You are not currently logged in.
Access JSTOR through your library or other institution:
Small-Sample Confidence Intervals for p1 - p2 and p1/p2 in 2 × 2 Contingency Tables
Thomas J. Santner and Mark K. Snell
Journal of the American Statistical Association
Vol. 75, No. 370 (Jun., 1980), pp. 386-394
Stable URL: http://www.jstor.org/stable/2287464
Page Count: 9
You can always find the topics here!Topics: Confidence interval, Confidence limits, Mathematical intervals, Statistics, Binomials, Proportions, Probabilities, Ratios, Biometrics, Integers
Were these topics helpful?See somethings inaccurate? Let us know!
Select the topics that are inaccurate.
Preview not available
Consider two binomial populations Π1 and Π2 having "success" probabilities p1 in (0, 1) and p2 in (0, 1), respectively. This article studies the problem of constructing small-sample confidence intervals for the difference of the success probabilities,
$\Delta \equiv p_1 - p_2$ and their ratio (the "relative risk"), $\rho \equiv p_1/p_2$ based on independent random samples of sizes n1 and n2 from Π1 and Π2, respectively. These are nuisance parameter problems; hence the proposed intervals achieve coverage probabilities greater than or equal to their nominal (1 - α) levels. Three methods of constructing intervals are proposed. The first one is based on the well -known conditional intervals for the odds ratio $\psi \equiv p_1(1 - p_2)/p_2(1 - p_1)$. It yields easily computable Δ and ρ intervals. The second method directly generates unconditional intervals of the desired size. An algorithm is given for producing the intervals for arbitrary n1 and n2. The 2 × 2 case is given as an illustrative example. The third method constructs unconditional intervals based on a generalization of the classical (Fisher) tail method. Some comparisons are made.
Journal of the American Statistical Association © 1980 American Statistical Association