INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,  
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)  
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue XI, November 2025  
Use of Factor Analysis to Improve Questionnaire-Based Research  
Design  
R. Kanya Priya  
Department of Mathematics, Sri Ramakrishna College of Arts & Science for Women  
DOI: https://doi.org/10.51583/IJLTEMAS.2025.1411000019  
Received: 07 November 2025; Accepted: 14 November 2025; Published: 02 December 2025  
ABSTRACT  
Questionnaire-based research remains one of the most commonly used methods in social sciences, management,  
psychology, education, and health studies. However, the reliability and validity of the conclusions depend  
heavily on the quality of the questionnaire. Factor Analysis (FA), a multivariate statistical technique, provides a  
systematic approach to evaluate and refine questionnaires by identifying underlying latent constructs, reducing  
redundant items, and improving overall measurement accuracy. This article discusses the conceptual foundation  
of factor analysis, its methodological applications in questionnaire design, and practical guidelines for  
researchers to enhance instrument reliability and validity.  
INTRODUCTION  
Questionnaires are powerful tools for collecting data from large and diverse populations. However, poorly  
designed questionnaires may include ambiguous, redundant, or irrelevant items that compromise data quality.  
Researchers often assume that items on a questionnaire measure the intended construct, but empirical verification  
is essential.  
Factor analysis (FA) is one of the most effective tools for analyzing questionnaire items because it examines the  
structure of interrelationships among variables. It helps identify groups of items (factors) that measure the same  
underlying dimension and eliminates items that weaken the reliability of the questionnaire. Consequently, FA  
supports both exploratory and confirmatory approaches to instrument development.  
This paper explores how factor analysis strengthens questionnaire-based research design and outlines a  
systematic approach to developing, assessing, and refining questionnaires using FA.  
Understanding Factor Analysis  
Factor analysis is a statistical method used to identify underlying dimensions (factors) that explain the pattern  
of correlations among observed variables.  
Types of Factor Analysis  
a. Exploratory Factor Analysis (EFA)  
EFA identifies latent factors without predefined hypotheses. It is useful in early stages of questionnaire design  
to:  
Explore underlying dimensions  
Group related items  
Eliminate irrelevant or ambiguous items  
www.ijltemas.in  
Page 195  
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,  
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)  
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue XI, November 2025  
b. Confirmatory Factor Analysis (CFA)  
CFA tests hypotheses about factor structure. It is used to:  
Validate the factor model discovered through EFA  
Confirm the dimensionality of constructs  
Compare theoretical measurement models  
Assumptions of Factor Analysis  
Before applying FA, certain conditions must be met:  
Adequate sample size (generally > 100 respondents)  
Sufficient correlations between items  
Kaiser–Meyer–Olkin (KMO) > 0.6  
Bartlett’s Test of Sphericity significant (p < 0.05)  
These assumptions ensure that the dataset is suitable for factor extraction.  
Role of Factor Analysis in Questionnaire-Based Research  
Refining Constructs and Dimensions  
Questionnaires often aim to measure abstract concepts such as satisfaction, motivation, or attitudes. FA helps:  
Identify how many dimensions a construct has  
Detect items that do not align with any factor  
Remove items with low loading (< 0.40)  
For example, a 20-item questionnaire on job satisfaction may reveal only three meaningful factors: work  
environment, compensation, and personal growth.  
Reducing Redundant Items  
Items that measure the same concept may create unnecessary repetition. FA groups these items, allowing  
researchers to:  
Combine similar items  
Remove duplicates  
Shorten the questionnaire without reducing information quality  
This improves response rate and reduces fatigue among respondents.  
Improving Reliability and Validity  
FA strengthens both forms of validity:  
Construct validity: Ensures items measure the intended theoretical construct.  
www.ijltemas.in  
Page 196  
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,  
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)  
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue XI, November 2025  
Convergent and discriminant validity: Ensures that items load highly on their intended factor and minimally  
on others.  
Reliability can also be improved by removing items that reduce internal consistency (based on Cronbach’s  
alpha).  
Enhancing Data Interpretation  
With FA, researchers can interpret responses at the factor level rather than individual item level. This provides:  
More meaningful insights  
Reduced noise in data  
Better statistical power for regression or structural modeling  
Methodology for Using Factor Analysis in Questionnaire Design  
Step 1: Developing Initial Items  
Begin by:  
Reviewing literature  
Conducting interviews  
Using expert judgment  
Generating more items than required  
A comprehensive initial list increases the chances of capturing all dimensions.  
