Segmented regression with errors in predictors: semi-parametric and parametric methods.

Abstract:

:We consider the estimation of parameters in a particular segmented generalized linear model with additive measurement error in predictors, with a focus on linear and logistic regression. In epidemiologic studies segmented regression models often occur as threshold models, where it is assumed that the exposure has no influence on the response up to a possibly unknown threshold. Furthermore, in occupational and environmental studies the exposure typically cannot be measured exactly. Ignoring this measurement error leads to asymptotically biased estimators of the threshold. It is shown that this asymptotic bias is different from that observed for estimating standard generalized linear model parameters in the presence of measurement error, being both larger and in different directions than expected. In most cases considered the threshold is asymptotically underestimated. Two standard general methods for correcting for this bias are considered; regression calibration and simulation extrapolation (simex). In ordinary logistic and linear regression these procedures behave similarly, but in the threshold segmented regression model they operate quite differently. The regression calibration estimator usually has more bias but less variance than the simex estimator. Regression calibration and simex are typically thought of as functional methods, also known as semi-parametric methods, because they make no assumptions about the distribution of the unobservable covariate X. The contrasting structural, parametric maximum likelihood estimate assumes a parametric distributional form for X. In ordinary linear regression there is typically little difference between structural and functional methods. One of the major, surprising findings of our study is that in threshold regression, the functional and structural methods differ substantially in their performance. In one of our simulations, approximately consistent functional estimates can be as much as 25 times more variable than the maximum likelihood estimate for a properly specified parametric model. Structural (parametric) modelling ought not be a neglected tool in measurement error models. An example involving dust concentration and bronchitis in a mechanical engineering plant in Munich is used to illustrate the results.

journal_name

Stat Med

journal_title

Statistics in medicine

authors

Küchenhoff H,Carroll RJ

doi

10.1002/(sici)1097-0258(19970130)16:2<169::aid-sim

subject

Has Abstract

pub_date

1997-01-15 00:00:00

pages

169-88

issue

1-3

eissn

0277-6715

issn

1097-0258

pii

10.1002/(SICI)1097-0258(19970130)16:2<169::AID-SIM

journal_volume

16

pub_type

杂志文章
  • Bootstrap confidence intervals for medical costs with censored observations.

    abstract::Medical costs data with administratively censored observations often arise in cost-effectiveness studies of treatments for life-threatening diseases. Mean of medical costs incurred from the start of a treatment until death or a certain time point after the implementation of treatment is frequently of interest. In many...

    journal_title:Statistics in medicine

    pub_type: 杂志文章

    doi:10.1002/sim.1556

    authors: Jiang H,Zhou XH

    更新日期:2004-11-15 00:00:00

  • Statistical estimation of parameters in a disease transmission model: analysis of a Cryptosporidium outbreak.

    abstract::Population dynamic models, commonly used tools in the study of epidemics and other complex population processes, are implicit non-linear mathematical equations. Inference based on such models can be difficult due to the problems associated with high dimensional parameters that may be non-identified and complex likelih...

    journal_title:Statistics in medicine

    pub_type: 杂志文章

    doi:10.1002/sim.1258

    authors: Brookhart MA,Hubbard AE,van der Laan MJ,Colford JM Jr,Eisenberg JN

    更新日期:2002-12-15 00:00:00

  • Curtailed two-stage designs in Phase II clinical trials.

    abstract::When the accrual rate is low and the treatment period is long, a long observational period is required before information concerning the primary end point, such as binary response, becomes available in the study. Simon's two-stage designs are often employed in Phase II clinical trials to avoid giving patient an ineffe...

    journal_title:Statistics in medicine

    pub_type: 杂志文章

    doi:10.1002/sim.3424

    authors: Chi Y,Chen CM

    更新日期:2008-12-20 00:00:00

  • Estimating the mean hazard ratio parameters for clustered survival data with random clusters.

    abstract::We consider a latent variable hazard model for clustered survival data where clusters are a random sample from an underlying population. We allow interactions between the random cluster effect and covariates. We use a maximum pseudo-likelihood estimator to estimate the mean hazard ratio parameters. We propose a bootst...

    journal_title:Statistics in medicine

    pub_type: 杂志文章

    doi:10.1002/(sici)1097-0258(19970915)16:17<2009::aid-s

    authors: Cai J,Zhou H,Davis CE

    更新日期:1997-09-15 00:00:00

  • A general approach to evaluating the bias of 2-stage instrumental variable estimators.

    abstract::Unmeasured confounding is a common concern when researchers attempt to estimate a treatment effect using observational data or randomized studies with nonperfect compliance. To address this concern, instrumental variable methods, such as 2-stage predictor substitution (2SPS) and 2-stage residual inclusion (2SRI), have...

