Elementary Statistical Modeling for Applied Biostatistics
Copyright 2018 Jeffrey A. Walker
More cynically, one could also well ask “Why has medicine not adopted frequentist inference, even though everyone presents P-values and hypothesis tests?” My answer is: Because frequentist inference, like Bayesian inference, is not taught. Instead everyone gets taught a misleading pseudo-frequentism: a set of rituals and misinterpretations caricaturing frequentist inference, leading to all kinds of misunderstandings. – Sander Greenland
We use statistics to learn from data with uncertainty. Traditional introductory textbooks in biostatistics implicitly or explicitly train students and researchers to “discover by p-value” using hypothesis tests (Chapter 9). Over the course of many chapters, the student learns to use something like a dichotomous key to choose the correct “test” for the data at hand, compute a test statistic for their data, compute a \(p\)-value based on the test statistic, and compare the p-value to 0.05. Textbooks typically give very little guidance about what can be concluded if \(p < 0.05\) or if \(p > 0.05\), but many researchers conclude (incorrectly) they have “discovered” something if \(p < 0.05\) but found “no effect” if \(p > 0.05\).
Researchers learn almost nothing useful from a hypothesis test. True, a \(p\)-value is evidence against the null, and thus, a tool to dampen the frequency that we are fooled by randomness. But if we are investigating the effects of an increasingly acidified ocean on coral growth, \(p=0.002\) may be evidence of an effect of the experimental intervention, but, from everything we know about pH and cell biology, it would be absurd to conclude from any data that pH does not affect growth. Instead, we want to know the magnitude of the effect and our uncertainty in estimating this magnitude. We can use this magnitude and uncertainty to make predictions about the future of coral reefs, under different scenarios of ocean acidification. We can use the estimated effects and uncertainty to model the consquences of the effects of acidification on coral growth on fish production or carbon cycling.
The “discovery by p-value” strategy, or Null-Hypothesis Significance Testing (NHST), has been criticized by statisticians for many, many decades. Nevertheless, introductory biostatistics textbooks written by both biologists and statisticians continue to organize textbooks around a collection of hypothesis tests, with little emphasis on estimation and uncertainty.
This book is an introduction to the analysis of biological data using a statistical modeling approach. As an introduction, the focus will be linear models and extensions of the linear models including linear mixed models and generalized linear models. Linear models are the engine behind many hypothesis tests but the emphasis in statistical modeling is estimation and uncertainty instead of test statistics and \(p\)-values. A modeling view of statistics is also more coherent than a dichotomous key strategy.