Some Test Statistics for Testing the Binomial Parameter: Empirical Power Comparison | Science Publications

American Journal of Biostatistics

B. M.G. Kibria¹  Florence George¹ 

关键词: Binomial distribution;    empirical power;    hypothesis testing;    simulation study;    Type I error;    AMS 2000 subject classifications;    primary 62F03;    secondary 62F40;    binomial distribution;    fasting glucose;    binomial proportion;    null hypothesis;   

DOI  :  10.3844/amjbsp.2010.82.93

学科分类：卫生学

来源: Science Publications

【 摘 要 】

Problem statement: The Binomial distribution is one of the most useful probabilitydistributions in the filed of quality control, physical and medical sceinces. Many questions of interestto the health worker related to make inference about the unknown population proportion, parameter ofbinomial distribution. This study considers the problem of hypotheses testing of the parameter of abinomial distribution. Approach: Different test statistics available in literature are reviewed andcompared based on the empirical size and power properties. Since a theoretical comparison is notpossible, a simulation study has been conducted to compare the performance of the test statistics. Toillustrate the findings of the paper, two real life health related data are analyzed. Results: Thesimulation study suggests that some methods have better size and power properties than the other teststatistics. The performnace of the proposed test statistics also depend on the hypothesized value of thebinomial parameter. Conclusions/Recommendations: The practitioners should be careful about thehypothesized value of the binomial parameter p. If the hypothesized value is near 0.5, any test isacceptable for moderate to large sample size. However, for testing the end or small value of p, onemight need very large sample size to have a good power and actual size of the test.

【 授权许可】

Unknown