Bias in Mixtures of Normal Distributions and Joint Modeling of Longitudinal and Time-to-event Data with Monotonic Change Curves PDF Download
Are you looking for read ebook online? Search for your book and save it on your Kindle device, PC, phones or tablets. Download Bias in Mixtures of Normal Distributions and Joint Modeling of Longitudinal and Time-to-event Data with Monotonic Change Curves PDF full book. Access full book title Bias in Mixtures of Normal Distributions and Joint Modeling of Longitudinal and Time-to-event Data with Monotonic Change Curves by Spencer Lourens. Download full books in PDF and EPUB format.
Author: Spencer Lourens Publisher: ISBN: Category : Biometric identification Languages : en Pages : 248
Book Description
Estimating parameters in a mixture of normal distributions dates back to the 19th century when Pearson originally considered data of crabs from the Bay of Naples. Since then, many real world applications of mixtures have led to various proposed methods for studying similar problems. Among them, maximum likelihood estimation (MLE) and the continuous empirical characteristic function (CECF) methods have drawn the most attention. However, the performance of these competing estimation methods has not been thoroughly studied in the literature and conclusions have not been consistent in published research. In this article, we review this classical problem with a focus on estimation bias. An extensive simulation study is conducted to compare the estimation bias between the MLE and CECF methods over a wide range of disparity values. We use the overlapping coefficient (OVL) to measure the amount of disparity, and provide a practical guideline for estimation quality in mixtures of normal distributions. Application to an ongoing multi-site Huntington disease study is illustrated for ascertaining cognitive biomarkers of disease progression. We also study joint modeling of longitudinal and time-to-event data and discuss pattern-mixture and selection models, but focus on shared parameter models, which utilize unobserved random effects in order to "join" a marginal longitudinal data model and marginal survival model in order to assess an internal time-dependent covariate's effect on time-to-event. The marginal models used in the analysis are the Cox Proportional Hazards model and the Linear Mixed model, and both of these models are covered in some detail before defining joints models and describing the estimation process. Joint modeling provides a modeling framework which accounts for correlation between the longitudinal data and the time-to-event data, while also accounting for measurement error in the longitudinal process, which previous methods failed to do. Since it has been shown that bias is incurred, and this bias is proportional to the amount of measurement error, utilizing a joint modeling approach is preferred. Our setting is also complicated by monotone degeneration of the internal covariate considered, and so a joint model which utilizes monotone B-Splines to recover the longitudinal trajectory and a Cox Proportional Hazards (CPH) model for the time-to-event data is proposed. The monotonicity constraints are satisfied via the Projected Newton Raphson Algorithm as described by Cheng et al., 2012, with the baseline hazard profiled out of the $Q$ function in each M-step of the Expectation Maximization (EM) algorithm used for optimizing the observed likelihood. This method is applied to assess Total Motor Score's (TMS) ability to predict Huntington Disease motor diagnosis in the Biological Predictors of Huntington's Disease study (PREDICT-HD) data.
Author: Spencer Lourens Publisher: ISBN: Category : Biometric identification Languages : en Pages : 248
Book Description
Estimating parameters in a mixture of normal distributions dates back to the 19th century when Pearson originally considered data of crabs from the Bay of Naples. Since then, many real world applications of mixtures have led to various proposed methods for studying similar problems. Among them, maximum likelihood estimation (MLE) and the continuous empirical characteristic function (CECF) methods have drawn the most attention. However, the performance of these competing estimation methods has not been thoroughly studied in the literature and conclusions have not been consistent in published research. In this article, we review this classical problem with a focus on estimation bias. An extensive simulation study is conducted to compare the estimation bias between the MLE and CECF methods over a wide range of disparity values. We use the overlapping coefficient (OVL) to measure the amount of disparity, and provide a practical guideline for estimation quality in mixtures of normal distributions. Application to an ongoing multi-site Huntington disease study is illustrated for ascertaining cognitive biomarkers of disease progression. We also study joint modeling of longitudinal and time-to-event data and discuss pattern-mixture and selection models, but focus on shared parameter models, which utilize unobserved random effects in order to "join" a marginal longitudinal data model and marginal survival model in order to assess an internal time-dependent covariate's effect on time-to-event. The marginal models used in the analysis are the Cox Proportional Hazards model and the Linear Mixed model, and both of these models are covered in some detail before defining joints models and describing the estimation process. Joint modeling provides a modeling framework which accounts for correlation between the longitudinal data and the time-to-event data, while also accounting for measurement error in the longitudinal process, which previous methods failed to do. Since it has been shown that bias is incurred, and this bias is proportional to the amount of measurement error, utilizing a joint modeling approach is preferred. Our setting is also complicated by monotone degeneration of the internal covariate considered, and so a joint model which utilizes monotone B-Splines to recover the longitudinal trajectory and a Cox Proportional Hazards (CPH) model for the time-to-event data is proposed. The monotonicity constraints are satisfied via the Projected Newton Raphson Algorithm as described by Cheng et al., 2012, with the baseline hazard profiled out of the $Q$ function in each M-step of the Expectation Maximization (EM) algorithm used for optimizing the observed likelihood. This method is applied to assess Total Motor Score's (TMS) ability to predict Huntington Disease motor diagnosis in the Biological Predictors of Huntington's Disease study (PREDICT-HD) data.
