Choosing the optimal unconditioned test for comparing two independent proportions

Abstract The most powerful non-asymptotic unconditioned method for comparing two proportions (independent samples) is that of Barnard (1945), but the complexity of computation has led to several simplifying versions being produced. There is no complete global comparison of these (though there are some partial ones, such as Haber's, 1987), nor has there been an evaluation of the loss incurred by not using Barnard's method. In this paper all existing relevant versions (including Barnard's, and one proposed by the authors) for a wide range of sample sizes are compared, as well as for one-and two-tailed tests (only the second case has been dealt with in recent literature), and a conclusion is drawn about the suitability of the new method proposed. The comparison is effected on the basis of the new criterion of “mean power”, and the other customary criteria for comparing methods, based on the comparison of their powers in each point of the parametric space, are criticized. The new criterion can be applied to all tests based on discrete random variables. Finally, given the large number of methods proposed in the relevant literature for solving this problem, the authors classify the same in function of their precision and their complexity of computation.

[1]  G. Upton.  A Comparison of Alternative Tests for the 2 Times 2 Comparative Trial , 1982 .

[2]  Michael Haber,et al.  A comparison of some conditional and unconditional exact tests for 2x2 contingency tables , 1987 .

[3]  A. M. Andrés,et al.  Tablas 2×2 y test exacto de Fisher , 1987 .

[4]  An Alternative Approach to the Analysis of a Fourfold Table , 1969 .

[5]  New critical region tables for Fisher's exact test , 1991 .

[6]  A. Boomsma,et al.  Comparing two independent binomial proportions by a modified chi square test , 1980 .

[7]  Ralph B. D'Agostino,et al.  The Appropriateness of Some Common Procedures for Testing the Equality of Two Independent Binomial Populations , 1988 .

[8]  AUDREY M. B. PARKER.  Unit Cell and Space-Group of Cc2Al9 , 1945, Nature.

[9]  A. M. Andrés,et al.  A critical review of asymptotic methods for comparing two proportions by means of independent samples , 1992 .

[10]  George A. Milliken,et al.  A Nonrandomized Unconditional Test for Comparing Two Proportions in 2×2 Contingency Tables , 1977 .

[11]  R. D. Boschloo.  Raised conditional level of significance for the 2 × 2‐table when testing the equality of two probabilities , 1970 .

[12]  Samy Suissa,et al.  Exact Unconditional Sample Sizes for the 2 Times 2 Binomial Trial , 1985 .

[13]  W. R. Rice,et al.  A New Probability Model for Determining Exact P-Values for 2 x 2 Contingency Tables When Comparing Binomial Proportions , 1988 .

[14]  A. Martín Andrés,et al.  A review of classic non-asymptotic methods for comparing two proportions by means of independent sampLES , 1991 .

[15]  R. Fisher,et al.  The Logic of Inductive Inference , 1935 .

[16]  K F Hirji,et al.  A quasi-exact test for comparing two binomial proportions. , 1991, Statistics in medicine.

[17]  F. Yates,et al.  Tests of Significance for 2 × 2 Contingency Tables , 1984 .

[18]  Michael A. Fligner,et al.  A Comparison of Two Tests for Equality of Two Proportions , 1977 .

[19]  H. Raiffa,et al.  Applied Statistical Decision Theory. , 1961 .

[20]  G. Barnard.  Significance tests for 2 X 2 tables. , 1947, Biometrika.

[21]  G. Barnard,et al.  A New Test for 2 × 2 Tables , 1945 .

[22]  K. D. Tocher.  Extension of the Neyman-Pearson theory of tests to discontinuous variates. , 1950, Biometrika.

[23]  George A. Milliken,et al.  A Nonrandomized Unconditional Test for Comparing Two Proportions. , 1975 .

[24]  Choongrak Kim,et al.  Exact Properties of Some Exact Test Statistics for Comparing Two Binomial Proportions , 1990 .