This page contains the supplementary materials for the manuscript 'Why checking model assumptions using null hypothesis significance tests does not suffice'. It contains the following files:
SPSS-files for the analysis of the motivating example using NHST:
- 'Fictional data for example.sav'. This file contains the data that were created manually to illustrate the possible issues that arise when using NHST to determine whether a model assumption should be accepted.
- 'SPSS syntax for example.sps', which contains the syntax for running the independent sample t-test on the data.
- 'SPSS output t-test example.spv', containing the output that is obtained after running the syntax.
Files concerning the Bayes factor test of Boeing-Messing, van Assen, Hofman, Hoijtink, and Mulder (2016) for equality of variances:
- 'Instructions for Bayes factor test.docx', which contains instructions for applying the procedure (instructions presented as they appear in Boeing-Messing et al. (2016)
- 'Output BF test unequal prior probability.bmp', containing the output obtained when using a prior probability of .1 for the null hypothesis.
- 'Output BF test equal prior probability.bmp', containing the output obtained when using a prior probability of .5 for the null hypothesis.
File for producing the results presented in Table 1:
- 'Posterior plausibility - Table 1.xlsx', a Microsoft Excel file that can be used to obtain the posterior plausibility under various conditions, which was used to obtain the results in Table 1 of the manuscript.
References:
- Boeing-Messing, F., van Assen, M. A., Hofman, A. D., Hoijtink, H., \& Mulder, J. (2017). Bayesian evaluation of constrained hypotheses on variances of multiple independent groups. *Psychological Methods, 22*(2), 262-287.