Overdispersion Tests in Count-Data Analysis

Bibliographic Data

ID13653464
AuthorsJaume Vives (0000-0001-5412-7275, Universitat Autonòma de Barcelona, corresponding author), Josep-María Losilla (0000-0002-5140-5847, Universitat Autonòma de Barcelona), Maria F Rodrigo (0000-0002-9209-7377, Universitat de València), Maria-Florencia Rodrigo (Universitat de València), Mariona Portell (0000-0002-5939-6842, Universitat Autonòma de Barcelona)
Year2008
Volume103
Issue1
Pages145-160
Publication date2008-08-01
Open AccessYes
TypeARTICLE
VenuePsychological Reports (JOURNAL)
Journal identifiersISSN: 0033-2941 • E-ISSN: 1558-691X
PublisherSAGE Publishing (PUBLISHER • US)
DOI10.2466/pr0.103.1.145-160
PMID18982948
OpenAlexW2029626907
LanguageEN
References cited19

Count data are commonly assumed to have a Poisson distribution, especially when there is no diagnostic procedure for checking this assumption. However, count data rarely fit the restrictive assumptions of the Poisson distribution. The violation of much of such assumptions commonly results in overdispersion, which invalidates the Poisson distribution. Undetected overdispersion may entail important misleading inferences, so its detection is essential. In this study, different overdispersion diagnostic tests are evaluated through two simulation studies. In Exp. 1, the nominal error rate is compared under different sample sizes and lamda conditions. Analysis shows a remarkable performance of the chi2 df test. In Exp. 2 and 3, statistical power is compared under different sample sizes, lamda, and overdispersion conditions. Chi2 and LR tests provide the highest statistical power

Count data · Overdispersion · Poisson distribution · Statistics · Mathematics · Odor and Emission Control Technologies · Psychology · Statistical Methods and Bayesian Inference · Water Quality and Resources Studies

Tools

Open DOISci-Hub