In surveys either social or experimental, it is sometimes necessary to compare certain characteristics. Odds ratio is a method that replaces risk ratio that works with responses in binary numbers. But if we have to compare say responses in a survey sampling, a ratio of means may provide basic information on comparison. Though the sample odds ratio is not difficult to handle for moderate and large samples, but if one or more of the cells in the contingency table have a small value, the sample odds ratio can be biased and show evidence of high variance. A number of alternative estimators of the odds ratio have been proposed by various authors In this paper we develop a new statistic for a corruption perception index (CPI). The ratio of any two CPIs is unit less and is interpreted as odds type ratio.
Discussion(0)
No comments yet. Be the first to comment.