2018
DOI: 10.1002/ajpa.23399
|View full text |Cite
|
Sign up to set email alerts
|

The continuing misuse of null hypothesis significance testing in biological anthropology

Abstract: There is over 60 years of discussion in the statistical literature concerning the misuse and limitations of null hypothesis significance tests (NHST). Based on the prevalence of NHST in biological anthropology research, it appears that the discipline generally is unaware of these concerns. The p values used in NHST usually are interpreted incorrectly. A p value indicates the probability of the data given the null hypothesis. It should not be interpreted as the probability that the null hypothesis is true or as… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
30
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 52 publications
(38 citation statements)
references
References 99 publications
0
30
0
Order By: Relevance
“…Recent criticisms of null hypothesis statistical tests (NHST) point out that null hypothesis testing is misused in the sciences, including biological anthropology (Ferguson, ; Smith, ). Critics argue that measures of effects and effect confidence intervals (CIs) are neglected statistical indicators of relationships that are superior to p ‐values because the latter are affected by sample size.…”
Section: Methodsmentioning
confidence: 99%
See 1 more Smart Citation
“…Recent criticisms of null hypothesis statistical tests (NHST) point out that null hypothesis testing is misused in the sciences, including biological anthropology (Ferguson, ; Smith, ). Critics argue that measures of effects and effect confidence intervals (CIs) are neglected statistical indicators of relationships that are superior to p ‐values because the latter are affected by sample size.…”
Section: Methodsmentioning
confidence: 99%
“…Because null hypothesis significance tests (NHST) are considered by some to be insufficient indicators of the relationships of variables (Rosnow & Rosenthal, ; Smith, ) we also include 95% confidence intervals and effect sizes in our results. This aspect of the study is described in more detail below.…”
Section: Research Hypothesesmentioning
confidence: 99%
“…There is currently discussions regarding moving away from the use of the p ≤ 0.05 approach (American Statistical Association 2016), we would recommend that if p-values are presented, they should always be the full, unadjusted p-value and should be accompanied by effect sizes or confidence intervals. Effect sizes or confidence intervals provide greater details regarding hypothesis testing compared to p-values (Smith 2018) and will enhance replication, as studies evaluating small effects in the wake of considerable noise are likely false positives (Gelman 2018), considering a system rewarded by positive findings.…”
Section: Discussionmentioning
confidence: 99%
“…Given the numerous empirical and logical problems associated with conventional null hypothesis testing based on significance levels (e.g., Amrhein, Greenland, & Mcshane, 2019; Halsey, 2019; Smith, 2018), we supplement the above analyses with a Bayesian hypothesis testing approach (Bayesian linear regression). Bayes factors are used to quantify the relative levels of evidence in the collected data for the null and alternative hypotheses.…”
Section: Methodsmentioning
confidence: 99%