Addendum to the article: Misuse of null hypothesis significance testing: Would estimation of positive and negative predictive values improve certainty of chemical risk assessment?
参考文献:1. Bundschuh M, Newman MC, Zubrod JP, Seitz F, Rosenfeldt RR, Schulz R (2013) Misuse of null hypothesis significance testing: Would estimation of positive and negative predictive values improve certainty of chemical risk assessment? Environ Sci Pollut Res 20:7341鈥?347 CrossRef 2. Ioannidis JPA (2005) Why most published research findings are false. Plos Med 2:696鈥?01 3. Ioannidis JP, Tarone R, McLaughlin JK (2011) The false-positive to false-negative ratio in epidemiologic studies. Epidemiol 22:450鈥?56 CrossRef 4. Newman MC (2008) 鈥淲hat exactly are you inferring?鈥?A closer look at hypothesis testing. Environ Toxicol Chem 27:1013鈥?019 CrossRef 5. Newman MC (2010) Fundamentals of Ecotoxicology, 3rd edn. Taylor & Francis/CRC Press, Boca Raton 6. Newman MC (2013) Quantitative ecotoxicology. CRC/Taylor & Francis, Boca Raton 7. Wacholder S, Chanock S, Garcia-Closas M, El Ghormli L, Rothman N (2004) Assessing the probability that a positive report is false: an approach for molecular epidemiology studies. J Nation Cancer Inst 96:434鈥?42 CrossRef
刊物类别:Earth and Environmental Science
刊物主题:Environment Environment Atmospheric Protection, Air Quality Control and Air Pollution Waste Water Technology, Water Pollution Control, Water Management and Aquatic Pollution Industrial Pollution Prevention
出版者:Springer Berlin / Heidelberg
ISSN:1614-7499
文摘
We argued recently that the positive predictive value (PPV) and the negative predictive value (NPV) are valuable metrics to include during null hypothesis significance testing: They inform the researcher about the probability of statistically significant and non-significant test outcomes actually being true. Although commonly misunderstood, a reported p value estimates only the probability of obtaining the results or more extreme results if the null hypothesis of no effect was true. Calculations of the more informative PPV and NPV require a priori estimate of the probability (R). The present document discusses challenges of estimating R.