Asymptotic Score Test Statistic in Multilevel Models with Application to the Income Tax Payments Data

Zamani Mehreyan, Sedigheh; Kazemi, Ramin

doi:10.22034/jirss.2026.2096683.1234

Asymptotic Score Test Statistic in Multilevel Models with Application to the Income Tax Payments Data

Articles in Press

Document Type : Original Article

Authors

Sedigheh Zamani Mehreyan

Ramin Kazemi

‎Department of Statistics‎, ‎ ‎Imam Khomeini International University‎, ‎Qazvin‎, ‎Iran‎

10.22034/jirss.2026.2096683.1234

Abstract

Multilevel structural equation modeling is a statistical framework of major relevance for research concerned with people’s interpersonal dynamics. The purpose of this study is to determine the asymptotic distribution of score test statistics for hypothesis tests in a multilevel regression. We estimate the model parameters using the EM algorithm. Then, we derive the asymptotic distribution of score test statistics for regression tests. Through simulation studies, the performance of the EM algorithm is evaluated. Additionally, the relative frequency of the regression test is examined. A real data analysis carried out to illustrate the theoretically obtained procedures. The proposed method is then applied to predict the logarithm of the total positive tax liability from individual characteristics and economic characteristics, to demonstrate the practical application of the theoretical findings.

Keywords

EM algorithm

multilevel model

random intercept

random slopes

score test

Subjects

Regression Models

Aitkin M, Longford N. Statistical modelling in school effectiveness studies (with discussion). Journal of the Royal Statistical Society. 1986;149:1–43.
Barendse MT, Rosseel Y. Multilevel SEM with random slopes in discrete data using the pairwise maximum likelihood. British Journal of Mathematical and Statistical Psychology. 2023;76(2):327–352.
Barr DJ. Random effects structure for confirmatory hypothesis testing: keep it maximal. Journal of Memory and Language. 2013;68:255–278.
Bates MD, Castellano KE, Rabe-Hesketh S, Skrondal A. Handling correlations between covariates and random slopes in multilevel models. Journal of Educational and Behavioral Statistics. 2014;39(6):524–549.
Berkhof J, Kampen JK. Asymptotic effect of misspecification in the random part of the multilevel model. Journal of Educational and Behavioral Statistics. 2004;29:201–218.
Bryan ML, Jenkins SP. Multilevel modelling of country effects: a cautionary tale. European Sociological Review. 2016;32:3–22.
Cox DR, Hinkley DV. Theoretical statistics. London: Chapman and Hall; 1974.
Dempster AP, Laird NM, Rubin DB. Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society: Series B (Methodological). 1977;39(1):1–38.
FreesEW. Longitudinal and panel data: Analysis and applications in the social sciences. New York: Cambridge University Press; 2004.
Grund S, Lüdtke O, Robitzsch A. Multiple imputation of missing covariate values in multilevel models with random slopes: a cautionary note. Behavior Research Methods. 2016;48:640–649.
Heisig JP, Schaeffer M, Giesecke J. The costs of simplicity: why multilevel models may benefit from accounting for cross-cluster differences in the effects of controls. American Sociological Review. 2017;82:796–827.
Humberg S, Grund S, Nestler S. Estimating nonlinear effects of random slopes: A comparison of multilevel structural equation modeling with a two-step, a singleindicator, and a plausible values approach. Behavior Research Methods. 2024;.
Johnson RA, Wichern DW. Applied multivariate statistical analysis. 6 ed. Pearson Prentice Hall; 2007.
Kenward MG, Roger JH. Small sample inference for fixed effects from restricted maximum likelihood. Biometrics. 1997;53(3):983–997.
Kim JS, Frees EW. Multilevel modeling with correlated effects. Psychometrika. 2007;72:505–533.
Laird NM, Ware JH. Random-effects models for longitudinal data. Biometrics. 1982;38(4):963–974.
Longford NT. A fast scoring algorithm for maximum likelihood estimation in unbalanced mixed models with nested random effects. Biometrika. 1987;74:817–827.
Oberpriller J, Leite M, Pichler M. Fixed or random? On the reliability of mixed-effects models for a small number of levels in grouping variables. Ecology and Evolution. 2022;12(7):e9062.
Rabe-Hesketh S, Skrondal A. Multilevel and longitudinal modeling using Stata. 2 ed. StataCorp LP; 2008.
Raudenbush SW, Bryk AS. A hierarchical model for studying school effects. Sociology of Education. 1986;12:241–269.
Satterthwaite FE. An approximate distribution of estimates of variance components. Biometrics Bulletin. 1946;2(6):110–114.
Schmidt-Catran AW, Fairbrother M. The random effects in multilevel models: getting them wrong and getting them right. European Sociological Review. 2016;32:23–38.
Wald A. Tests of statistical hypotheses concerning several parameters when the number of observations is large. Transactions of the American Mathematical Society. 1943;54(3):426–482.
Wilks SS. The large-sample distribution of the likelihood ratio for testing composite hypotheses. The Annals of Mathematical Statistics. 1938;9(1):60–62.
Wooldridge JM. Fixed-effects and related estimators for correlated random coefficient and treatment-effect panel data models. Review of Economics and Statistics. 2005;51:385–390.
Zamani Mehreyan S, Sharafi M, Nematollahi A. Large sample properties of the score test statistic in nonlinear regression involving stationary and non-stationary errors: an application in age estimation of European wild rabbits from eye lens weight.Journal of Agricultural, Biological and Environmental Statistics. 2024;.
Zhao Y, Edland SD. Power formulas for mixed effects models with random slope and intercept comparing rate of change across groups. Biostat. 2021;18(1):173–182.