Why P Values Are Not a Useful Measure of Evidence in Statistical Significance Testing

By R. Hubbard, D. University, Rachael Lindsay. 2008

238 citations recorded by the source corpus.

Subfields: General Decision Sciences, Management Science and Operations Research, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/a0936e9957ad740d9b766713e1b4343db91157ea

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In General Decision Sciences

In Management Science and Operations Research

In Statistics and Probability

Citations in the corpus

Abandon Statistical Significance (2017, background): “Second, because it is a poor measure of the evidence for or against a statistical hypothesis (Edwards et al. , 1963; Berger and Sellke, 1987; Cohen, 1994; Hubbard and Lindsay, 2008).”
A comparison of informal and formal acceptability judgments using a random sample from Linguistic Inquiry 2001--2010 (2013, background): “…are true of the world, and ask how likely a given hypothesis would be under that assumption (e.g., Gallistel, 2009; Kruschke, 2011; and for accessible reviews of the controversies surrounding NHT, see Shaver, 1993; Cohen, 1994; Nickerson, 2000; Balluerka et al., 2005; Hubbard and Lindsay, 2008).”
Statistical Significance and the Dichotomization of Evidence (2017, background): “Savage 1963; Berger and Sellke 1987; Cohen 1994; Hubbard and Lindsay 2008; Johnson 2013).”
Reconnecting p-Value and Posterior Probability Under One- and Two-Sided Tests (2018, background): “Hubbard and Lindsay (2008) showed that p-value tends to exaggerate the evidence against the null hypothesis.”
Replication Research and Special Education (2016, result): “Hubbard and Lindsay (2008) explained how erroneous beliefs about p values result in false impressions that the statistic indicates (a) results occurred by coincidence, (b) results are very likely replicable, (c) the alternative hypothesis is true, (d) obtained results are important (i.e.,…”
A tutorial on a practical Bayesian alternative to null-hypothesis significance testing (2011, background): “This comparison suggests that from the Bayesian perspective, researchers should be very cautious when interpreting evidence for an effect based on an NHST p value that hovers near .05 (see also Hubbard & Lindsay, 2008 ).”
Significance tests as sorcery: Science is empirical—significance tests are not (2012, unknown): “…Fisher, 1955, 1956; Gigerenzer, 1987, 1993, 2004; Gigerenzer et al., 1989; Gill, 1999; Granaas, 2002; Greenwald, 1975; Hubbard & Armstrong, 2006; Hubbard & Lindsay, 2008; Hubbard & Ryan, 2000; Jones & Tukey, 2000; Kirk, 1996, 2003; Lindsay, 1995; Lykken, 1968, 1991; Meehl, 1967, 1978, 1990;…”
Valid P-Values Behave Exactly as They Should: Some Misleading Criticisms of P-Values and Their Resolution With S-Values (2019, result): “By this measure, and contrary to certain commentaries (e.g., Goodman 1999; Sellke et al. 2001; Hubbard and Lindsay 2008), P-values do not overstate evidence against hypotheses or models: The observed p is just a hypothetical probability or percentile computed from H and A.”