2026-10-14T03:25:49Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33802864 2026-09-15T15:27:31Z portal_1197 item_type_3 month_year_09_2026

Data for Not so Harmless After All: The Fixed-Effects Model Vera Troeger (24805879) Thomas Plümper (3902578) Economics -- Mathematical models Econometrics -- Mathematical models Monte Carlo method Migrated from ePrints The fixed-effects estimator is biased in the presence of dynamic misspecification and omitted within variation correlated with one of the regressors. We argue and demonstrate that fixed-effects estimates can amplify the bias from dynamic misspecification and that with omitted time-invariant variables and dynamic misspecifications, the fixed-effects estimator can be more biased than the ‘naïve’ OLS model. We also demonstrate that the Hausman test does not reliably identify the least biased estimator when time-invariant and time-varying omitted variables or dynamic misspecifications exist. Accordingly, empirical researchers are ill-advised to rely on the Hausman test for model selection or use the fixed-effects model as default unless they can convincingly justify the assumption of correctly specified dynamics. Our findings caution applied researchers to not overlook the potential drawbacks of relying on the fixed-effects estimator as a default. The results presented here also call upon methodologists to study the properties of estimators in the presence of multiple model misspecifications. Our results suggest that scholars ought to devote much more attention to modeling dynamics appropriately instead of relying on a default solution before they control for potentially omitted variables with constant effects using a fixed-effects specification.<br><br>Data record consists of 3 data files, in .do and .dta format, and a readme file. All Monte Carlo simulations in the paper have been executed with STATA 14 SE 64bit version and the following STATA ado-files installed: tabstatmat.ado , xml_tab.ado . The data files are as follows: 1. nosoharmless_replication_final.do: STATA do-file: runs all MC simulations and generates all tables and figures in the article (tables 1, 2, 3a,b, 4a,b) and the online appendix (A1-A9), this file runs for ca. 60 hours on a machine similar to the one mentioned above. 2. results_mc_absbias_pa_final.dta: STATA data-file: contains all final MC results in a spreadsheet format 3. notsoharmless_replicaton_tables.do: STATA do-file: uses results_mc_absbias_pa_final.dta to generate all tables and figures in the article (tables 1, 2, 3a,b, 4a,b) and the online appendix (A1-A9), this file runs for a few seconds. 2018-03-22T00:00:00Z Dataset Dataset 10.82444/warw.33802864.v1 https://figshare.com/articles/dataset/Data_for_Not_so_Harmless_After_All_The_Fixed-Effects_Model/33802864 CC BY 4.0