TITLE

ANALYSIS OF NONLINEAR REGRESSION MODELS: A CAUTIONARY NOTE

AUTHOR(S)
Peddada, Shyamal D.; Haseman, Joseph K.
PUB. DATE
July 2005
SOURCE
Dose-Response;2005, Vol. 3 Issue 3, p342
SOURCE TYPE
Academic Journal
DOC. TYPE
Article
ABSTRACT
Regression models are routinely used in many applied sciences for describing the relationship between a response variable and an independent variable. Statistical inferences on the regression parameters are often performed using the maximum likelihood estimators (MLE). In the case of nonlinear models the standard errors of MLE are often obtained by linearizing the nonlinear function around the true parameter and by appealing to large sample theory. In this article we demonstrate, through computer simulations, that the resulting asymptotic Wald confidence intervals cannot be trusted to achieve the desired confidence levels. Sometimes they could underestimate the true nominal level and are thus liberal. Hence one needs to be cautious in using the usual linearized standard errors of MLE and the associated confidence intervals.
ACCESSION #
22124862

 

Related Articles

  • Calculating and graphing within-subject confidence intervals for ANOVA. Baguley, Thom // Behavior Research Methods;Mar2012, Vol. 44 Issue 1, p158 

    The psychological and statistical literature contains several proposals for calculating and plotting confidence intervals (CIs) for within-subjects (repeated measures) ANOVA designs. A key distinction is between intervals supporting inference about patterns of means (and differences between...

  • Confidence Intervals for the Cross-Validated Multiple Correlation in Predictive Regression Models. Fowler, Robert L. // Journal of Applied Psychology;May86, Vol. 71 Issue 2, p318 

    A number of analytically derived formulas for estimating the predictive power of a regression model have been offered as viable alternatives to empirical cross-validation. Although point estimates of the squared population multiple correlation, p² and the squared population cross-validated...

  • Chemometrics in Spectroscopy Comparison of Goodness of Fit Statistics for Linear Regression, Part IV. Workman Jr., Jerome; Mark, Howard // Spectroscopy;Oct2004, Vol. 19 Issue 10, p30 

    Part IV. Describes the use of confidence limits in data analysis for calculating slope and intercept. Summation notation formula for calculating the intercept of a linear regression line; Lower limits for the slope and intercept.

  • Evidence of reference standard related bias in studies of plain radiograph reading performance: a meta-regression. S D Brealey; A J Scally; S Hahn; C Godfrey // British Journal of Radiology;Jun2007, Vol. 80 Issue 954, p406 

    The aim is to determine the effect of reference standard related bias on estimates of plain radiograph reading performance using studies conducted in clinical practice. Data were extracted on study eligibility, clinical and reference standard characteristics and reading performance. The choice...

  • ESTIMATION OF MULTIRESPONSE SIMULATION METAMODELS USING CONTROL VARIATES. De O. Porta Nova, Acácio M.; Wilson, James R. // Management Science;Nov89, Vol. 35 Issue 11, p1316 

    This paper provides a unified development of the method of control variates for simulation experiments in which the objective is estimation of a multiresponse metamodel--that is, a linear model for an output vector of simulation performance measures expressed in terms of an input vector of...

  • Bayesian Approach to identify Masking and Swamping Problems in the Multivariate-Multiple Regression Analysis. Ekiz, Ufuk // Gazi University Journal of Science;Apr2006, Vol. 19 Issue 2, p113 

    The Bayesian method developed by Chaloner and Brant to see whether, for instance, the outlier observation is included in the linear model or not, focuses on posterior distributions of realized but unobserved errors [5]. This method has been expanded by Varbanov for the multivariate-multiple...

  • The Unusually Poor Physical Health Status of Cambodian Refugees Two Decades After Resettlement. Wong, Eunice; Marshall, Grant; Schell, Terry; Elliott, Marc; Babey, Susan; Hambarsoomians, Katrin // Journal of Immigrant & Minority Health;Oct2011, Vol. 13 Issue 5, p876 

    To better document the health status of Cambodian refugees, the physical health functioning, disability, and general health status of Cambodian refugees was compared to that of non-refugee Asian immigrants with similar demographic characteristics. Data were collected between October 2003 and...

  • Relational and management continuity survey in patients with multiple long-term conditions. Gulliford, Martin; Cowie, Luke; Morgan, Myfanwy // Journal of Health Services Research & Policy;Apr2011, Vol. 16 Issue 2, p67 

    Objective: To quantify problems of relational and management continuity of care in patients with multiple long-term conditions. Methods: A mailed questionnaire survey was conducted among people aged 60 years and older from 15 general practices. The questionnaire included 16 items concerning...

  • The effects of binge drinking and social capital on violent victimisation: findings from Moscow. Stickley, A.; Pridemore, W. A. // Journal of Epidemiology & Community Health;Oct2010, Vol. 64 Issue 10, p902 

    Background Rates of violence in Russia are among the highest in the world, and violent victimisation represents a major public health threat in the country. As yet, however, little research has been undertaken on what factors are associated with non-lethal violent victimisation in this setting....

Share

Read the Article

Courtesy of VIRGINIA BEACH PUBLIC LIBRARY AND SYSTEM

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

Try another library?
Sign out of this library

Other Topics