Step 2: Conducting a Pilot Study  
Administer the questionnaire to a small sample (30–50 respondents) to:  
Test wording clarity  
Identify confusing items  
Detect inconsistencies  
Step 3: Performing Exploratory Factor Analysis (EFA)  
After collecting main data, apply EFA:  
1. Check KMO and Bartlett’s test  
2. Choose extraction method (e.g., Principal Component Analysis or Maximum Likelihood)  
3. Determine number of factors using:  
o
o
o
Eigenvalues > 1  
Scree plot  
Parallel analysis  
www.ijltemas.in  
Page 197  
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,  
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)  
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue XI, November 2025  
1. Rotate factors (Varimax or Promax)  
2. Interpret and label factors  
3. Remove items with low communalities or cross-loadings  
Step 4: Refining the Questionnaire  
After EFA:  
Delete problematic items  
Reassign items to proper factors  
Re-evaluate reliability (Cronbach’s alpha ≥ 0.7 recommended)  
Step 5: Confirmatory Factor Analysis (CFA)  
CFA is used on a new dataset to confirm the final structure. Researchers evaluate:  
Model fit indices (CFI, TLI, RMSEA, χ²/df)  
Convergent validity (Average Variance Extracted > 0.5)  
Discriminant validity  
If necessary, further modifications are made.  
Step 6: Finalizing the Research Instrument  
Once validated, the questionnaire:  
Has a clear factor structure  
Measures the intended constructs accurately  
Is ready for large-scale data collection  
Practical Example  
Consider a questionnaire measuring online learning satisfaction with 25 items. After applying EFA:  
Only 4 factors emerge: technology support, content quality, instructor interaction, and learner  
engagement.  
7 items show low loading (< 0.4) and are removed.  
Remaining items regroup logically within factors.  
CFA confirms:  
Good model fit (CFI = 0.95, RMSEA = 0.06)  
High reliability (Cronbach’s alpha = 0.88)  
Thus, factor analysis significantly improves the instrument’s precision and usability.  
www.ijltemas.in  
Page 198  
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,  
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)  
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue XI, November 2025  
Advantages of Using Factor Analysis in Questionnaire Research  
Strengthens construct validity  
Minimizes measurement errors  
Produces shorter, more effective questionnaires  
Supports theory building  
Enhances the accuracy of statistical modeling  
Improves respondent experience  
Increases credibility of research findings  
Challenges and Considerations  
Despite its benefits, factor analysis has certain limitations:  
Requires large sample sizes  
Depends on researcher judgment in interpreting factors  
May produce unstable results with poor-quality items  
CFA requires advanced statistical skills and software (AMOS, LISREL, R, SPSS)  
Proper training and methodological rigor are essential for effective application.  
CONCLUSION  
Factor analysis plays a critical role in improving questionnaire-based research design by uncovering underlying  
constructs, removing weak items, ensuring reliability, and enhancing overall measurement quality. When used  
systematically—from initial item generation to EFA and CFA validation—it transforms raw questionnaires into  
scientifically robust research instruments. As research becomes more data-driven, the use of advanced statistical  
techniques like factor analysis becomes essential for producing high-quality, valid, and meaningful results.  
REFERENCES  
1. Hair, J. F., Black, W. C., Babin, B. J., & Anderson, R. E. (2019). Multivariate Data Analysis. Pearson.  
2. Field, A. (2018). Discovering Statistics Using SPSS. Sage Publications.  
3. Tabachnick, B. G., & Fidell, L. S. (2020). Using Multivariate Statistics. Pearson.  
4. DeVellis, R. F. (2016). Scale Development: Theory and Applications. Sage.  
5. Byrne, B. M. (2016). Structural Equation Modeling with AMOS. Routledge.  
6. Costello, A. B., & Osborne, J. (2005). “Best Practices in Exploratory Factor Analysis.” Practical  
Assessment, Research & Evaluation, 10(7).  
7. MacCallum, R. C., Widaman, K. F., Zhang, S., & Hong, S. (1999). “Sample Size in Factor Analysis.”  
Psychological Methods, 4(1), 84–99.  
8. Gorsuch, R. L. (2015). Factor Analysis: Classic Edition. Routledge.  
9. Brown, T. A. (2015). Confirmatory Factor Analysis for Applied Research (2nd ed.). Guilford Press.  
10. Jöreskog, K. G. (1969). “A General Approach to Confirmatory Maximum Likelihood Factor Analysis.”  
Psychometrika, 34, 183–202.  
www.ijltemas.in  
Page 199