Unmatched count

In psychology and social research, unmatched count, or item count, is a technique to improve, through anonymity, the number of true answers to possibly embarrassing or self-incriminating questions. It is very simple to use but yields only the number of people bearing the property of interest and leads to a larger sampling error than direct questions. It was introduced by Raghavarao and Federer in 1979.[1]

Method

The participants of the survey are divided into two groups at random. One group (the control group) is given a few harmless questions, while the other group gets one additional question (hence the name "unmatched count"), the one about the property of interest. The respondents are to reveal only the number of "yes"-answers they have given. Since the interviewer does not know how they arrived at that number, it is safe to answer the awkward question truthfully. Due to the unmatched count of items, the number of people who answered "yes" to the awkward question can be mathematically deduced.

Example

The control group is asked how many of the following statements apply:

  • I have moved house in the past.
  • I own a pet.
  • I like to go to the theatre.
  • I have never been in a traffic accident.

Let the total number of "yes"-answers from this group be 410.

The second group additionally gets a question concerning the point of interest:

  • I have cheated on an examination.

Let the total number of "yes"-answers from this group be 460.

Evaluation

The number of "yes"-answers in the control group is called the baseline. It is assumed that the second group would have given the same number, were it not for the critical question. Thus, their additional "yes"-answers (50 in the example) are due to the critical question. Their percentage is used to estimate the percentage of cheaters in the population. Let the number of participants in each group be 300. As expectation value, 50 of them answered "yes" to the critical question, meaning that approximately 17% of the population have cheated on examinations.

gollark: Technically, the RFCs act as a standard for the particular behaviour they contain.
gollark: Rewriting in antirust, muahahahahahahahahaħæħæ.
gollark: It should also ship with antivalgrind, which detects unsafe behaviour and makes it much worse.
gollark: Yes. Antirust should make unsafety not just possible and easy but mandatory and maximally unsafe.
gollark: This is unacceptable.

See also

References
  1. D. Raghavarao and W. T. Federer (1979). "Block Total Response as an Alternative to the Randomized Response Method in Surveys". Journal of the Royal Statistical Society, Series B. 41 (1): 40–45.
  • Elisabeth Coutts, Ben Jann (2009). Sensitive Questions in Online Surveys: Experimental Results for the Randomized Response Technique (RRT) and the Unmatched Count Technique (UCT), General Online Research Conference in Vienna
  • Dan R. Dalton, James C. Wimbush, Catherine M. Daily (1994). Using the Unmatched Count Technique (UCT) to estimate base rates for sensitive behavior. Personnel Psychology 47, pp. 817–829
  • Allison M. Ahart, Paul R. Sackett (2004). A New Method of Examining Relationships between Individual Difference Measures and Sensitive Behavior Criteria: Evaluating the Unmatched Count Technique. Organizational Research Methods, Vol. 7, No. 1, pp. 101–114
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.