Checking linearity of non-parametric component in partially linear models with an application in systemic inflammatory response syndrome study

Hua Liang
June 2006
Statistical Methods in Medical Research;Jun2006, Vol. 15 Issue 3, p273
Academic Journal
Two tests are proposed for checking the linearity of nonparametric function in partially linear models. The first one is based on a Crámer–von Mises statistic. This test can detect the local alternative converging to the null at the parametric rate 1/√n. A bootstrap resample technique is provided to calculate the critical values. The second one is constructed in a penalized spline framework along with linear mixed-effects (LME) modeling. This is an extension likelihood ratio test for testing zero variance of random effects in LME models. Simulation experiments are conducted to explore the numerical performance of two tests. It is observed that two tests have good level properties, and the first test has a substantially superior power property over the second test in a variety of cases. A real data set is analysed with the proposed tests.


Related Articles

  • Distribution-Free Methods of Approximating Nonlinear Marketing Relationships. Rust, Roland T.; Bornman, Elizabeth O. // Journal of Marketing Research (JMR);Aug1982, Vol. 19 Issue 3, p372 

    Many, if not most, of the important functional relationships in marketing are inherently nonlinear. Fitting a nonlinear function to data involves first the specification of a model, and then the estimation of the model's parameters. Where theory gives insufficient guidance for the specification...

  • Life After Chi-Squared: An Introduction to Log-Linear Analysis. BUMBERRY, WILLIAM M.; GRISSO, J. THOMAS // Canadian Journal of Psychiatry;Oct1998, Vol. 48 Issue 8, p837 

    Chi-squared tests are used to examine the relationships among categorical variables. However, they are difficult to use and interpret when more than 2 variables are involved. In such cases, it is better to use a related statistic, catted tog-linear analysis. This article is an introduction to...

  • Properties and MIS Applications of Combinatorial Distribution Functions. Papayanopoulos, Lee // Journal of Management Information Systems;Summer85, Vol. 2 Issue 1, p77 

    We examine a versatile mathematical device which systematically summarizes combinations of linear functions of integer variables. The deterministic frequency function, like its relative the probability distribution, may be manipulated numerically or analytically to serve different purposes. Here...

  • A New Statistical Tool: Scalar Score Function. Fabián, Zdeněk // Computer Technology & Application;2011, Vol. 2 Issue 2, p109 

    The basic inference function of mathematical statistics, the score function, is a vector function. The author has introduced the scalar score, a scalar inference function, which reflects main features of a continuous probability distribution and which is simple. Its simplicity makes it possible...

  • Handling Nonlinearity in an Ensemble Kalman Filter: Experiments with the Three-Variable Lorenz Model. Yang, Shu-Chih; Kalnay, Eugenia; Hunt, Brian // Monthly Weather Review;Aug2012, Vol. 140 Issue 8, p2628 

    An ensemble Kalman filter (EnKF) is optimal only for linear models because it assumes Gaussian distributions. A new type of outer loop, different from the one used in 3D and 4D variational data assimilation (Var), is proposed for EnKF to improve its ability to handle nonlinear dynamics,...

  • Asymptotic Fitness Distribution in the Bak-Sneppen Model of Biological Evolution with Four Species. Schlemm, Eckhard // Journal of Statistical Physics;Aug2012, Vol. 148 Issue 2, p191 

    We suggest a new method to compute the asymptotic fitness distribution in the Bak-Sneppen model of biological evolution. As applications we derive the full asymptotic distribution in the four-species model, and give an explicit linear recurrence relation for a set of coefficients determining the...

  • Bayesian inference for generalized linear mixed models. Youyi Fong; Rue, Håvard; Wakefield, Jon // Biostatistics;Jul2010, Vol. 11 Issue 3, p397 

    Generalized linear mixed models (GLMMs) continue to grow in popularity due to their ability to directly acknowledge multiple levels of dependency and model different data types. For small sample sizes especially, likelihood-based inference can be unreliable with variance components being...

  • Isotonic logistic discrimination. Sungyoung Auh; Sampson, Allan R. // Biometrika;Dec2006, Vol. 93 Issue 4, p961 

    We propose an isotonic logistic discrimination procedure which generalises linear logistic discrimination by allowing linear boundaries to be more flexibly shaped as monotone functions of the discriminant variables. Under each of three familiar sampling schemes for obtaining a training dataset,...

  • A CLASS OF MIX DESIGN PROBLEMS: FORMULATION, SOLUTION METHODS AND APPLICATIONS. Zhong Wan; Teo, K. L.; Lingshuang Kong; Chunhua Yang // ANZIAM Journal;2009, Vol. 50 Issue 4, p455 

    In this paper, we consider a linear program with only equality constraints but containing interval and random coefficients. We first address the linear program with interval coefficients, and establish some structural properties of this linear program. On this basis, a solution method is...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics