Epidemiology 4 Multiplicity in randomised trials I: endpoints and treatments

By K. Schulz, D. Grimes. 2005

344 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/48a322ab66d616462edcc7be971d77a4a932d669

How researchers see this paper

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

Citations in the corpus

Do p Values Lose Their Meaning in Exploratory Analyses? It Depends How You Define the Familywise Error Rate (2017, unknown): “However, many researchers have questioned the usefulness of universal null hypotheses (Armstrong, 2014; Bender & Lange, 2001; Hurlbert & Lombardi, 2012; O’Keefe, 2003; Matsunaga, 2007; Morgan, 2007; Parascandola, 2010; Perneger, 1998; Rothman, 1990; Schulz & Grimes, 2005).”
LOPSIDED REASONING ON LOPSIDED TESTS AND MULTIPLE COMPARISONS (2012, background): “As Schulz & Grimes (2005) state, 'statistical adjustments for multiplicity provide crude answers to an irrelevant question.”
Best (but oft-forgotten) practices: the multiple problems of multiplicity-whether and how to correct for many statistical tests. (2015, background): “However sensible Schulz and Grimes’ (21) advice is with regard to limiting the number of outcomes, it is infeasible when evaluating complex interventions.”
Coup de Grâce for a Tough Old Bull: “Statistically Significant” Expires (2019, background): “…out their ponderous and arbitrary nature for half a century (e.g., Wilson 1962; Cox 1965; J. A. Nelder [in O’Neill and Wetherill 1971]; Carmer and Walker 1982; Perry 1986; Finney 1988; Mead 1988; Rothman 1990; Keppel 1991; Pearce 1993; Stewart-Oaten 1995; Nakagawa 2004; Schulz and Grimes 2005).”
An introduction to multiplicity issues in clinical trials: the what, why, when and how. (2016, background): “If we test each of the individual outcomes separately at a nominal 5% level and obtain any significant difference, the probability of a spurious claim of significance is higher than the anticipated 5%.(2,16,17) To avoid inflation of the type I error rate, several solutions have been proposed.”