User-friendly computer programs so econometricians can run the a priori procedure
Main Article Content
In the 2019 special issue of Econometrics on significance testing and alternatives, Trafimow (2019) provided an alternative, termed the a priori procedure (APP). The APP involves finding the necessary sample size to meet prior specifications for precision and confidence and Trafimow reviewed equations for performing the APP. But the Trafimow article is limited in two important ways. Most important, the crucial equations must be solved by iteration, thereby rendering them impractical without the aid of relevant programming. The present work addresses the limitation by providing links to user-friendly programs, along with instructions, so even researchers unsophisticated in mathematics or statistics can use the APP. An additional limitation is that the APP bears a surface resemblance to power analysis. Although Trafimow had explained qualitatively why the APP and power analysis differ, there were no quantitative demonstrations. In contrast, the present article provides quantitative demonstrations to increase the clarity of the distinction. A conclusion that comes out of the quantitative demonstrations is that power analysis, as it is conventionally used, causes researchers to use insufficient sample sizes; an ironic conclusion as an important reason for researchers to perform power analyses is to address the problem of insufficient sample sizes. Thus, the present work is a follow-up piece to the previous Econometrics article because it addresses two important limitations of that article.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
- Paolella MS. Linear Models and Time-Series Analysis: Regression, ANOVA, ARMA and GARCH, Chichester: John Wiley and Sons, 2018.
- Trafimow D. Using the Coefficient of Confidence to Make the Philosophical Switch From A Posteriori to A Priori Inferential Statistics. Educational & Psychological Measurement, 2017, 77: 831-854. https://doi.org/10.1177/0013164416667977
- Trafimow D. A frequentist alternative to significance testing, p-values, and confidence intervals. Econometrics, 2019, 7(2): 1-14.
- Trafimow D and Michael M. Editorial. Basic and Applied Social Psychology, 2015, 37: 1-2.
- Trafimow D, Wang T and Wang C. From a sampling precision perspective, skewness is a friend and not an enemy! Educational and Psychological Measurement, 2019, 79(1): 129-150. https://doi.org/10.1177/0013164418764801
- Trafimow D, Wang T and Wang C. Making the a priori procedure (APP) work for differences between means. Educational and Psychological Measurement, 2020, 80: 186-198. https://doi.org/10.1177/0013164419847509
- Wang C, Wang T, Trafimow D, et al. Necessary sample size for estimating the scale parameter with specified closeness and confidence. International Journal of Intelligent Technologies and Applied Statistics, 2019, 12: 17-29.
- Wasserstein RL, Schirm AL and Lazar NA. Moving to a world beyond “p ¡ 0:05”. The American Statistician, 2019, 73(51): 1-19. https://doi.org/10.1080/00031305.2019.1583913