Loading

Error: Cannot Load Popup Box

Hit List

Title:

Cross-sectional Analysis of Longitudinal Data with Missing Values in the Dependent Variables: A Comparison of Weighted Estimating Equations with the Complete Case Analysis

Author:

Description:

Inference for cross-sectional models using longitudinal data can be drawn with independence estimating equations (Liang and Zeger, 1986). Many studies suffer from missing data. Robins and coworkers proposed to use weighted estimating equations (WEE) in estimating the mean structure, if missing data are present in dependent variables. In this pap...

Inference for cross-sectional models using longitudinal data can be drawn with independence estimating equations (Liang and Zeger, 1986). Many studies suffer from missing data. Robins and coworkers proposed to use weighted estimating equations (WEE) in estimating the mean structure, if missing data are present in dependent variables. In this paper the WEE are compared with complete case analyses for binary responses using simulated data. Our results are in accordance with the theoretical findings of Robins and coworkers. The WEE yield consistent estimates, even if the data are missing at random. Keywords: Correlated Data Analysis, Generalised Estimating Equations, HorvitzThompson Estimation, Marginal Models, Missing Data, Weighted Estimating Equations 1 Introduction Several approaches for the analysis of cross-sectional models using longitudinal data have been proposed. Application of these marginal models is very popular in the literature. The Generalised Estimating Equations (GEE; . Minimize

Contributors:

The Pennsylvania State University CiteSeerX Archives

Year of Publication:

2009-04-13

Source:

ftp://ftp.stat.uni-muenchen.de/pub/sfb386/paper64.ps.Z

ftp://ftp.stat.uni-muenchen.de/pub/sfb386/paper64.ps.Z Minimize

Document Type:

text

Language:

en

Subjects:

Correlated Data Analysis ; Generalised Estimating Equations ; HorvitzThompson Estimation ; Marginal Models ; Missing Data ; Weighted Estimating Equations

Correlated Data Analysis ; Generalised Estimating Equations ; HorvitzThompson Estimation ; Marginal Models ; Missing Data ; Weighted Estimating Equations Minimize

DDC:

310 Collections of general statistics *(computed)*

Rights:

Metadata may be used without restrictions as long as the oai identifier remains attached to it.

Metadata may be used without restrictions as long as the oai identifier remains attached to it. Minimize

URL:

Content Provider:

My Lists:

My Tags:

Notes:

Title:

Solving Generalised Estimating Equations With Missing Data Using Pseudo Maximum Likelihood Estimation Is Equivalent to Complete Case Analysis

Author:

Description:

Arminger and Sobel (1990) proposed an approach to estimate meanand covariance structures in the presence of missing data. These authors claimed that their method based on Pseudo Maximum Likelihood (PML) estimation may be applied if the data are missing at random (MAR) in the sense of Little and Rubin (1987). Rotnitzky and Robins (1995), however,...

Arminger and Sobel (1990) proposed an approach to estimate meanand covariance structures in the presence of missing data. These authors claimed that their method based on Pseudo Maximum Likelihood (PML) estimation may be applied if the data are missing at random (MAR) in the sense of Little and Rubin (1987). Rotnitzky and Robins (1995), however, stated that the PML approach may yield inconsistent estimates if the data are (MAR). We show that the adoption of the PML approach for mean- and covariance structures to mean structures in the presence of missing data as proposed by Ziegler (1994) is identical to the complete case (CC) estimator. Nevertheless, the PML approach has the computational advantage in that the association structure remains the same. Keywords: Correlated Data Analysis, Generalised Estimating Equations, Marginal Models, Missing Data, Pseudo Maximum Likelihood 1 Introduction Arminger and Sobel (1990) introduced an approach to estimate mean- and covariance structures in . Minimize

Contributors:

The Pennsylvania State University CiteSeerX Archives

Year of Publication:

2009-04-12

Source:

ftp://ftp.stat.uni-muenchen.de/pub/sfb386/paper128.ps.Z

ftp://ftp.stat.uni-muenchen.de/pub/sfb386/paper128.ps.Z Minimize

Document Type:

text

Language:

en

Subjects:

Correlated Data Analysis ; Generalised Estimating Equations ; Marginal Models ; Missing Data ; Pseudo Maximum Likelihood

Correlated Data Analysis ; Generalised Estimating Equations ; Marginal Models ; Missing Data ; Pseudo Maximum Likelihood Minimize

DDC:

310 Collections of general statistics *(computed)*

Rights:

Metadata may be used without restrictions as long as the oai identifier remains attached to it.

Metadata may be used without restrictions as long as the oai identifier remains attached to it. Minimize

URL:

Content Provider:

My Lists:

My Tags:

Notes:

Title:

A comparison of Jackknife estimators of variance for GEE2

Author:

Description:

Marginal regression modeling with generalised estimating equations became very popular in the last decade. While the mean structure is of primary interest in first-order generalised estimating equations (GEE1), second-order generalised estimating equations (GEE2) allow the estimation of both the mean and the association structure. It has repeate...

