Research Of Some Randomized Response Technique

Sample survey methods and theory come into being and develop from practicality, apply to many domains such as society, economy etc.But in the practical problems,we sometimes need facts about sensitives questions in sampling survey such as tax doding,cheating etc.Attempted open queries about such sensivies issues often result in nonresponse rates or high response biases arising out of willful misstatements or blatant lies. So instead of open surveys,alternative procedures are needed if we are to procure reliable data on such confidential matters,especially the sensitives ones,believed to carry reprehensible stigmas.Warner(1965) introduced the first procedure called the randomized response(RR) technique used for collecting data on sensitive issues while tring to protect respondent privacy.Warner'stechnique was modified by Simmons (1969),Fox and Tracy(1986), Moors (1971),Chaudburi(1987),Kuk(1990),Mangat and Singh(1990),Singh and Singh(1993),Mangat(1994)among oher researchers for irnproving greater cooperation and efficiency.This paper includes four sections of theory. Firstly, it set forth the concepts and the features concerned randomized response(RR) technique basing on the related data of both inside and outside the country, and analyses the statistical effection of randornized response(RR) technique under the deterministic view and stochastic view,further advances the settlement way.This paper introduces five randomized response procedures,especially introduces version.We compare these procedure with the efficient and cooperation.Second, according to the two aspects of raising response and controlling the RRT differences.In this paper generalization of one of the strategies is provided for complex survey designs,wider class of estimation and quantitative charateristics,basing on the outcome of study of both inside and outside the country.Third, we consider an ratio estimation procedure that is a developrnent for some existing investigations,and then provide the suitable ratio estimator for estimating an unknown proportion of people bearing a sensitive characteristic in a given community .It is demonstrated the superiority the proposed procedure over Greenberg(1969) procedure.Final, according to the above and the conditions of our country, we consider the estimation of the ratio of population means when some observations are missing. Randomized response(RR) technique theory is more extended from the theory of one-dimensional sampling survey, and more fits the practicality. It would be at the bottom of important action in sampling survey. But there are many works to investigate.