Improved Tests for Mediation (2403.02144v1)
Abstract: Testing for a mediation effect is important in many disciplines, but is made difficult - even asymptotically - by the influence of nuisance parameters. Classical tests such as likelihood ratio (LR) and Wald (Sobel) tests have very poor power properties in parts of the parameter space, and many attempts have been made to produce improved tests, with limited success. In this paper we show that augmenting the critical region of the LR test can produce a test with much improved behavior everywhere. In fact, we first show that there exists a test of this type that is (asymptotically) exact for certain test levels $\alpha $, including the common choices $\alpha =.01,.05,.10.$ The critical region of this exact test has some undesirable properties. We go on to show that there is a very simple class of augmented LR critical regions which provides tests that are nearly exact, and avoid the issues inherent in the exact test. We suggest an optimal and coherent member of this class, provide the table needed to implement the test and to report p-values if desired. Simulation confirms validity with non-Gaussian disturbances, under heteroskedasticity, and in a nonlinear (logit) model. A short application of the method to an entrepreneurial attitudes study is included for illustration.
- Aggarwal, S. (2019). A survey-cum-tutorial on approximations to Gaussian Q𝑄Qitalic_Q function for symbol error probability analysis over Nakagami-m𝑚mitalic_m fading channels. IEEE Communications Surveys & Tutorials 21(3), 2195–2223.
- Alwin, D. F. and R. M. Hauser (1975). The decomposition of effects in path analysis. American sociological review 40, 37–47.
- Baron, R. M. and D. A. Kenny (1986). The moderator–mediator variable distinction in social psychological research: Conceptual, strategic, and statistical considerations. Journal of personality and social psychology 51(6), 1173.
- Berger, R. L. (1989). Uniformly more powerful tests for hypotheses concerning linear inequalities and normal means. Journal of the American Statistical Association 84(405), 192–199.
- Julia: A fresh approach to numerical computing. SIAM review 59(1), 65–98.
- Cohen, J. D. (1988). Noncentral chi-square: Some observations on recurrence. The American Statistician 42(2), 120–122.
- The effect of control systems on trust and cooperation in collaborative environments. The Accounting Review 80(2), 477–500.
- Davison, A. C. (2003). Statistical models, Volume 11. Cambridge university press.
- Sample size for studying intermediate endpoints within intervention trials or observational studies. American Journal of Epidemiology 136(9), 1148–1159.
- Hayes, A. F. (2017). Introduction to mediation, moderation, and conditional process analysis: A regression-based approach. Guilford publications.
- Causal analysis after haavelmo. Econometric Theory 31(1), 115–151.
- Econometric mediation analyses: Identifying the sources of treatment effects from experimentally estimated production technologies with unmeasured and mismeasured inputs. Econometric reviews 34(1-2), 6–31.
- Lehmann, E. L. (1952). Testing multiparameter hypotheses. The Annals of Mathematical Statistics 23(4), 541–552.
- The role of attitude toward the ad as a mediator of advertising effectiveness: A test of competing explanations. Journal of marketing research 23(2), 130–143.
- The intermediate endpoint effect in logistic and probit regression. Clinical Trials 4(5), 499–513.
- A comparison of methods to test mediation and other intervening variable effects. Psychological methods 7(1), 83.
- A note on testing two-dimensional normal mean. Annals of the Institute of Statistical Mathematics 39(3), 489–495.
- The emperor’s new tests. Statistical Science 14(4), 355–369.
- The moderating role of social ties on entrepreneurs’ depressed affect and withdrawal intentions in response to economic stress. Journal of Organizational Behavior 33(6), 789–810.
- Van Garderen, K. J. and N. P. A. Van Giersbergen (2021). A nearly similar powerful test for mediation. arXiv preprint arXiv:2012.11342.
- Van Garderen, K. J. and N. P. A. Van Giersbergen (2022). On the optimality of the LR test for mediation. Symmetry 14(178).
- VanderWeele, T. (2015). Explanation in causal inference: methods for mediation and interaction. Oxford University Press.
- Vaughan, R. J. and W. N. Venables (1972). Permanent expressions for order statistic densities. Journal of the Royal Statistical Society: Series B (Methodological) 34(2), 308–310.
- White, H. (1980). A heteroskedasticity-consistent covariance matrix estimator and a direct test for heteroskedasticity. Econometrica: journal of the Econometric Society 48(4), 817–838.
- Wolfram Research, I. (2022). Mathematica, Version 13.1. Champaign, IL, 2022.