Comparison of statistical models for individual’s ability index and ranking

ABSTRACT

Economic efficiency demands accurate assessment of individual ability for selection purposes. This study investigates Classical Test Theory (CTT) and Item Response Theory (IRT) for estimating true ability and ranking individuals. Two Monte Carlo simulations and real data analyses were conducted. Results suggest a slight advantage for IRT, but ability estimates from both methods were highly correlated (r=0.95), indicating similar outcomes. The Logistic two-parameter IRT model emerged as the most reliable and rigorous approach.

KEYWORDS:

• Monte Carlo
• logistic and probit models
• item response theory
• classical test theory
• ranking of individuals

Disclosure statement

No potential conflict of interest was reported by the author(s).

Ethical approval

Not applicable, as this study does not directly involve human beings.

Data availability statement

This study utilizes simulated data with a disclosed data generation process in the methodology section. The real data used in this investigation is confidential and cannot be revealed.

Author’s contribution

Javed Iqbal: Conceptualization, Supervision, Data Collection, Methodology, Coding, First Draft

Tanweer Ul Islam: Literature Review, Data Cleaning, Coding, Estimation, Analysis, Final Draft

Additional information

Notes on contributors

Javed Iqbal

Javed Iqbal is a joint director in the State Bank of Pakistan in the Statistics division. His areas of interest are Econometrics, Data aggregation or decomposition, and Machine learning.

Tanweer Ul Islam

Tanweer Ul Islam is a professor in the School of Social Sciences and Humanities at the National University of Sciences and Technology, Islamabad where he has been a faculty member since 2008. Tanweer received his Ph.D. from the International Islamic University, Islamabad. His research interests lie in applied time series, simulation, normality testing and development economics.