Browsing by Author "Adepetun, A. O."
Now showing 1 - 6 of 6
Results Per Page
Sort Options
Item Bayesian Analysis of Kim and Warde Randomized Response Technique Using Alternative Priors(American Journal of Computational and Applied Mathematics, 2014) Adepetun, A. O.; Adewara, A. A.In this paper, we developed the Bayesian estimators of the population proportion of a stigmatized attribute using Kumaraswamy and Generalised Beta prior distributions when data were obtained through the Randomized Response Technique (RRT) proposed by Kim and Warde [15]. We validated our newly developed Bayesian estimators for a wide range of the designed values of the population proportion at varying sample sizes. It was observed that our newly developed Bayesian estimators performed significantly better than the Bayesian estimator developed by Hussain and Shabbir [12] for relatively small as well as moderate sample sizes. However, the reverse was the case for very large sample sizes.Item BAYESIAN ESTIMATION OF POPULATION PROPORTION OF A STIGMATIZED ATTRIBUTE USING A FAMILY OF ALTERNATIVE BETA PRIORS(International Journal of Scientific & Engineering Research, 2015) Adepetun, A. O.; Adewara, A. A.In this study, we have developed the Bayes estimators of the population proportion of a stigmatized attribute when data were gathered through the randomized response technique (RRT) put forward by Hussain and Shabbir [9]. Using both the Kumaraswamy (KUMA) and the Generalised (GLS) beta distributions as a family of alternative beta priors, superiority of the derived Bayes estimators was established for a large interval of the values of the population proportion. We observed that for small, moderate as well as large sample sizes, the alternative Bayes estimators were better than the Bayes estimator proposed by Hussain and Shabbir [10] when a simple beta prior was usedItem ESTIMATION OF POPULATION PROPORTION OF STIGMATIZED ATTRIBUTE USING BAYESIAN APPROACH(Bulgarian Journal of Science and Education Policy, 2019) Adepetun, A. O.; Adewara, A. A.. Bayesian Approach to Randomized Response Technique has been a technique for estimating the population proportion, especially of respondents possessing stigmatized attributes such as induced abortion, use of drugs and tax evasion. In this paper, we propose Bayesian estimators of population proportion of a stigmatized attribute assuming Kumaraswamy and the generalised beta prior using life data on induced abortion. The newly proposed Bayesian estimators were validated numerically for a large interval of the designed values of the population proportion at different sample sizes. It was observed that the newly developed Bayesian estimators were more sensitive in capturing stigmatized attribute than the Bayesian estimator developed by Hussain & Shabbir (2012) for relatively small, moderate as well as large sample sizes.Item Extension of Mangat Randomized Response Technique Using Alternative Beta Priors(Punjab University, 2016) Adepetun, A. O.; Adewara, A. A.In this study, an extension of Mangat Randomized Response Technique using alternative beta priors has been considered and new Bayes estimators of population proportion of respondents possessing stigmatized attribute were developed when data were gathered through administration of survey questionnaire on induced abortion on 300 matured women in the metropolis. Dominance picture of the proposed Bayes estimators has been portrayed for a wide range of values of population proportion assuming alternative Beta distributions as Prior information. It is observed that the proposed Bayes estimators performed better than the Bayes estimator proposed by Hussain et al [15] when a simple Beta prior was used for small, medium as well as large sample sizes respectively. This is evident as our proposed Bayes estimators have least mean squared errors (MSEs) as π approaches one.Item New Bayesian Estimators for Randomized Response Technique(Malaysian Journal of Applied Sciences, 2017) Adepetun, A. O.; Adewara, A. A.This paper proposes new Bayesian estimators of the population proportion of a sensitive attribute when life data were collected through the administration of questionnaires on abortion on 300 matured women in some selected hospitals in Akure, Ondo State, Nigeria. Assuming both the Kumaraswamy (KUMA) and the generalised (GLS) beta distributions as alternative beta priors, efficiency of the proposed Bayesian estimators was established for a wide interval of the values of the population proportion (π). We observed that for small, medium as well as large sample sizes, the developed Bayesian estimators were better in capturing responses from respondents than the conventional simple beta estimator proposed by Hussain and Shabbir (2009a) as π approaches one.Item New Stratified Bayesian Estimators Using Warner’s Randomized Response Technique Through Mixed Priors(JOURNAL OF SCIENTIFIC RESEARCH, 2018) Adepetun, A. O.; Adewara, A. A.In this paper, we propose new stratified Bayesian estimators of population proportion of a sensitive trait by adopting a mixture of alternative beta distributions as quantification of prior information in a stratified random sampling situation. Data were collected through Warner’s randomized response technique. To study the performance of the newly developed stratified estimators, mean squared error and absolute bias were used as performance criteria. The proposed estimators were compared with the existing one. We observed that the proposed estimators are more sensitive to responses than the existing one at various sample sizes respectively