Suchergebnisse

The use of quantitative data & multiple tests of hypotheses in political science causes chance to play a significant role in shaping the results. Here, recent statistical work on the likelihood of coincidences is reviewed, & findings are applied to common problems of data analysis in political science, eg, significance testing, model specification, & dummy variable analysis. Several ways that statistical results can appear to be meaningful when they are not are illustrated, & remedies that aid in the assessment of the true probability of the improbable in research results are suggested. 3 Tables, 42 References.