Search

This paper proposes an alternative randomized response technique by improving existing works on tripartite randomized response technique (TRRT) using unrelated questions. To improve the technique, this work studies TRRT under sampling with unequal probabilities with or without replacement. The study of percentage relative efficiency shows that the proposed estimator is far better than the Hybrid Tripartite Randomized Response Technique with increase in the sensitive character and that of the unrelated character. In addition, conducting survey using both the proposed technique and direct (traditional) technique shows that the proposed technique is more efficiency than the direct technique of data collection.

Obtaining correct responses to sensitive questions in social and behavioural researches is an ancient problem in survey research with respondents misreporting on sensitive behaviours or giving false response to protect themselves. This paper develops an alternative unbiased estimator by modifying the dichotomous randomized response technique model to tackle this problem. The proposed estimator was compared numerically with conventional ones by considering different practicable and suitable design choices. Proposed model was also considered when sampling with unequal probabilities with or without replacement. It was observed that the proposed estimator performs efficiently than the conventional ones. As the proposed model captures progressively more people involved in the sensitive attribute, the model outperforms other models considered. Therefore, social and behavioural researchers can now obtain correct and valid responses from sensitive behavioural researches with ease in order to make informed and reliable decisions.

In this paper, a new randomized response technique has been proposed that combines the unrelated question randomized response technique and tripartite randomized response technique. The relative efficiency of the newly proposed Randomized Response technique over the existing Randomized Response technique was obtained. It was observed that the relative efficiency of the proposed technique over the tripartite RRT increases with increase in πA and πU. The applicability of the proposed technique was also shown. However, it has been shown that the proposed technique performs better than the conventional ones.

The study examined the prevalence of two related sensitive characters: induced abortion and multiple sexual partners among women of Akure, the state capital of Ondo state, Nigeria using improved randomized response technique (RRT) for two sensitive attributes (IRRT2). Also, the direct method of data collection was used in collecting information on the two sensitive characters, these were further compared with the IRRT2. A wide gap was noticed between the two methods as response rate increased tremendously with the use of IRRT2. The data collected also confirm the fact that RRT is far more efficient than direct method.

La malhonnetete academique est restee endemique dans les etablissements d'enseignement superieur, malgre les efforts deployes pour la combattre. Des recherches anterieures sur l'etat de la malhonnetete academique parmi les universitaires utilisent des methodes traditionnelles qui conduisent a des fausses reponses ou a des non-reponsse. Cependant, l'utilisation de techniques de reponses aleatoires a ete demontree theoriquement plus efficace que la methode traditionnelle avec quelques applications. Par consequent, cet article evalue le niveau de plagiat et de pratiques non-orthodoxes en appliquant une technique amelioree de reponses randomisees pour deux attributs sensibles (IRRT2). Puis elle est comparee aux methodes traditionnelles de collecte de donnees. Une enquete en ligne a ete realisee dans la plaeforme Google, aupres de 240 personnes d'Afrique, d'Amerique, d'Asie et d'Europe. Les resultats ont montre que le plus haut niveau de plagiat est enregistre parmi les universitaires de carriere intermediaire (10-19 ans). Ces travaux ont egalement revele qu'il serait peut-etre necessaire de minimiser la dependance excessive vis-a-vis des certificats et des articles de journaux en tant que moyen principal de promotion parmi les universitaires car cela reduirait le desespoir des enseignants et des etudiants. L'etude recommande egalement l'utilisation de la methode IRRT2 au lieu de la methode traditionnelle car elle conduit a des resultats optimaux.

Substance use disorder is often viewed as a sensitive issue as persons with the disorder keep their status as secretive as possible. This study measures the prevalence of substance use disorder among residents of Akure Metropolis. Tripartite Randomized Response Technique (TRRT) and the Direct Method (DM) were applied in the estimation of proportion. We also compared mean substance use disorder by respondents’ demographic characteristics and self-medication. The proportion was estimated as 0.575 using TRRT while DM gave 0.115 with variances 0.003 and 0.102, respectively. Hence, high rate of substance use disorder in the studied population with predominantly youths’ involvement. Key words : Direct Method, Estimation, Self-Medication, Substance Use Disorder, Tripartite Randomized Response Techniques.

We proposed new and more ecient estimators for estimating population proportion of respondents belonging to two related sensitive attributes in survey sampling by extending the work of Mangat(1994). Our proposed estimators are more ecient than Lee et al (2013) simple and crossed model estimators as the population proportion of possessing the sensitive attribute increases. Keywords: Eciency, Proportion Estimation, Randomized Response Techniques, Reliable Information, Unbiased Estimation