Pitfalls of post-model-selection testing: experimental quantification

Traditional specification testing does not always improve subsequent inference. We demonstrate by means of computer experiments under which circumstances, and how severely, data-driven model selection can destroy the size properties of subsequent parameter tests, if they are used without adjusting for the model-selection step. The investigated models are representative of macroeconometric and microeconometric workhorses. The model selection procedures include information criteria as well as sequences of significance tests (“general-to-specific”). We find that size distortions can be particularly large when competing models are close, with closeness being defined relatively to the sample size.     

Will Teichert 65 Jahre

Ohne Zusammenfassung     

On the Utility of E-Learning in Statistics

Students of introductory courses consider statistics as particularly difficult, as the understanding of the underlying concepts may require more time and energy than for other disciplines. For decades statisticians have tried to enhance understanding with the help of technical solutions such as animation, video or interactive tools. However, it is not clear if the added value generated by these e‐learning tools justifies the work invested. In this paper the experience with various e‐learning solutions in terms of utility and the impact on teaching is discussed.