DSpace Repository

Models for sequentially selecting between two and three experiments for optimal estimation of prevalence rate with imperfect tests

Show simple item record

dc.contributor.author Matiri, George Munene
dc.date.issued 2017-09
dc.date.accessioned 2019-11-20T12:10:36Z
dc.date.available 2019-11-20T12:10:36Z
dc.identifier.uri http://41.89.96.81:8080/xmlui/handle/123456789/2085
dc.description.abstract The idea of pool testing originated from Dorfman during the World War II as an economical method of testing blood samples of army inductees in order to detect the presence of infection. Dorfman proposed that rather than testing each blood sample individually, portions of each of the samples can be pooled and the pooled sample tested first. If the pooled sample is free of infection, all inductees in the pooled sample are passed with no further tests otherwise the remaining portions of each of the blood samples are tested individually. Apart from classification problem, pool testing can also be used in estimating the prevalence rate of a trait in a population which was the focus of our study. In approximating the prevalence rate, one-at-a-time testing is time consuming, non-cost effective and is bound to errors hence pool testing procedures have been proposed to address these problems. Despite these procedures, when pool testing strategies are used using imperfect kits, there tend to be loss of sensitivity. Lost sensitivity of a test is recovered by retesting pools classified positive in the initial test. This study has developed statistical models which are used to sequentially select some combination of two or three experiments when the sensitivity and specificity of the test kits is less than 100%. The experiments are selected sequentially at each stage so that the information obtained at a given stage is used to determine the experiment to be carried out in the subsequent stage. To accomplish this, the study has employed the method of maximum likelihood estimation in obtaining the estimators. The Fisher information of different experiments is compared and the cut off values where both experiments have the same Fisher information is calculated. The joint experiment models while choosing between two experiments and joint experiment model while choosing between three experiments obtained in this study are found to be more superior to the existing one–at-a-time, pooled and pooled with retesting experiments. Furthermore, asymptotic relative efficiency (ARE) of the joint two and three experiment models are computed and the joint three experiment model found to perform better. en_US
dc.language.iso en en_US
dc.publisher Egerton University en_US
dc.subject Prevalence rate with imperfect tests en_US
dc.title Models for sequentially selecting between two and three experiments for optimal estimation of prevalence rate with imperfect tests en_US
dc.type Thesis en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account