    journal_title:Statistics in medicine

    pub_type: 杂志文章

    doi:10.1002/sim.7636

    authors: Wan F,Small D,Mitra N

    更新日期:2018-05-30 00:00:00

  • Analysis of messy longitudinal data from a randomized clinical trial. MRC Lung Cancer Working Party.

    abstract::The randomized clinical trial, LU19, conducted by the Medical Research Council Lung Cancer Working Party, was designed to compare ACE (doxorubicin, cyclophosphamide and etoposide) chemotherapy plus G-CSF (granulocyte colony-stimulating factor) at 2-week intervals versus ACE chemotherapy alone at standard 3-week interv...

    journal_title:Statistics in medicine

    pub_type: 临床试验,杂志文章

    doi:10.1002/1097-0258(20001015)19:19<2657::aid-sim557>

    authors: Qian W,Parmar MK,Sambrook RJ,Fayers PM,Girling DJ,Stephens RJ

    更新日期:2000-10-15 00:00:00

  • Descriptive statistical analyses of serial dilution data.

    abstract::The serial dilution assay (for example, an in vitro antimicrobic susceptibility test or a serum antibody titer assay) is an important technique in biomedical research. The structure of the experiment forces grouping of the threshold concentrations into intervals. Statistical methods to analyse threshold concentrations...

    journal_title:Statistics in medicine

    pub_type: 杂志文章

    doi:10.1002/sim.4780070410

    authors: Hamilton MA,Rinaldi MG

    更新日期:1988-04-01 00:00:00

  • Modelling age-specific risk: application to dementia.

    abstract::We give up-to-date methods for estimating the age-specific incidence of a disease and for estimating the effect of risk factors. We recommend taking age as the basic time scale of the analysis; then, the hazard function can be interpreted as the age-specific incidence of the disease. This choice raises a delayed entry...

    journal_title:Statistics in medicine

    pub_type: 杂志文章

    doi:10.1002/(sici)1097-0258(19980915)17:17<1973::aid-s

    authors: Commenges D,Letenneur L,Joly P,Alioum A,Dartigues JF

    更新日期:1998-09-15 00:00:00

  • Two-sample rank tests for acceleration in cure models.

    abstract::I derive the locally most powerful rank tests for acceleration against semi-parametric alternatives when some patients are cured of the disease. I consider some particular classes of alternatives and present simulation results to verify the validity of the proposed tests. Real data from clinical trials for childhood l...

    journal_title:Statistics in medicine

    pub_type: 杂志文章

    doi:10.1002/sim.4780141905

    authors: Lee JW

    更新日期:1995-10-15 00:00:00

  • Genetic association studies with bivariate mixed responses subject to measurement error and misclassification.

    abstract::In genetic association studies, mixed effects models have been widely used in detecting the pleiotropy effects which occur when one gene affects multiple phenotype traits. In particular, bivariate mixed effects models are useful for describing the association of a gene with a continuous trait and a binary trait. Howev...

    journal_title:Statistics in medicine

    pub_type: 杂志文章

    doi:10.1002/sim.8688

    authors: Zhang Q,Yi GY

    更新日期:2020-11-20 00:00:00

  • Performance of analytical methods for overdispersed counts in cluster randomized trials: sample size, degree of clustering and imbalance.

    abstract::Many different methods have been proposed for the analysis of cluster randomized trials (CRTs) over the last 30 years. However, the evaluation of methods on overdispersed count data has been based mostly on the comparison of results using empiric data; i.e. when the true model parameters are not known. In this study, ...

    journal_title:Statistics in medicine

    pub_type: 杂志文章

    doi:10.1002/sim.3681

    authors: Durán Pacheco G,Hattendorf J,Colford JM Jr,Mäusezahl D,Smith T

    更新日期:2009-10-30 00:00:00

  • Modelling the relationship between continuous covariates and clinical events using isotonic regression.

    abstract::In a medical study we are often interested in graphically displaying the relationship between continuous variables and clinical events indicating disease progression. Often, it is reasonable to make the minimal assumption that the risk of progression is an arbitrary monotone function of the continuous variable. Someti...

    journal_title:Statistics in medicine

    pub_type: 杂志文章

    doi:10.1002/sim.1561

    authors: Ancukiewicz M,Finkelstein DM,Schoenfeld DA

    更新日期:2003-10-30 00:00:00

  • Empirical Bayes versus fully Bayesian analysis of geographical variation in disease risk.

    abstract::This paper reviews methods for mapping geographical variation in disease incidence and mortality. Recent results in Bayesian hierarchical modelling of relative risk are discussed. Two approaches to relative risk estimation, along with the related computational procedures, are described and compared. The first is an em...

