Summary
This paper is concerned with tests of distribution free methods in sequential form. One of the most outstanding features of this methods is the broad field of application, we don’t need almost any assumption about the distribution function of the random variable that we study. Unfortunately this distribution free methods need a large sample size to get the neccessary accuracy, so the usefulness of sequential methods that have great savings in average sample size. The distribution free test in sequential form has two very important proprieties, broad field of application and a small average sample size.
In the first chapter the author give a test S for the median of any distribution, that, in the case of normal distribution has one relative efficiency of 60% againts Wald sequential test, and about 120% against current most powerful test. So we can use this test S instead of the most powerful test with advantage in sample size and in numerical calculus, because the test S is very simple.
In the second chapter, the previous tests S is adapted to “two sample problem”, in first time with alternative hypothesis of differences in location, and then generalized to any alternative. With normal distribution and alternative hypothesis of differences in location the test presented by the author is most powerful and smaller in sample size than other usual tests, Wilcoxon, Wald and Wolfowitz, Epstein, Tsao.
In the chapter three the author study the tests of randomness in a similar way.
Similar content being viewed by others
Bibliografia
Wald, A.—Sobre los principios de la inferencia estadistica.Trabajos de Estadística Vol. II. Cuad. II. 1951, p. 113.
Savage, I. R..—Bibliography of Nonparametric Statistics an related topics.Jour. Am. Stat. Ass. Vol. 48. Núm. 264, 1954, pp. 844–006.
Walsh, J. E..—Some significance test for the median wich are valid under very general conditions.Ann. Math. Stat. Vol. XX, 1949, p. 64.
Wilkss, S. S..—Order Statistics.Bull. Am. Math. Soc. Vol. 54, 1948, páginas 6–50.
Pitman, E. J. G..—Significance tests wich may be applied to samples from any population.Jour. Royal Stat. Soc. Supplement Vol. 4, 1937, pp. 119–130.
Wilcoxon, F.—Individual Comparisons by ranking methods.Biometrics. Vol. 1, 1946, pp. 80–82.
Mood, A. M.—Introdution to theory of statistics. New York, 1950 (McGraw-Hill), pp. 107–108.
Rios, S.—Introducción a los métodos de la Estadística. 2.a parte. Madrid, 1954, pp. 273.
Thompson, W. R.—On confidence ranges for the median and other expectations distributions for populations of unknown distribution form.Ann. Math. Stat. Vol. 7, 1936, pp. 122–128.
Wald, A.—Sequential analisys. New York, 1947 (Wiley).
Royo, J. yFerrer, S.—Tablas de números aleatorios y estadisticas. Instituto de Investigaciones Estadísticas. Madrid, 1955.
Pearson, K.—Tables of the incomplete beta function. Cambridge, 1932 (Cambridge University Press).
Cramer, H.—Mathematical Methods of Statistics. Princeton, 1946 (Princeton University Press).
Dixon, W. J. yMassey, F. J.—Introduction to statistical analisys. New York, 1951 (McGraw-Hill).
Wilcoxon, F.—Individual Comparisons by ranking methods.Biometries. Vol. 1, 1946, pp. 80–82.
Terry, M. E.—Some rank order test wich are most powerful against specific parametric alternatives.Ann. Math. Stat. Vol. 23, 1952, pp. 346–366.
Van der Waerden, B. L.—Order test for the two sample problem and their power.Indagationes Mathematicae Vol. 14, 1952, pp. 453–458.
Epstein, B.—Tables for the distribution of the number of exceedances.Ann. Math. Stat Vol. 25, 1954, pp. 762–768.
Wald, A. yWolfowttz, J.—On a test whether two samples are from the same population.Ann. Math. Stat. Vol. XI, 1940, pp. 147–162.
Smirnoff—Tables for estimating the goodnes of fit of empirical distributions.Ann. Math. Stat Vol. XIV, 1943, pp. 66–87.
Massey, F. J. Jr.—The distributión of the maximum deviation between two cumulative step functions.Ann. Math. Stat. Vol. 22, 1951, pp. 125–128.
Tsao, C. K.—An extension of Massey’s distribution of the maximum deviation of two cumulative step functions.Ann. Math. Stat. Vol. 25, páginas 587–592.
Van Dantzig, D. yHemelrijk, J.—Statistical methods based on few assupmtions.Bull. Inst. Inter. Statist Tome XXXIV
Noether, G.—Abstract of A sequential test of randomness againts linear trend.Ann. Math. Stat. Vol. 25, 1954, pp. 176.
Lehman, E.L.—Consistency and unbiasedness of certain non parametric test.Ann. Math. Stat. Vol. 22, 1951, pp. 165–179.
Epstein, B.—Comparisons of some non parametric tests againts normal alternatives with en application to life testing.Jour. Am. Stat. Ass. Vol. 50, 1955, pp. 894–900.
Kendall, M. G.—Rank correlation methods. London, 1948 (Griffin).
Cox, D. R. yStuart, S.—Some quick sing test for trend in location and disperiión.Biometrica Vol. 42, 1955, pp. 80–95.
Additional information
Instituto Investigaciones Estadisticas
Rights and permissions
About this article
Cite this article
Romaní, J. Tests no parametricos en forma secuencial. Trabajos de Estadistica 7, 43–96 (1956). https://doi.org/10.1007/BF03030141
Issue Date:
DOI: https://doi.org/10.1007/BF03030141