Significance tests as sorcery: Science is empirical—significance tests are not

141 citations recorded by the source corpus.

How researchers see this paper

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

A new global policy regime founded on invalid statistics? Hanushek, Woessmann, PISA, and economic growth (2017, background): “If the sample size is sufficiently large, any relationship and effect can be statistically significant (Lambdin 2012; Komatsu, Shinohara, and Otsuki 2015).”
Design Science Methodology for Information Systems and Software Engineering (2014, background): “Menzies [35] summarizes classical theories of counterfactual causation.”
Fair Statistical Communication in HCI (2016, background): “This task is necessarily subjective, but it is our job as scientists to carry it out (Thompson, 1999; Lambdin, 2012).”
The Mediation Myth (2015, background): “Significance testing is increasingly criticized in psychology, education, economics, and other disciplines as unscientific and unempirical (Kline, 2013; Lambdin, 2012).”
Assessing statistical aspects of test fairness with structural equation modelling (2013, background): “A drawback of both methods just described is that the selection of a reference group or marker variable may be arbitrary. Also, the reference-group method and the marker-variable method both require a homogeneity (invariance) assumption, but of a different type for each method. Because all factor va”