KSPM
Search
- Page Path
- HOME > Search
Special Article
- P>0.05 Is Good: The NORD-h Protocol for Several Hypothesis Analysis Based on Known Risks, Costs, and Benefits
- Alessandro Rovetta, Mohammad Ali Mansournia
- J Prev Med Public Health. 2024;57(6):511-520. Published online September 20, 2024
- DOI: https://doi.org/10.3961/jpmph.24.250
- 700 View
- 63 Download
-
Abstract
Summary
PDF
Supplementary Material - Statistical testing in medicine is a controversial and commonly misunderstood topic. Despite decades of efforts by renowned associations and international experts, fallacies such as nullism, the magnitude fallacy, and dichotomania are still widespread within clinical and epidemiological research. This can lead to serious health errors (e.g., misidentification of adverse reactions). In this regard, our work sheds light on another common interpretive and cognitive error: the fallacy of high significance, understood as the mistaken tendency to prioritize findings that lead to low p-values. Indeed, there are target hypotheses (e.g., a hazard ratio of 0.10) for which a high p-value is an optimal and desirable outcome. Accordingly, we propose a novel method that goes beyond mere null hypothesis testing by assessing the statistical surprise of the experimental result compared to the prediction of several target assumptions. Additionally, we formalize the concept of interval hypotheses based on prior information about costs, risks, and benefits for the stakeholders (NORD-h protocol). The incompatibility graph (or surprisal graph) is adopted in this context. Finally, we discuss the epistemic necessity for a descriptive, (quasi) unconditional approach in statistics, which is essential to draw valid conclusions about the consistency of data with all relevant possibilities, including study limitations. Given these considerations, this new protocol has the potential to significantly impact the production of reliable evidence in public health.
-
SummaryKey Message
The p-value is largely misused in medicine to classify results as “significant” and “non-significant” according to a sharp arbitrary threshold (typically 0.05), focusing only on the null hypothesis of exactly zero effect. Conversely, the NORD-h protocol offers an easy method to assess the degree of incompatibility (disagreement) between data and various meaningful effect sizes using the “s-value”. Unlike the p-value, the s-value is intuitive, representing the number “s” of consecutive heads in as many fair coin tosses. A simple graphical approach is proposed to avoid rigid cutoffs, promoting a nuanced interpretation of statistical findings based on cost-benefit analysis.
First
Prev
