Variance-stabilizing and Confidence-stabilizing Transformations for the Normal Correlation Coefficient with Known Variances

Fosdick and Raftery (2012) recently encountered the problem of inference for a bivariate normal correlation coefficient ρ with known variances. We derive a variance-stabilizing transformation y(ρ) analogous to Fisher’s classical z-transformation for the unknown-variance case. Adjusting y for the sample size n produces an improved “confidence-stabilizing” transformation y_n(ρ) that provides more accurate interval estimates for ρ than the known-variance MLE. Interestingly, the z transformation applied to the unknown-but-equal-variance MLE performs well in the known-variance case for smaller values of |ρ|. Both methods are useful for comparing two or more correlation coefficients in the known-variance case.     

On the distribution of the correlation coefficient when sampling from a mixture of two bivariate normal densities: Robustness and the effect of outliers

The distribution of the sample correlation coefficient is derived when the population is a mixture of two bivariate normal distributions with zero mean but different covariances and mixing proportions 1 - λ and λ respectively; λ will be called the proportion of contamination. The test of ρ = 0 based on Student's t, Fisher's z, arcsine, or Ruben's transformation is shown numerically to be nonrobust when λ, the proportion of contamination, lies between 0.05 and 0.50 and the contaminated population has 9 times the variance of the standard (bivariate normal) population. These tests are also sensitive to the presence of outliers.     

Estimating the correlation coefficient in the presence of correlated observations from a bivariate normal population

Estimation of the correlation coefficient between two variates (p) in the presence of correlated observations from a bivar iate normal population is considered The estimated maximum likelihood estimator (EMLE), an estimate based on the maximum likelihood estimator (MLE), is proposed and studied for the estimation of p For the large sample case , approximate expressions foi the variance and the bias of the Pearson estimate of the correlation coefficient are derived. These expressions suggests that the Pearson’s estimator possesses high mean square error (MSE) in estimating ρ in comparison to the MLE The MSE is particularly high when the observations within clusters aie highly correlated. The Pearson’s estimate, the MLE, and the EMLE aie evaluated in a simulation study This study shows that the proposed EMLE pefoims bettei than the Pearson’s correlation coefficient except when the number of clusters is small.     

Large sample confidence intervals for the skewness parameter of the skew-normal distribution based on Fisher's transformation

The skew-normal model is a class of distributions that extends the Gaussian family by including a skewness parameter. This model presents some inferential problems linked to the estimation of the skewness parameter. In particular its maximum likelihood estimator can be infinite especially for moderate sample sizes and is not clear how to calculate confidence intervals for this parameter. In this work, we show how these inferential problems can be solved if we are interested in the distribution of extreme statistics of two random variables with joint normal distribution. Such situations are not uncommon in applications, especially in medical and environmental contexts, where it can be relevant to estimate the distribution of extreme statistics. A theoretical result, found by Loperfido [7 Loperfido, N. 2002. Statistical implications of selectively reported inferential results. Statist. Probab. Lett., 56: 13–22. [Crossref], [Web of Science ®] , [Google Scholar]], proves that such extreme statistics have a skew-normal distribution with skewness parameter that can be expressed as a function of the correlation coefficient between the two initial variables. It is then possible, using some theoretical results involving the correlation coefficient, to find approximate confidence intervals for the parameter of skewness. These theoretical intervals are then compared with parametric bootstrap intervals by means of a simulation study. Two applications are given using real data.     

A Nonparametric Test for the Ordered Alternative Based on Kendall's Correlation Coefficient

Several methods have been developed for testing the ordered alternative. These include the Jonckheere–Terpstra (JT) test (Jonckheere, 1954 Jonckheere , A. R. ( 1954 ). A distribution free k-sample test against ordered alternatives . Biometrika 41 : 133 – 145 .[Crossref], [Web of Science ®] , [Google Scholar]; Terpstra, 1952 Terpstra , T. ( 1952 ). The asymptotic normality and consistency of Kendall's test against trend when ties are present in one ranking . Indigationes Mathematicae 14 : 327 – 333 . [Google Scholar]), a modified JT test (MJT) (Tryon and Hettmansperger, 1987 Tryon , V. P. , Hettmansperger , T. P. ( 1987 ). A class of nonparametric tests for homogeneity against ordered alternatives . Annals of Statistics 1 : 1061 – 1070 . [Google Scholar]), and a test proposed by Terpstra and Magel (TM) (Terpstra and Magel, 2003 Terpstra , J. T. , Magel , R. C. ( 2003 ). A new nonparametric test for the ordered alternative problem . Journal of Nonparametric Statistics 15 : 289 – 301 .[Taylor & Francis Online], [Web of Science ®] , [Google Scholar]), among others. This article proposes a new method for testing the ordered alternative. The proposed test is based on Kendall's tau statistic. The asymptotic distribution of the test statistic is given. A Monte Carlo simulation study is conducted comparing the estimated powers of the proposed test with existing tests under a variety of sample sizes and distributions.     