    journal_title:Statistics in medicine

    pub_type: 杂志文章

    doi:10.1002/sim.4780110802

    authors: Bernardinelli L,Montomoli C

    更新日期:1992-06-15 00:00:00

  • Generalized pairwise comparison methods to analyze (non)prioritized composite endpoints.

    abstract::In the analysis of composite endpoints in a clinical trial, time to first event analysis techniques such as the logrank test and Cox proportional hazard test do not take into account the multiplicity, importance, and the severity of events in the composite endpoint. Several generalized pairwise comparison analysis met...

    journal_title:Statistics in medicine

    pub_type: 杂志文章

    doi:10.1002/sim.8388

    authors: Verbeeck J,Spitzer E,de Vries T,van Es GA,Anderson WN,Van Mieghem NM,Leon MB,Molenberghs G,Tijssen J

    更新日期:2019-12-30 00:00:00

  • Variable selection for proportional odds model.

    abstract::In this paper we study the problem of variable selection for the proportional odds model, which is a useful alternative to the proportional hazards model and might be appropriate when the proportional hazards assumption is not satisfied. We propose to fit the proportional odds model by maximizing the marginal likeliho...

    journal_title:Statistics in medicine

    pub_type: 杂志文章

    doi:10.1002/sim.2833

    authors: Lu W,Zhang HH

    更新日期:2007-09-10 00:00:00

  • A spatial scan statistic for ordinal data.

    abstract::Spatial scan statistics are widely used for count data to detect geographical disease clusters of high or low incidence, mortality or prevalence and to evaluate their statistical significance. Some data are ordinal or continuous in nature, however, so that it is necessary to dichotomize the data to use a traditional s...

    journal_title:Statistics in medicine

    pub_type: 杂志文章

    doi:10.1002/sim.2607

    authors: Jung I,Kulldorff M,Klassen AC

    更新日期:2007-03-30 00:00:00

  • Bayesian sensitivity analysis of incomplete data: bridging pattern-mixture and selection models.

    abstract::Pattern-mixture models (PMM) and selection models (SM) are alternative approaches for statistical analysis when faced with incomplete data and a nonignorable missing-data mechanism. Both models make empirically unverifiable assumptions and need additional constraints to identify the parameters. Here, we first introduc...

    journal_title:Statistics in medicine

    pub_type: 杂志文章

    doi:10.1002/sim.6302

    authors: Kaciroti NA,Raghunathan T

    更新日期:2014-11-30 00:00:00

  • Incorporating data from various trial designs into a mixed treatment comparison model.

    abstract::Estimates of relative efficacy between alternative treatments are crucial for decision making in health care. Bayesian mixed treatment comparison models provide a powerful methodology to obtain such estimates when head-to-head evidence is not available or insufficient. In recent years, this methodology has become wide...

    journal_title:Statistics in medicine

    pub_type: 杂志文章

    doi:10.1002/sim.5764

    authors: Schmitz S,Adams R,Walsh C

    更新日期:2013-07-30 00:00:00

  • A survey of models for repeated ordered categorical response data.

    abstract::We survey models for analysing repeated observations on an ordered categorical response variable. The models presented are univariate models that permit correlation among repeated measurements. The models describe simultaneously the dependence of marginal response distributions on values of explanatory variables and o...

    journal_title:Statistics in medicine

    pub_type: 杂志文章

    doi:10.1002/sim.4780081005

    authors: Agresti A

    更新日期:1989-10-01 00:00:00

  • Analyzing sequentially randomized trials based on causal effect models for realistic individualized treatment rules.

    abstract::In this paper, we argue that causal effect models for realistic individualized treatment rules represent an attractive tool for analyzing sequentially randomized trials. Unlike a number of methods proposed previously, this approach does not rely on the assumption that intermediate outcomes are discrete or that models ...

    journal_title:Statistics in medicine

    pub_type: 杂志文章

    doi:10.1002/sim.3268

    authors: Bembom O,van der Laan MJ

    更新日期:2008-08-30 00:00:00

  • Assessing heterogeneity and correlation of paired failure times with the bivariate frailty model.

    abstract::We consider bivariate survival times for heterogeneous populations, where heterogeneity induces deviations in an individual's risk of an event as well as associations between survival times. The heterogeneity is characterized by a bivariate frailty model. We measure the heterogeneity effects through deviations associa...

    journal_title:Statistics in medicine

    pub_type: 杂志文章

    doi:10.1002/(sici)1097-0258(19990430)18:8<907::aid-sim

    authors: Xue X,Ding Y

    更新日期:1999-04-30 00:00:00

  • A joint model of recurrent events and a terminal event with a nonparametric covariate function.

    abstract::We extend the shared frailty model of recurrent events and a dependent terminal event to allow for a nonparametric covariate function. We include a Gaussian random effect (frailty) in the intensity functions of both the recurrent and terminal events to capture correlation between the two processes. We employ the penal...

