius Fitts
BUSI 820: Quantitative Research Methods
School of Business, Liberty University
9 February 2025
Assignment
Author Note
Quardarrius Fitts
I have no known conflict of interest to disclose.
Correspondence concerning this article should be addressed to Quardarrius Fitts.
1
BUSI 820 ASSIGNMENT 4
Email: qfitts@liberty.edu
Table of Contents
Page 3: Chapter 6 Interpretation Questions and Responses, Chapter 6, Problem 6.1,
Figure 1
Page 4: Chapter 6 Interpretation Questions and Responses, Chapter 6, Problem 6.2
Page 5: Chapter 6 Interpretation Questions and Responses, Chapter 6, Problem 6.2, Figure
2
Page 6-12: Chapter 6 Interpretation Questions and Responses, Chapter 6, Problem 6.3,
Figure 3
Page 13-15: Chapter 6 Interpretation Questions and Responses, Chapter 6, Problem 6.4,
Figure 4
Page 16: References
2
BUSI 820 ASSIGNMENT 4
QUANTITATIVE ANALYSIS: EVIDENCE FOR RELIABILITY AND VALIDITY
SPSS Problems
Chapter 6
6.1
Compute Cohen’s kappa to assess reliability using Rater 1 and Rater 2. Interpret your
output as in Output 6.1 by writing an explanatory paragraph as you would in the
method section of an article or paper.
Figure 1
3
BUSI 820 ASSIGNMENT 4
For two nominal variables, Morgan et al. (2020) explain that Cohen's Kapp is used to
observe or measure the interobserver reliability, or the degree of agreement beyond normal
circumstances. Cohen's kappa coefficient is a number between -1 and 1, where 1 denotes
perfect agreement, 0 denotes equivalency to normal conditions, and less than 0 denotes less
than what would be expected under normal conditions. All 60 participants had valid data,
and the agreement between Rater 1 and Rater 3 was evaluated using Cohen's kappa in
Figure 1. Both raters agreed to reject or accept 56 of the 60 essays (39 accepted, 17 denied),
leaving four essays that were not in agreement. This corresponds to a Cohen Kappa value of
0.846, indicating that the raters' level of agreement is strong and that the classifications are
more consistent than would be predicted by chance.
6.2 Compute interrater reliability by running a paired t test for the essay score 1 with
the essay score 2. Interpret your output following the guide in the Interpretation of
Output 6.2. Write up your results for this analysis as you would in the method section
of an article or paper.
Figure 2
4
BUSI 820 ASSIGNMENT 4
The means of two independent but dependent groups of participants are compared
using a paired t-test. The data being compared comes from the same entity, and each entity
provides two data points. As would be expected for a null hypothesis, a paired t-test score of
zero denotes no discernible change between measurements. A paired t-test between two
essay entries was used in Figure 2, and the results showed a mean difference of 1.667 and a
correlation of 0.908. This suggests that there was little variation between the two raters and
that there was a strong positive and linear relationship between the two sets of
measurements.
5
BUSI 820 ASSIGNMENT 4
6.3 Run an Exploratory Factor Analysis using the extraction method of principal axis
factoring as demonstrated in Problem 6.3. Run the factor analysis on the 13 items
related to stress. In the extraction window (see Fig. 6.7), request “fixed number of
factors to extract” as 2. Study your output using the Interpretation of Output 6.3,
make a table and write up your results as you would for an article or paper.
Figure 3
6
BUSI 820 ASSIGNMENT 4
7
BUSI 820 ASSIGNMENT 4
8
BUSI 820 ASSIGNMENT 4
9
BUSI 820 ASSIGNMENT 4
10
BUSI 820 ASSIGNMENT 4
11
BUSI 820 ASSIGNMENT 4
In order to "determine the number of fundamental influences underlying a domain of
variables, to quantify the extent to which each variable is associated with the factors, and to
obtain information about their nature from observing which factors contribute to
performance on which variables," exploratory factor analysis, or EFA, is used to understand
the correlations that exist among variables. All 60 cases were found to be valid in Figure 3,
the correlation matrix shows that all 13 values are correlated with correlations between near
0 and 0.60, and the KMO and Bartlett Test value is 0.898, indicating a suitable sample size
for factor analysis. According to these findings, the dataset is suitable for carrying out an
EFA. The analysis can effectively uncover the latent factors underlying the domain of
12
BUSI 820 ASSIGNMENT 4
variables if there are sufficient inter-variable correlations, valid cases, and a sufficient
sample size.
6.4 Run Cronbach’s alpha for the five happiness scale items from the Chapter Six data
file. Follow the procedures outlined in Problem 6.4. Write up an explanation of your
resulting Cronbach’s alpha finding as you would in an article or paper.
Figure 4
13
BUSI 820 ASSIGNMENT 4
A statistical metric called Cronbach's alpha evaluates the internal consistency or
dependability of a collection of several items, measurements, or ratings. Cronbach's alpha
values range from 0 to 1, with higher scores denoting greater consistency. A range of 0.70 or
higher is considered acceptable. It should be mentioned, though, that the ideal Cronbach's
alpha value may differ based on the construct being measured and the research setting. A
14
BUSI 820 ASSIGNMENT 4
Cronbach's alpha of 0.967, as shown in Figure 4, indicates that the scale's items have a high
degree of correlation with one another, indicating strong reliability and consistency in
measuring the intended construct.
15
BUSI 820 ASSIGNMENT 4
References
Morgan, G. A., Barrett, K. C., Leech, N. L., & Gloeckner, G. W. (2020). Ibm Spss for
introductory statistics: Use and interpretation (6th ed.). Routledge, Taylor et Francis
Group.
16