MSE performance and minimax regret significance points for a HPT estimator under a multivariate t error distribution

In this article, assuming that the error terms follow a multivariate t distribution,we derive the exact formulae forthe moments of the heterogeneous preliminary test (HPT) estimator proposed by Xu (2012b Xu, H. (2012b). MSE performance and minimax regret significance points for a HPT estimator when each individual regression coefficient is estimated. Commun. Stat. Theory Methods 42:2152–2164.[Taylor &; Francis Online], [Web of Science ®] , [Google Scholar]). We also execute the numerical evaluation to investigate the mean squared error (MSE) performance of the HPT estimator and compare it with those of the feasible ridge regression (FRR) estimator and the usual ordinary least squared (OLS) estimator. Further, we derive the optimal critical values of the preliminary F test for the HPT estimator, using the minimax regret function proposed by Sawa and Hiromatsu (1973 Sawa, T., Hiromatsu, T. (1973). Minimax regret significance points for a preliminary test in regression analysis. Econometrica 41:1093–1101.[Crossref], [Web of Science ®] , [Google Scholar]). Our results show that (1) the optimal significance level (α*) increases as the degrees of freedom of multivariate t distribution (ν₀) increases; (2) when ν₀ ? 10, the value of α* is close to that in the normal error case.     

A Confidence Interval and Test for the Mean of an Asymmetric Distribution

ABSTRACT

A confidence interval and test are obtained for the mean of an asymmetric distribution using a random sample of size n. The method is based on N. J. Johnson's (1978 Johnson , N. J. ( 1978 ). Modified, t tests and confidence intervals for asymmetrical populations. J. Amer. Statist. Assoc. 73 ( 363 ): 536 – 544 .[Taylor & Francis Online], [Web of Science ®] , [Google Scholar]) modified t-test, where terms of Cornish–Fisher expansions involving the third moment are used to adjust the conventional statistic to have more closely a Student's t-distribution with n ? 1 degrees of freedom. Johnson's (1978 Johnson , N. J. ( 1978 ). Modified, t tests and confidence intervals for asymmetrical populations. J. Amer. Statist. Assoc. 73 ( 363 ): 536 – 544 .[Taylor & Francis Online], [Web of Science ®] , [Google Scholar]) test cannot be inverted uniquely, so a corresponding confidence interval for the mean may be disjointed. However, an artificial term of small order can be added to make inversion of the test a uniquely defined operation, which prevents such disjointedness. The resulting one-sided and two-sided intervals perform better than others in the literature with skewed distributions, and have good performance with a normal distribution. The two-sided interval may be recommended for general use if the sample size is 10 or more and the nominal confidence coefficient is 95% or less, or if the sample size is 30 or more and the confidence coefficient is 99% or less.     

An Adaptive Goodness-of-Fit Test

In Fortiana and Grané (2003 Fortiana , J. , Grané , A. ( 2003 ). Goodness-of-fit tests based on maximum correlations and their orthogonal decompositions . J. Roy. Statist. Soc. B 65 ( 1 ): 115 – 126 . [CSA] [CROSSREF] [Crossref] , [Google Scholar]), we introduced the statistic Q _n , based on Hoeffding's maximum correlation, as a general-purpose goodness-of-fit test of uniformity. It admits an expansion along a countable set of orthogonal axes, originating a sequence of statistics. Linear combinations of a given number p of terms in this sequence have easy-to-compute probability distributions, either the exact ones for a finite sample or their normal asymptotic approximations for a large sample. In this article we develop an algorithm for tailoring a statistic within this class of linear combinations to test uniformity with optimal power against a specific alternative or family of alternatives.     

The Fisher Transform of the Pearson Product Moment Correlation Coefficient and Its Square: Cumulants,Moments, and Applications

This paper extends results on the distribution of the Fisher transform of the correlation coefficient (Fisher, 1921 Fisher , R. A. ( 1921 ). On the “probable error” of a coefficient of correlation deduced from a small sample . Metron 1 : 1 – 32 . [Google Scholar]). Approaches to obtain exact moments of the Fisher transform for both null and non-null correlations are presented. We extend the classic series expansion formulae of Hotelling (1953 Hotelling , H. ( 1953 ). New light on the correlation coefficient and its transforms . Journal of the Royal Statistical Society, Ser. B 15 : 192 – 232 . [Google Scholar]) for the moments of the Fisher transform. These results are considered in the context of quadratic functions of the Fisher transform. Some applications of these results are discussed in the context of correlational hypothesis tests and confidence intervals, and a Monte Carlo experiment is used to demonstrate how application of these results impact the small sample performance of select tests on correlations.     

