Simulation Study of Sequential Probability Ratio Test (SPRT) in Monitoring an Event Rate
Unlike the classical hypothesis test, the method of sequential probability ratio test (SPRT) checks the outcome sequentially. Based on the outcome, the test can have one of three test results: reject the null hypothesis, accept the null hypothesis, or continue the SPRT procedure. Consequently, the SPRT method may reduce the required sample size for performing a test as compared to a classical hypothesis test. A simulation study of SPRT was performed. A variety of comparisons between p0 and p1 were simulated with p0 =0.001 and p1 between 0.0011 and 0.0023. The target rates of the 12 time points for each group were from 0 out of 10^4 to 30 out of 10^4 with a constant increment of 2/10^4. The results showed that the larger the difference between p0 and p1, the quicker one could reject the null hypothesis. Therefore, we can expect a quicker response when p0/p1 has larger differences.
School:University of Cincinnati
School Location:USA - Ohio
Source Type:Master's Thesis
Keywords:key word sprt sequential probability ratio test simulation study
Date of Publication:07/16/2009