Through this mini-literature-review, this author would like to deliver the following messages. There is a wide agreement among the statistician community that Null Hypothesis Significance Test (NHST) is a never-justified practice that originated from confusions in the early history of modern statistics. The most important conclusion is, the concept of “statistical significance” should be abandoned entirely from statistical analysis practice. Although it is researchers’ desire to substitute intellectual capital for labour, an alternative magic recipe to replace NHST (as a series of allegedly neat and tidy methodological steps) for statistical inference does not exist and it should not exist. It is a matter of fact that most scientific research is exploratory in nature and the formal statistical inference can only play a limited role in scientific inference. Ultimately, it is statistical thinking enables good science. We should always remember that context is king in statistics and the seven words principles for performing statistical analysis without referring to statistical significance are: “Accept uncertainty. Be thoughtful, open, and modest.” With no exception, the messages delivered in this presentation are a reflection of this author’s understanding and interpretation of issues related to statistical inference in general and NHST in specific.
|Publication status||Published - 07 Jul 2021|
|Event||Australian and New Zealand Statistical Virtual Conference, 05-09 July 2021 (ANZSC 2021) - virtual conference, Australia|
Duration: 05 Jul 2021 → 09 Jul 2021
|Conference||Australian and New Zealand Statistical Virtual Conference, 05-09 July 2021 (ANZSC 2021)|
|Period||05/07/21 → 09/07/21|