A Test for Multivariate Analysis of Variance in High Dimension

In this article, we consider the problem of testing a general multivariate linear hypothesis in a multivariate linear model when the N × p observation matrix is normally distributed with unknown covariance matrix, and N ≤ p. This includes the case of testing the equality of several mean vectors. A test is proposed which is a generalized version of the two-sample test proposed by Srivastava and Du (2008 Srivastava , M. S. , Du , M. ( 2008 ). A test for the mean vector with fewer observations than the dimension . J. Multivariate Anal. 99 : 386 – 402 .[Crossref], [Web of Science ®] , [Google Scholar]). The asymptotic null and nonnull distributions are obtained. The performance of this test is compared, theoretically as well as numerically, with the corresponding generalized version of the two-sample Dempster (1958 Dempster , A. P. (1958). A high dimensional two sample significance test. Ann. Math. Statist. 29:995–1010.[Crossref] , [Google Scholar]) test, or more appropriately Bai and Saranadasa (1996 Bai , Z. , Saranadasa , H. ( 1996 ). Effect of high dimension: an example of a two sample problem . Statistica Sinica 6 : 311 – 329 .[Web of Science ®] , [Google Scholar]) test who gave its asymptotic version.     

A Modified Hall-Padmanabhan Test for the Homogeneity of Scales

We consider a simple adaptive test for the homogeneity of scales due to Hall and Padmanabhan (1997 Hall , P. , Padmanabhan , A. R. ( 1997 ). Adaptive inference for the two-sample scale problem . Technometrics 23 : 351 – 361 . [Google Scholar]) which is based on the ratio of adaptively trimmed sample variances. We develop a modification of this test that has the form of a combined bootstrap test and that is obtained within the nonparametric combination of dependent tests framework (Pesarin, 2001 Pesarin , F. ( 2001 ). Multivariate Permutation Tests with Applications in Biostatistics . Chichester : Wiley . [Google Scholar]). We considered other approaches for the combination of tests concluding that the Liptak method is the most suitable one for the problem at hand. We compare the modified test with the original one in terms of robustness of significance level and power in a simulation study which considers distributions that range from symmetric to skewed and from light to heavy tailed ones. We show that the modified test is more powerful than the original one under heavier than normal tailed and very skewed distributions. A practical application to detect difference in scale of energy intake of lactating and non pregnant and not lactating women is presented.     

Semiparametric analysis of transformation models with doubly censored data

Double censoring arises when T represents an outcome variable that can only be accurately measured within a certain range, [L, U], where L and U are the left- and right-censoring variables, respectively. In this note, using Martingale arguments of Chen et al. [3 Chen, K., Jin, Z. and Ying, Z. 2002. Semiparametric analysis of transformation models with censored data. Biometrika, 89: 659–668. [Crossref], [Web of Science ®] [Google Scholar]], we propose an estimator (denoted by ?β) for estimating regression coefficients of transformation model when L is always observed. Under Cox proportional hazards model, the proposed estimator is equivalent to the partial likelihood estimator for left-truncated and right-censored data if the left-censoring variables L were regarded as left-truncated variables. In this case, the estimator ?β can be obtained by the standard software. A simulation study is conducted to investigate the performance of ?β. For the purpose of comparison, the simulation study also includes the estimator proposed by Cai and Cheng [2 Cai, T. and Cheng, S. 2004. Semiparametric regression analysis for doubly censored data. Biometrika, 91: 277–290. [Crossref], [Web of Science ®] [Google Scholar]] for the case when L and U are always observed.     

On Test Statistics in Profile Analysis with High-dimensional Data

We consider profile analysis with unequal covariance matrices under multivariate normality. In particular, we discuss this problem for high-dimensional data where the dimension is larger than the sample size. We propose three test statistics based on Bennett’s (1951) transformation and the Dempster trace criterion proposed by Dempster (1958 Dempster, A.P. (1958). A high dimensional two samples significance test. Annals of Mathematical Statistics 29:995–1010.[Crossref] , [Google Scholar]). We derive the null distributions as well as the nonnull distributions of the test statistics. Finally, in order to investigate the accuracy of the proposed statistics, we perform Monte Carlo simulations for some selected values of parameters.     

