On some tests for independence in nonnormal situations: neyman'S C(A)test

A study is made of Neyman's C(a) test for testing independence in nonnormal situations. It is shown that it performs very well both in terms of the level of significance and the powereven for smallvalues of the samplesize. Also, in the case of the bivariate Polsson distribution, itis shown that Fisher's z and Student's t transforms of the sample correlation coefficient are good competitors for Neyman's procedure.

     

A new rank test for the K-Sample problem

The treatment sum of squares in the one-way analysis of variance can be expressed in two different ways: as a sum of comparisons between each treatment and the remaining treatments combined, or as a sum of comparisons between the treatments two at a time. When comparisons between treatments are made with the Wilcoxon rank sum statistic, these two expressions lead to two different tests; namely, that of Kruskal and Wallis and one which is essentially the same as that proposed by Crouse (1961,1966). The latter statistic is known to be asymptotically distributed as a chi-squared variable when the numbers of replicates are large. Here it is shown to be asymptotically normal when the replicates are few but the number of treatments is large. For all combinations of numbers of replicates and treatments its empirical distribution is well approximated by a beta distribution     

Discrete adaptive design in attribute life testing

Properties of a discrete adaptive design in attribute life testing situation are studied. It is shown that the design is strongly consistent and asymptotically normal. Some examples are discussed to show that the design could be used in a wide range of ields, Finally, we give some simulation results to compare the discrete adaptive desigin with some continuous optimal designs.     

A stepwise algorithm for selecting category boundaries for the chi-squared goodness-of-fit test

A stepwise algorithm for selecting categories for the chisquared goodness-of-fit test with completely specified continuous null and alternative distributions is described in this paper. The procedure's starting point is an initial partitioning of the sample space into a large number of categories. A second partition with one fewer category is constructed by combining two categories of the original partition. The procedure continues until there are only two categories; the partition in the sequence with the highest estimated power is the one chosen. For illustartive purposes, the performance of the algorithm is evaluated for several hypothesis tests of the from H₀: normal distribution vs. H₁: a specific mixed normal distribution. For each test considered, the partition identified by the algorithm was compared to several equiprobable partitions, including the equiprobable partition with the highest estimated power. In all cases but one, the algorithm identified a parttion with higher estimated power than the best equiprobable partition. Applciations of the procedure are discussed.     

A simple method for constructing confounded designs for mixed factorial experiments

This paper presents the sinplesr procedure that uses wodular aryithmetic for constructing confounded designs for mixed factorial experiments. The present procedure and the classical one for confounding in symmetrical factorial experiments are both at the same mathema.tical level. The present procedure is written for

practitioners and is lllustrared with several examples.     

A test for variance-covarianch parameters in normal linear models

This paper derives a test statistic for the variance-covariance parameters which is a quadratic function of their MINQUE (Minimum Norm Quadratic Unbiased Estimation) estimates. The test is a Wald-type test, and its development closely parallels the theory used to derive a similar test for the coefficients in linear models. In fact, the derivation proceeds by first setting up the estimation problem in a derived linear model in which the dispersion parameters are the coefficients. The test statistic is shown to be the sum of the squares of independent standardized x² variables.     

Estimation of parameters and reliability from generalized life models

Simultaneous estimation of parameters with p (≥ 2) components, where each component has a generalized life distribution, is considered under a sum of squared error loss function. Improved estimators are obtained which dominate the maximum likelihood and the niinimum mean square estimators. Robustness of the improved estimators is shown even when the component distributions are dependent. The result is extended to the estimation of the system reliability when the components are connected in series. Several numerical studies are performed to demonstrate the risk improvement and the Pitman closeness of the new estimators.     

The two-sample t test versus satterthwaite's approximate f test

A comparison between the two-sample t test and Satterthwaite's approximate F test is made, assuming the choice between these two tests is based on a preliminary test on the variances. Exact formulas for the sizes and powers of the tests are derived. Sizes and powers are then calculated and compared for several situations.     

Classification procedures using principal component analysis and stepwise discriminant function

Classification procedures are examined in the case when the dimensionality exceeds the sample size. Two particular suggestions are (i) Principal components analysis and (ii) Two-step discriminant analysis. Comparisons are made in the two sample and the several sample cases. Extensions to growth curve model are investigated using the two stage discriminant analysis.     

Normal approximation in an urn model with indistinguishable balls

For the Bose-Einstein Statistics, where n indistinguishable balls are distributed in m urns such that all the arrangements are equally likely, define the random variables

M_k = number of urns containing exactly k balls each;

N_k = number of urns containing at least k balls each.

We consider the approximation of the distributions of M_k and N_k by suitable normal distributions, for large but finite m. Estimates are found for the error in the approximation to both the probability mass function and the distribution function in each case. These results apply also to the alternative model where no urn is allowed to be empty. The results are illustrated by some numerical examples.