Improved Likelihood Inference on Testing the Difference of Non Centrality Parameters of Two Independent Non central t Distributions with Identical Degrees of Freedom

Kim and Hayter (2008 Kim , J. , Hayter , A. J. ( 2008 ). Testing the equality of the non centrality parameters of the two non central t-distributions with identical degrees of freedom . Communications in Statistics: Simulation and Computation 37 : 1709 – 1717 .[Taylor & Francis Online], [Web of Science ®] , [Google Scholar]) showed that testing the difference of the non centralities of two non central t distributions, which have identical degrees of freedom, is the equivalent to testing the difference of two signal-to-noise ratios for two independent samples from different normal distributions. Moreover, from a biomedical research point of view, the above test is also equivalent to testing the existence of the effect size when the sample sizes of the control group and treatment group are the same. In this article, two third-order likelihood-based methods are proposed to approximate the p-value for this significance test problem. A real life example is used to illustrate that results from the proposed methods and the existing methods can be quite different. Simulation results show that the proposed methods give remarkable accuracy even when sample size reaches the smallest possible value.     

Likelihood based inference for the ratio of gamma means

Inference concerning the ratio of two means based two independent two-parameter gamma models with common shape parameter was examined in Booth et al. (1999 Booth, J. G., Hobert, J. P. and Ohman, P. A. (1999). On the probable error of the ratio of two gamma means. Biometrika, 86: 439–452.  [Google Scholar]) and a computationally intensive bootstrap calibration method was developed. In this paper, a likelihood based method is proposed for small sample inference about the ratio of two means of the two-parameter gamma models when the shape parameters may or may not be equal. The proposed method is very simple to use and, as illustrated in simulation studies, gives extremely accurate results.     

Ridge estimation in generalized linear models and proportional hazards regressions

Conventionally, a ridge parameter is estimated as a function of regression parameters based on ordinary least squares. In this article, we proposed an iterative procedure instead of the one-step or conventional ridge method. Additionally, we construct an indicator that measures the potential degree of improvement in mean squared error when ridge estimates are employed. Simulations show that our methods are appropriate for a wide class of non linear models including generalized linear models and proportional hazards (PHs) regressions. The method is applied to a PH regression with highly collinear covariates in a cancer recurrence study.     

Fitting finite mixture models using iterative Monte Carlo classification

Parameters of a finite mixture model are often estimated by the expectation–maximization (EM) algorithm where the observed data log-likelihood function is maximized. This paper proposes an alternative approach for fitting finite mixture models. Our method, called the iterative Monte Carlo classification (IMCC), is also an iterative fitting procedure. Within each iteration, it first estimates the membership probabilities for each data point, namely the conditional probability of a data point belonging to a particular mixing component given that the data point value is obtained, it then classifies each data point into a component distribution using the estimated conditional probabilities and the Monte Carlo method. It finally updates the parameters of each component distribution based on the classified data. Simulation studies were conducted to compare IMCC with some other algorithms for fitting mixture normal, and mixture t, densities.     

Analysis of generalized linear mixed models via a stochastic approximation algorithm with Markov chain Monte-Carlo method

In recent years much effort has been devoted to maximum likelihood estimation of generalized linear mixed models. Most of the existing methods use the EM algorithm, with various techniques in handling the intractable E-step. In this paper, a new implementation of a stochastic approximation algorithm with Markov chain Monte Carlo method is investigated. The proposed algorithm is computationally straightforward and its convergence is guaranteed. A simulation and three real data sets, including the challenging salamander data, are used to illustrate the procedure and to compare it with some existing methods. The results indicate that the proposed algorithm is an attractive alternative for problems with a large number of random effects or with high dimensional intractable integrals in the likelihood function.     

Simultaneous variable and factor selection via sparse group lasso in factor analysis

This paper considers variable and factor selection in factor analysis. We treat the factor loadings for each observable variable as a group, and introduce a weighted sparse group lasso penalty to the complete log-likelihood. The proposal simultaneously selects observable variables and latent factors of a factor analysis model in a data-driven fashion; it produces a more flexible and sparse factor loading structure than existing methods. For parameter estimation, we derive an expectation-maximization algorithm that optimizes the penalized log-likelihood. The tuning parameters of the procedure are selected by a likelihood cross-validation criterion that yields satisfactory results in various simulation settings. Simulation results reveal that the proposed method can better identify the possibly sparse structure of the true factor loading matrix with higher estimation accuracy than existing methods. A real data example is also presented to demonstrate its performance in practice.     

Lack-of-Fit Tests for Generalized Linear Models via Splines

Cubic B-splines are used to estimate the nonparametric component of a semiparametric generalized linear model. A penalized log-likelihood ratio test statistic is constructed for the null hypothesis of the linearity of the nonparametric function. When the number of knots is fixed, its limiting null distribution is the distribution of a linear combination of independent chi-squared random variables, each with one df. The smoothing parameter is determined by giving a specified value for its asymptotically expected value under the null hypothesis. A simulation study is conducted to evaluate its power performance; a real-life dataset is used to illustrate its practical use.     

Multivariate thin plate spline estimates for the posterior probabilities in the classification problem

A nonparametric estimate for the posterior probabilities in the classification problem using multivariate thin plate splines is proposed. This method presents a nonpararnetric alternative to logistic discrimination as well as to survival curve estimation. The degree of smoothness of the estimate is determined from the data using generalized crossvalidation.     

Some pitfalls of tests of separate families of hypotheses: normality vs. lognormality

It is often desirable to test non-nested hypotheses. Cox (1961, 1962) proposed forming a log-likelihood ratio from their maxima and then comparing this value to its expected value under the null hypothesis. Pitfalls exists when we apply Cox's test to the special case of testing normality versus lognormality. Pesaran (1981) and Kotz (1973) pointed out the slow convergence rate of the Cox's test. In this paper, this fact has been reemphasized; moreover, we propose an alternative likelihood ratio test which remedies problems arising from negative estimates of the asymptotic variance of Cox's test statistic and is uniformly more powerful than most commonly used tests.     

Sums of squares and products matrices for a non-full ranks hypothesis in the model of potthoff and roy

Formulae for sums of squares and products matrices, useful in testing a general linear hypothesis in the model of POTTHOFF and ROY, are given, Contrary to the customary approach, these formulae are expressed in original terms of the design matrices and the matrices formulating the hypothesis. They are applicable regardless of the ranks of the matrices involved, which allows to avoid a transformation of the hypothesis and a repara-metrization of the model.