Type S error rates for classical and Bayesian single and multiple comparison procedures

By Andrew Gelman, Francis Tuerlinckx. Computational statistics (Zeitschrift), 2000

330 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/20e06e571827d881f6b2544340e1b97910df84e3

How researchers see this paper

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

In Statistics and Probability

Citations in the corpus

The Connection Between Varying Treatment Effects and the Crisis of Unreplicable Research (2015, background): “First, uncertainty: when studying small effects, it is very possible for a large proportion of statistically significant findings to be in the wrong direction as well as be gross overestimates of the magnitude of the underlying effect (Gelman and Tuerlinckx, 2000).”
Beyond Power Calculations (2014, positive): “We frame our calculations not in terms of Type 1 and Type 2 errors but rather Type S (sign) and Type M (magnitude) errors, which relate to the probability that claims with confidence have the wrong sign or are far in magnitude from underlying effect sizes (Gelman & Tuerlinckx, 2000).”
False discovery rates: a new deal (2016, background): “Along the same lines, Gelman and co-workers (Gelman and Tuerlinckx, 2000; Gelman and others, 2012) suggest focusing on “type S errors,” meaning errors in sign, rather than the more traditional type I errors.”
Multimodel inference in ecology and evolution: challenges and solutions (2011, background): “It should be borne in mind, however, that assigning the incorrect sign to a weak parameter estimate is a possibility in any regression (Gelman & Tuerlinckx, 2000), and further research as to the effects of model averaging on this type of error would be useful.”
Why We (Usually) Don't Have to Worry About Multiple Comparisons (2009, background): “These are both examples of what is referred to as “Type S” (sign) errors (Gelman and Tuerlinckx, 2000).”