Resumen
El problema de contrastar la hipótesis de que la diferencia de las medias de dos poblaciones normales, está comprendida en el intervalo (a, b), conociendo una muestra de cada una de las antedichas poblaciones, constituye el problema de Berhens-Fisher.
Se estudia, en primer lugar, la solución pseudocondicional de Behrens, la qual se presta maravillosamente a una reinterpretación en términos de la distribución fiduciaria, debida a Fisher. Más tarde se comparan estos resultados con las soluciones aproximadas de la teoría clásica, y finalmente, se generaliza a poblaciones no normales; a poblaciones con la misma media, etc.
Index Bibliographique
R. A. Fisher: Statistical methods for research workers, 10 th edition (Edinburgh, Oliver and Boyd), 1946.
J. Neyman: Basic ideas… of the theory of testing statistical hypotheses.J. R. Stat. Soc., 115 (1942), 292.
W. V. Behrens: Ein Beitrag zur Fehlerberechnung bei wenigen Beobachtungen.Landwirtschaftliche Jahrbrücher, 68 (1929), 807.
P. C. Mahalanobis: Professor R. A. Fisher,Sankhyā, 4 (1938), 266.
M. Frechet: Citant le réponse de M. Gini à l'enquête sur les problèmes d'estimation.Proc. Intern. Stat. Conference III (A), 1950 381–382.
R. A. Fisher: Inverse probability.Proc. Camb. Phil. Soc., 26 (1930), 528.
R. A. Fisher: Inverse probability and fiducial probability referring to unknown parameters.Proc. R. Soc. A, 139 (1933), 343.
R. A. Fisher: The logic of inductive inference.J. R. Stat Soc., 98 (1935), 39.
R. A. Fisher: The fiducial argument in statistical inference.Ann. of Eugenics, 6 (1935), 391.
R. A. Fisher: Uncertain inference.Proc. R. Soc., B 221 (1936), 1.
R. A. Fisher: On a point raised by M. S. Bartlett on fiducial probability,Ann. of Engenics, 7 (1937), 370.
R. A. Fisher: The comparison of samples with possibly unequal variances.Ann. of Eugenics, 9 (1939), 174.
R. A. Fisher: A note on fiducial inference.Ann. Math. Stat, 10 (1939), 383.
R. A. Fisher: The asymptotic approach to Behrens'integral.Ann of Eugenics, 11 (1941), 141.
R. A. Fisher: Conclusions fiduciaires.Ann. Inst. H. Poincaré, 10 (1948), 191.
R. A. Fisher: Contributions to Mathematical Statistics (New-York, Wiley), 1950.
P. V. Sukhatme: On Fisher and Behrens'test of significance.Sankhyā, 4 (1938), 39.
J. L. Doob: Stochastic Processes (chap. I, § 32) (New-York, Wiley), 1953.
M. S. Bartlett: The information available in small samples.Proc. Camb. Phil. Soc., 32 (1936), 560.
M. S. Bartlett: Complete simultaneous fiducial distributions.Ann. Math. Stat., 10 (1939), 129.
J. Neyman: Fiducial argument and the theory of confidence intervals.Biometrika, 32 (1941), 128.
F. Yates: A apparent inconsistency arising from tests of significance.Proc. Camb. Phil. Soc., 35 (1939), 579.
G. A. Barnard: The meaning of a significance level.Biometrika, 34 (1947), 179.
G. A. Barnard: On the Behrens-Fisher test.Biometrika, 37 (1950), 203.
S. S. Wilks: On the problem of two samples from population with unequal variance.Ann. Math. Stat., 11 (1940), 475.
R. A. Fisher: Foundations of theoritical statistics.Phil. Trans. R. Soc., A 222 (1922), 309.
E. S. Pearson: The choice of statistical tests.Biometrika, 34 (1947), 193.
H. Cramér: Mathematical methods of statistics (Princeton, University Press), 1946.
H. Scheffe: On solutions of the Behrens-Fisher problem based on the distribution.Ann. Math. Stat., 14 (1943), 35.
H. Scheffe: On the ratio of variances of two normal samples.Ann. Math. Stat., 13 (1942), 371.
M. S. Bartlett: Properties of sufficiency and statistical tests.J. R. Stat. Soc., A 160 (1937), 268.
J. E. Walsh: On the power of the «best»t test solution for the Behrens-Fisher problem.Ann. Math. Stat., 20 (1949), 616.
D. Chapman: Some two sample tests.Ann. Math. Stat., 21 (1950), 601.
B. L. Welch: The significance of the difference between two means.Biometrika, 29 (1937), 380.
P. L. Hsu: Contribution to the theory of Student'st test.Stat. Res. Mem., 2 (1938), 1.
E. James: On the comparison of several mean values.Biometrika, 38 (1951), 324.
B. L. Welch: On the comparison of several mean values; an alternative approach.Biometrika, 38 (1951), 330.
E. A. Cornish, R. A. Fisher: Moments and cumulants in the specification of distributions.Rev. Inst. Intern. Stat., 5 (1937), 307.
D. G. C. Gronow: Non-normatily in 2 samplet test.Biometrika, 40 (1953), 222.
J. E. Walsh: On a generalization of the Behrens-Fisher problem.Human Biology, 32 (1950), 125.
E. N. Barankin: Extension of the Romanovsky-Bartlett-Scheffé test.Proc. 1st Berkeley Symposium on Math. Stat., p. 433 (Berkeley, University of California Press), 1949.
A. Wald: Testing the difference between the means of two normal populations with unknown standard deviations; Selected in papers in statistics and probability by A. Wald; (New-York, Mc Graw Hill), 1955; p. 669–695.
Rights and permissions
About this article
Cite this article
Breny, H. L'etat actuel du probleme de Behrens-Fisher. Trabajos de Estadistica 6, 111–131 (1955). https://doi.org/10.1007/BF03003948
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF03003948