Test for the equality of several correlation coefficients

We derive two C(α) statistics and the likelihood-ratio statistic for testing the equality of several correlation coefficients, from k ≥ 2 independent random samples from bivariate normal populations. The asymptotic relationship of the C(α) tests, the likelihood-ratio test, and a statistic based on the normality assumption of Fisher's Z-transform of the sample correlation coefficient is established. A comparative performance study, in terms of size and power, is then conducted by Monte Carlo simulations. The likelihood-ratio statistic is often too liberal, and the statistic based on Fisher's Z-transform is conservative. The performance of the two C(α) statistics is identical. They maintain significance level well and have almost the same power as the other statistics when empirically calculated critical values of the same size are used. The C(α) statistic based on a noniterative estimate of the common correlation coefficient (based on Fisher's Z-transform) is recommended.     

Inequalities for sums of squares of reranked differences involving ties and missing data

An inequality for the sum of squares of rank differences associated with Spearman’s rank correlation coefficient, when ties and missing data are present in both rankings, was established numerically in Loukas and Papaioannou (1991 Loukas, S., Papaioannou, T. (1991). Rank correlation inequalities with ties and missing data. Stat. Probab. Lett. 11:53–56.[Crossref], [Web of Science ®] , [Google Scholar]). That inequality is improved and generalized.     

Edgeworth Expansion of the Moment-Based Test for Homogeneity in an NEF-QVF Mixture Model

In this article, we study the moment-based test procedure for a mixture distribution for the Natural exponential family with quadratic variance functions (NEF-QVF) family proposed by Ning et al. (2009b Ning, W., Zhang, S. G. and Yu, C. 2009b. A moment-based test for the homogeneity in mixture natural exponential family with quadratic variance functions. Statistical and Probability Letters, 79: 828–834. [Crossref] , [Google Scholar]) in the small sample size scenario. We derive the approximation for the null distribution of the test statistic by the Edgeworth expansion. The simulations are conducted for a binomial mixture distribution, which includes the situation corresponding to the detection of the linkage in the genetic analysis, with different sample sizes and family sizes at various significance levels. The simulation results show that our test performs reasonably well. We also apply the proposed method to the real clinical data to verify the significant difference between two drug treatments. The critical values associated with a binomial mixture distribution are also provided.     

New weighted rank correlation coefficients sensitive to agreement on top and bottom rankings

Three new weighted rank correlation coefficients are proposed which are sensitive to both agreement on top and bottom rankings. The first one is based on the weighted rank correlation coefficient proposed by Maturi and Abdelfattah [13 T.A. Maturi and E.H. Abdelfattah, A new weighted rank correlation, J. Math. Stat. 4 (2008), pp. 226–230. doi: 10.3844/jmssp.2008.226.230[Crossref] , [Google Scholar]], the second and the third are based on the order statistics and the quantiles of the Laplace distribution, respectively. The limiting distributions of the new correlation coefficients under the null hypothesis of no association between the rankings are presented, and a summary of the exact and approximate quantiles for these coefficients is provided. A simulation study is performed to compare the performance of Kendall's tau, Spearman's rho, and the new weighted rank correlation coefficients in detecting the agreement on the top and the bottom rankings simultaneously. Finally, examples are given for illustration purposes, including a real data set from financial market indices.     

Three-stage and ‘accelerated’ sequential procedures for the mean of a normal population with known coefficient of variation

Three-stage and ‘accelerated’ sequential procedures are developed for estimating the mean of a normal population when the population coefficient of variation (CV) is known. In spite of the usual estimator, i.e. the sample mean, Searls' (1964 Searls, DT. (1964). The utilization of a known coefficient of variation in the estimation procedure. J. Amer. Statist. Assoc, 50: 1225–1226.  ) estimator is utilized for the estimation purpose. It is established that Searls' estimator dominates the sample mean under the two sampling schemes.     

Adaptive Test for Periodicity in Autoregressive Conditional Heteroskedastic Processes

This article is concerned with the periodicity testing problem in Autoregressive Conditional Heteroskedastic (ARCH) process. Adaptive locally asymptotically optimal test is derived, when the innovation density is unspecified but symmetric satisfying only some general technical assumptions, for the null hypothesis of classical ARCH process against an alternative of periodically correlated ARCH dependence. The main technical tool is LeCam's (1960 LeCam , L. ( 1960 ). Locally Asymptotically Normal Families of Distributions . University California Publ. Statistics 3:27–98 . [Google Scholar]) Local Asymptotic Normality (LAN) property. The LAN property of the central sequence is shown via the adapted sufficient Swensen's conditions (1985 Swensen , A. R. ( 1985 ). The asymptotic distribution of the likelihood ratio for autoregressive time series with a regression trend . Journal of Multivariate Analysis 16 : 54 – 70 .[Crossref], [Web of Science ®] , [Google Scholar]). The performance of the established test is shown via simulation studies.