Findings may depend on the particular groups researchers select.

Evidence

Revealing as these results are, our sampling of groups still is not fully representative. Although many were picked according to our pilot test, some were selected on the basis of our theories and our curiosities. One might argue that the empirical support emerges from the particular groups used. — Susan T. Fiske et al., A Model of (Often Mixed) Stereotype…, 158

Categorization

• XREF: connects to: Factor analysis results hinge on researchers’ many discretionary decisions. — Bob Altemeyer, The Authoritarian Specter, 2597; Comparing analyses across differently defined populations reveals selection bias. — Gary Goertz, Social Science Concepts: A User’s Guide, 1095; Identification might operate at a different level than researchers measured. — John Drury and Rupert Brown and Roberto González and Daniel Miranda, Emergent social identity and observing…, 120 (+4 more)

Broader Connections

• Disagreement between studies can stem from method and sample differences, not real findings. #corroborates (0.90)
• Comparing analyses across differently defined populations reveals selection bias. #exemplifies (0.88) — Gary Goertz, Social Science Concepts, 1095
• Factor analysis results hinge on researchers’ many discretionary decisions. #expands (0.85) — Bob Altemeyer, The Authoritarian Specter, 2597
• Contact studies vary in how they generalize findings beyond immediate settings. #exemplifies (0.82) — Thomas F. Pettigrew, Linda R. Tropp, A Meta-Analytic Test of Intergroup…, 78
• Survey correlations may be artifacts of a single source providing both predictors and outcomes #exemplifies (0.80)
• Identification might operate at a different level than researchers measured. #complicates (0.78) — John Drury and Rupert Brown and Roberto González and Daniel Miranda, Emergent social identity and observing…, 120
• Publication bias can be detected through sample-size and effect-size correlations. #exemplifies (0.72) — Thomas F. Pettigrew, Linda R. Tropp, A Meta-Analytic Test of Intergroup…, 47