Author: Elizabeth Juarez Colunga Publisher: ISBN: Category : Poisson processes Languages : en Pages : 0
Book Description
Recently there has been tremendous growth in the use and interest of longitudinal data, particularly because of the development of large scale investigations which are conducted to study different aspects of the dynamics of a population over time (for instance, the Canadian National Longitudinal Study of Children and Youth (Statistics Canada, 1996)). Recurrent event data are a type of longitudinal data which occur in many fields. Such data arise when an event repeats over time, and are common especially in medicine and reliability. Sometimes, in addition to the occurrence of the event, there is also information which reflects the severity of the event; this is called a mark. In this thesis, we develop efficient designs for longitudinal recurrent event studies, and we also develop methods to model recurrent events with marks. In longitudinal recurrent event studies, sometimes partial information on the counting process, such as the number of events occurring in specific intervals, called panel data, provides nearly the same precision for estimation of treatment effects as full information based on data from continuous observation of the process. We compare the efficiency of the analysis of such panel data with respect to the analysis of data recorded as times of recurrences, and we articulate conditions for efficient panel designs where the focus is on estimation of a treatment effect when adjusting for other covariates. We model the recurrent intensity through the common proportional intensity framework, with the treatment effect modeled flexibly as piecewise constant over panels, or groups of panels. We provide some important considerations for the design of efficient panel studies. The thesis also develops methods for situations where marks, denoting a measure of prognostic factors or severity of the event, are also recorded. Often, there is an association between the recurring processes of events and their marks. We model these outcomes jointly through the use of shared or linking random effects, and investigate biases resulting in analyses of the outcomes when they are not modeled jointly. This analysis of joint outcomes is motivated by a study of healthy menstruating women prior to hysterectomy/ovariectomy for benign disease.
Author: Stephanie Ann Kliethermes Publisher: ISBN: Category : Bayesian statistical decision theory Languages : en Pages : 152
Book Description
Longitudinal growth patterns are routinely seen in medical studies where developments of individuals on one or more outcome variables are followed over a period of time. Many current methods for modeling growth presuppose a parametric relationship between the outcome and time (e.g., linear, quadratic); however, these relationships may not accurately capture growth over time. Functional mixed effects (FME) models provide flexibility in handling longitudinal data with nonparametric temporal trends because they allow the data to determine the shape of the curve. Although FME methods are well-developed for continuous, normally distributed outcome measures, nonparametric methods for handling categorical outcomes are limited.
Author: Dimitris Rizopoulos Publisher: CRC Press ISBN: 1439872864 Category : Mathematics Languages : en Pages : 279
Book Description
In longitudinal studies it is often of interest to investigate how a marker that is repeatedly measured in time is associated with a time to an event of interest, e.g., prostate cancer studies where longitudinal PSA level measurements are collected in conjunction with the time-to-recurrence. Joint Models for Longitudinal and Time-to-Event Data: With Applications in R provides a full treatment of random effects joint models for longitudinal and time-to-event outcomes that can be utilized to analyze such data. The content is primarily explanatory, focusing on applications of joint modeling, but sufficient mathematical details are provided to facilitate understanding of the key features of these models. All illustrations put forward can be implemented in the R programming language via the freely available package JM written by the author. All the R code used in the book is available at: http://jmr.r-forge.r-project.org/
Author: Gerhard Tutz Publisher: Springer ISBN: 3319281585 Category : Mathematics Languages : en Pages : 252
Book Description
This book focuses on statistical methods for the analysis of discrete failure times. Failure time analysis is one of the most important fields in statistical research, with applications affecting a wide range of disciplines, in particular, demography, econometrics, epidemiology and clinical research. Although there are a large variety of statistical methods for failure time analysis, many techniques are designed for failure times that are measured on a continuous scale. In empirical studies, however, failure times are often discrete, either because they have been measured in intervals (e.g., quarterly or yearly) or because they have been rounded or grouped. The book covers well-established methods like life-table analysis and discrete hazard regression models, but also introduces state-of-the art techniques for model evaluation, nonparametric estimation and variable selection. Throughout, the methods are illustrated by real life applications, and relationships to survival analysis in continuous time are explained. Each section includes a set of exercises on the respective topics. Various functions and tools for the analysis of discrete survival data are collected in the R package discSurv that accompanies the book.
