Statistical Power Analysis can Improve Fisheries Research and Management

TLDR

Possible: "The paper reviews how β, power, effect size, sample size, and variability interrelate, demonstrates how power analysis can guide interpretation and design of future studies and regulations, and recommends routine use of power analysis and shifting the burden of proof onto industry." Mechanism sentences: - "I review relationships among β, power, detectable effect size, sample size, and sampling variability." (already in Purpose) - "I show how statistical power analysis can help interpret past results and improve designs of future experiments, impact assessments, and management regulations." (also in Purpose) But Mechanism label includes these sentences. So one sentence: "The author reviews the mathematical relationships among β, power, effect size, sample size, and variability, and illustrates how power analysis can be applied to interpret past findings and design future experiments, impact assessments, and regulations." Findings sentences: - "However, 52% of those papers drew conclusions as if H0 were true." - "Past statistical power analyses show that abundance estimation techniques usually have high β and that only large effects are detectable." - "I show how statistical power analysis can help interpret past results and improve designs of future experiments, impact assessments, and management regulations." (also in Purpose) - "I make recommendations for researchers and decision makers, including routine application of power analysis, more cautious management, and reversal of the burden of proof to put it on industry, not management agencies." (also Purpose) Findings: The key findings: 52% of papers incorrectly concluded H0 true; past power analyses show high β and only large effects detectable; the paper demonstrates power analysis can help interpret past results and improve designs. Count 4 sentences. Ensure no extra.

Abstract

Ninety-eight percent of recently surveyed papers in fisheries and aquatic sciences that did not reject some null hypothesis (H 0 ) failed to report β, the probability of making a type II error (not rejecting H 0 when it should have been), or statistical power (1 – β). However, 52% of those papers drew conclusions as if H 0 were true. A false H 0 could have been missed because of a low-power experiment, caused by small sample size or large sampling variability. Costs of type II errors can be large (for example, for cases that fail to detect harmful effects of some industrial effluent or a significant effect of fishing on stock depletion). Past statistical power analyses show that abundance estimation techniques usually have high β and that only large effects are detectable. I review relationships among β, power, detectable effect size, sample size, and sampling variability. I show how statistical power analysis can help interpret past results and improve designs of future experiments, impact assessments, and management regulations. I make recommendations for researchers and decision makers, including routine application of power analysis, more cautious management, and reversal of the burden of proof to put it on industry, not management agencies.