    journal_title:Statistics in medicine

    pub_type: 杂志文章

    doi:10.1002/sim.4297

    authors: Zhangsheng Y,Liu L

    更新日期:2011-09-30 00:00:00

  • Simultaneous estimation of intrarater and interrater agreement for multiple raters under order restrictions for a binary trait.

    abstract::It is valuable in many studies to assess both intrarater and interrater agreement. Most measures of intrarater agreement do not adjust for unequal estimates of prevalence between the separate rating occasions for a given rater and measures of interrater agreement typically ignore data from the second set of assessment...

    journal_title:Statistics in medicine

    pub_type: 杂志文章

    doi:10.1002/sim.1138

    authors: Lester Kirchner H,Lemke JH

    更新日期:2002-06-30 00:00:00

  • Estimating kappa from binocular data and comparing marginal probabilities.

    abstract::Suppose that two graders classify all eyes in a sample of patients for the presence or absence of a specified abnormality. In the statistical analysis of the data, possible correlation between the observations in the right and left eyes should be taken into account. Recently, general methods have been developed to ana...

    journal_title:Statistics in medicine

    pub_type: 杂志文章

    doi:10.1002/sim.4780122306

    authors: Schouten HJ

    更新日期:1993-12-15 00:00:00

  • Methods for epidemiologic analyses of multiple exposures: a review and comparative study of maximum-likelihood, preliminary-testing, and empirical-Bayes regression.

    abstract::Many epidemiologic investigations are designed to study the effects of multiple exposures. Most of these studies are analysed either by fitting a risk-regression model with all exposures forced in the model, or by using a preliminary-testing algorithm, such as stepwise regression, to produce a smaller model. Research ...

    journal_title:Statistics in medicine

    pub_type: 杂志文章,评审

    doi:10.1002/sim.4780120802

    authors: Greenland S

    更新日期:1993-04-30 00:00:00

  • Group sequential designs for cure rate models with early stopping in favour of the null hypothesis.

    abstract::Ewell and Ibrahim derived the large sample distribution of the logrank statistic under general local alternatives. Their asymptotic results enable us to extend several group sequential designs which allow for early stopping in favour of the null hypothesis to the setting in which the cure rate model is appropriate. In...

    journal_title:Statistics in medicine

    pub_type: 杂志文章

    doi:10.1002/1097-0258(20001130)19:22<3023::aid-sim638>

    authors: Patricia Bernardo MV,Ibrahim JG

    更新日期:2000-11-30 00:00:00

  • A copula-based mixed Poisson model for bivariate recurrent events under event-dependent censoring.

    abstract::In many chronic disease processes subjects are at risk of two or more types of events. We describe a bivariate mixed Poisson model in which a copula function is used to model the association between two gamma distributed random effects. The resulting model is a bivariate negative binomial process in which each type of...

    journal_title:Statistics in medicine

    pub_type: 杂志文章

    doi:10.1002/sim.3830

    authors: Cook RJ,Lawless JF,Lee KA

    更新日期:2010-03-15 00:00:00

  • A practical introduction to Bayesian estimation of causal effects: Parametric and nonparametric approaches.

    abstract::Substantial advances in Bayesian methods for causal inference have been made in recent years. We provide an introduction to Bayesian inference for causal effects for practicing statisticians who have some familiarity with Bayesian models and would like an overview of what it can add to causal estimation in practical s...

    journal_title:Statistics in medicine

    pub_type: 杂志文章

    doi:10.1002/sim.8761

    authors: Oganisian A,Roy JA

    更新日期:2021-01-30 00:00:00

  • The Peto odds ratio viewed as a new effect measure.

    abstract::Meta-analysis has generally been accepted as a fundamental tool for combining effect estimates from several studies. For binary studies with rare events, the Peto odds ratio (POR) method has become the relative effect estimator of choice. However, the POR leads to biased estimates for the OR when treatment effects are...

    journal_title:Statistics in medicine

    pub_type: 杂志文章

    doi:10.1002/sim.6301

    authors: Brockhaus AC,Bender R,Skipka G

    更新日期:2014-12-10 00:00:00

  • Kappa coefficients in medical research.

    abstract::Kappa coefficients are measures of correlation between categorical variables often used as reliability or validity coefficients. We recapitulate development and definitions of the K (categories) by M (ratings) kappas (K x M), discuss what they are well- or ill-designed to do, and summarize where kappas now stand with ...

    journal_title:Statistics in medicine

    pub_type: 杂志文章,评审

    doi:10.1002/sim.1180

    authors: Chmura Kraemer H,Periyakoil VS,Noda A

    更新日期:2002-07-30 00:00:00