Author: Simon Wood Publisher: CRC Press ISBN: 1584884746 Category : Mathematics Languages : en Pages : 412
Book Description
Now in widespread use, generalized additive models (GAMs) have evolved into a standard statistical methodology of considerable flexibility. While Hastie and Tibshirani's outstanding 1990 research monograph on GAMs is largely responsible for this, there has been a long-standing need for an accessible introductory treatment of the subject that also emphasizes recent penalized regression spline approaches to GAMs and the mixed model extensions of these models. Generalized Additive Models: An Introduction with R imparts a thorough understanding of the theory and practical applications of GAMs and related advanced models, enabling informed use of these very flexible tools. The author bases his approach on a framework of penalized regression splines, and builds a well-grounded foundation through motivating chapters on linear and generalized linear models. While firmly focused on the practical aspects of GAMs, discussions include fairly full explanations of the theory underlying the methods. Use of the freely available R software helps explain the theory and illustrates the practicalities of linear, generalized linear, and generalized additive models, as well as their mixed effect extensions. The treatment is rich with practical examples, and it includes an entire chapter on the analysis of real data sets using R and the author's add-on package mgcv. Each chapter includes exercises, for which complete solutions are provided in an appendix. Concise, comprehensive, and essentially self-contained, Generalized Additive Models: An Introduction with R prepares readers with the practical skills and the theoretical background needed to use and understand GAMs and to move on to other GAM-related methods and models, such as SS-ANOVA, P-splines, backfitting and Bayesian approaches to smoothing and additive modelling.
Author: Brian Everitt Publisher: Springer Science & Business Media ISBN: 1441996508 Category : Mathematics Languages : en Pages : 284
Book Description
The majority of data sets collected by researchers in all disciplines are multivariate, meaning that several measurements, observations, or recordings are taken on each of the units in the data set. These units might be human subjects, archaeological artifacts, countries, or a vast variety of other things. In a few cases, it may be sensible to isolate each variable and study it separately, but in most instances all the variables need to be examined simultaneously in order to fully grasp the structure and key features of the data. For this purpose, one or another method of multivariate analysis might be helpful, and it is with such methods that this book is largely concerned. Multivariate analysis includes methods both for describing and exploring such data and for making formal inferences about them. The aim of all the techniques is, in general sense, to display or extract the signal in the data in the presence of noise and to find out what the data show us in the midst of their apparent chaos. An Introduction to Applied Multivariate Analysis with R explores the correct application of these methods so as to extract as much information as possible from the data at hand, particularly as some type of graphical representation, via the R software. Throughout the book, the authors give many examples of R code used to apply the multivariate techniques to multivariate data.
Author: Jianguo Sun Publisher: Springer ISBN: 0387371192 Category : Mathematics Languages : en Pages : 310
Book Description
This book collects and unifies statistical models and methods that have been proposed for analyzing interval-censored failure time data. It provides the first comprehensive coverage of the topic of interval-censored data and complements the books on right-censored data. The focus of the book is on nonparametric and semiparametric inferences, but it also describes parametric and imputation approaches. This book provides an up-to-date reference for people who are conducting research on the analysis of interval-censored failure time data as well as for those who need to analyze interval-censored data to answer substantive questions.
Author: James K. Lindsey Publisher: Springer Science & Business Media ISBN: 038722730X Category : Mathematics Languages : en Pages : 265
Book Description
This book describes how generalised linear modelling procedures can be used in many different fields, without becoming entangled in problems of statistical inference. The author shows the unity of many of the commonly used models and provides readers with a taste of many different areas, such as survival models, time series, and spatial analysis, and of their unity. As such, this book will appeal to applied statisticians and to scientists having a basic grounding in modern statistics. With many exercises at the end of each chapter, it will equally constitute an excellent text for teaching applied statistics students and non- statistics majors. The reader is assumed to have knowledge of basic statistical principles, whether from a Bayesian, frequentist, or direct likelihood point of view, being familiar at least with the analysis of the simpler normal linear models, regression and ANOVA.
Author: Spencer Lourens
Author: Spencer Lourens
Author: Elizabeth Juarez Colunga
Author: Juan Li
Author: Stephanie Ann Kliethermes
Author: Dimitris Rizopoulos
Author: Gerhard Tutz
Author: Simon Wood
Author: Brian Everitt
Author: Jianguo Sun
Author: James K. Lindsey