Published eLetters
Guidelines
As a forum for professional feedback, submissions of letters are open to all. You do not need to be a subscriber. To avoid redundancy, we urge you to read other people's letters before submitting your own. Name, current appointment, place of work, and email address are required to send a letter, and will be published with your review. We also require that you declare any competing financial interests. Unprofessional submissions will not be considered or responded to.
Jump to comment:
- Page navigation anchor for RE: Author Response to Alger et al.RE: Author Response to Alger et al.
Alger’s defense of testing with p values is informed by a falsificationist approach to science, one in which scientists derive predictions from their theories, collect data, and then judge their predictions as corroborated or refuted.
Alger argues that estimation is not suitable for a falsificationist approach to science. Are p values more suitable? Under current practice: no. Neuroscientists currently test the null hypothesis, not their own (often unspecified) predictions. In fact, the current approach to using p values does not allow the researcher’s predictions to be falsified. Non-significant results, which should be “valuable ‘negative information’ for scientific knowledge” are published at implausibly low rates.
What would it take to use p values according to falsificationist ideals of science? Estimation thinking. That is, researchers would need to think more about effect sizes and uncertainty, enough to derive quantitative predictions from their hypotheses (If our theory is correct, CREB1 enhancement will boost memory by >30%). Then, researchers would need to conduct tests that put those predictions are real risk. That would involve, at a minimum: a) planning for an adequate sample size b) specifying an interval null hypotheses to pro...
Show MoreCompeting Interests: None declared.