الفهرس 
contentsOnly 14 pages are availabe for public view
 |  | from | 117 |  |  |
| | | from | 117 | | |
Abstract
Researchers often use sample survey methodology to obtain information about a large aggregate or population by selecting and measuring a sample from that population.Data obtained from surveys are affected by two main sources of error.The first is the sampling error that results from taking a sample instead of enumerating the whole population.The second type of error is the non-sampling error.The main sources of non-sampling error in any survey are non-response bias and response bias.Non-response bias arises from subjects’ refusal to respond and response bias arises from giving incorrect responses.When open or direct surveys are about sensitive matters (e.g., tax evasion habits, addiction, drunken driving and abortion), non-response bias and response bias become serious problems because people do not often wish to give correct information. In order to reduce non-response and response bias, a survey technique different from open or direct surveys was needed to make people comfortable and to encourage truthful answers. Warner (1965) developed such an alternative survey technique that is called ”randomized response” technique. Warner’s randomized response survey technique is designed to eliminate evasive answer bias and keep the respondents’ confidentiality.
Randomized response is a technique used to collect sensitive information from individuals in such a way that survey interviewers and those who process the data do not know which of two alternative questions the respondent has answered.It allows respondents to respond to sensitive issues such as criminal behavior, sexuality, addiction, informal marriage and abortion while remaining confidentiality.It was firstly proposed by S.L. Warner in (1965) and modified by others; see, for example, Greenberg (1969), Liu and Chow (1976), Mangat and Singh (1990), Mangat (1994) and Kim and Warde (2004).