Marginal regression modeling with generalised estimating equations became very popular in the last decade. While the mean structure is of primary interest in first-order generalised estimating equations (GEE1), second-order generalised estimating equations (GEE2) allow the estimation of both the mean and the association structure. It has repeatedly been shown that the usual robust variance estimator for the GEE1 is conservative, especially in small samples. As an alternative, the jackknife estimator of variance can be used. In this discussion paper, we extend the different jackknife estimators of variance to GEE2 models. The variance estimators are compared in a simulation study. While there is only little difference in the variance estimates of the mean structure across simulated models, the results differ substantially with respect to the association structure. The fully iterated jackknife estimator seems to be the most appropriate when focusing on the GEE2. Minimize

Contributors:

The Pennsylvania State University CiteSeerX Archives

Year of Publication:

2009-03-26

Source:

ftp://ftp.stat.uni-muenchen.de/pub/sfb386/paper167.ps.Z

ftp://ftp.stat.uni-muenchen.de/pub/sfb386/paper167.ps.Z Minimize

Document Type:

text

Language:

en

Subjects:

Generalised Estimating Equations ; Marginal Models ; Jackknife Estimators

Generalised Estimating Equations ; Marginal Models ; Jackknife Estimators Minimize

DDC:

310 Collections of general statistics *(computed)*

Rights:

Metadata may be used without restrictions as long as the oai identifier remains attached to it.

Metadata may be used without restrictions as long as the oai identifier remains attached to it. Minimize

URL:

Content Provider:

My Lists:

My Tags:

Notes:

Title:

Analysing the Relationship Between Ectomycorrhizal Infection and Forest Decline Using Marginal Models

Author:

Description:

This statistical survey originates from the problem of discovering which relationship exists between root ectomycorrhizal infection and health status of forest plants. The sampling scheme takes observations from roots that come from sectors around the tree resulting in a hierarchical association structure of the observations. Marginal regression...

This statistical survey originates from the problem of discovering which relationship exists between root ectomycorrhizal infection and health status of forest plants. The sampling scheme takes observations from roots that come from sectors around the tree resulting in a hierarchical association structure of the observations. Marginal regression models are used to analyze the mean effect of the ectomycorrhizal state on a response variable proxy for the health degree of the plants. Keywords: ectomycorrhizal infection, forest decline, generalized estimating equations, likelihood methods, marginal models 1 Introduction This statistical survey originates from the problem of discovering which relationship exists between root ectomycorrhizal infection and health status of forest plants. The ectomycorrhiza is a symbiosis involving fine root apexes of plants and some species of fungi. It is characterized by an hyphal mantle outside the apex surface and an internal, extracellular net of hyphae. Minimize

Contributors:

The Pennsylvania State University CiteSeerX Archives

Year of Publication:

2009-04-13

Source:

ftp://ftp.stat.uni-muenchen.de/pub/sfb386/paper143.ps.Z

ftp://ftp.stat.uni-muenchen.de/pub/sfb386/paper143.ps.Z Minimize

Document Type:

text

Language:

en

Subjects:

ectomycorrhizal infection ; forest decline ; generalized estimating equations ; likelihood

ectomycorrhizal infection ; forest decline ; generalized estimating equations ; likelihood Minimize

DDC:

310 Collections of general statistics *(computed)*

Rights:

Metadata may be used without restrictions as long as the oai identifier remains attached to it.

URL:

Content Provider:

My Lists:

My Tags:

Notes:

Title:

New features in MAREG 0.2.0

Author:

Description:

This paper describes changes in the software tool MAREG from version 0.0.7 (July 1997) to version 0.2.0 (June 1999). As these new features are not implemented in WinMAREG yet, they can only be used via editing the ini-files (*.cai). Handling and features of Version 0.0.7 are described in Fieger, Heumann and Kastner (1996), Fieger, Kastner and He...

This paper describes changes in the software tool MAREG from version 0.0.7 (July 1997) to version 0.2.0 (June 1999). As these new features are not implemented in WinMAREG yet, they can only be used via editing the ini-files (*.cai). Handling and features of Version 0.0.7 are described in Fieger, Heumann and Kastner (1996), Fieger, Kastner and Heumann (1998) and Kastner, Fieger and Heumann (1997). 1 Changes 1 1.1 Test statistics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 GEE output . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 2 New general options 2 2.1 Expected values of the response variable . . . . . . . . . . . . . . . . . 2 2.2 Global Wald tests . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 2.3 Specifying start values . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 2.4 Sequential logit link . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 3 New options for the GEE module 4 4 New values for .cai. Minimize

Contributors:

The Pennsylvania State University CiteSeerX Archives

Year of Publication:

2009-04-14

Source:

ftp://ftp.stat.uni-muenchen.de/pub/sfb386/paper156.ps.Z

ftp://ftp.stat.uni-muenchen.de/pub/sfb386/paper156.ps.Z Minimize

Document Type:

text

Language:

en

Rights:

Metadata may be used without restrictions as long as the oai identifier remains attached to it.

URL:

Content Provider:

My Lists:

My Tags:

Notes:

Title:

WinMAREG Quick Start

Author:

Description:

This paper is a short introduction into the usage of WinMAREG. Two examples are used to illustrate the most common options and features of the software. Keywords: User guide, MAREG, WinMAREG. 1 Introduction This quick start will give the user a short introduction into the handling of WinMAREG. We present the analysis of two data sets, which are ...

This paper is a short introduction into the usage of WinMAREG. Two examples are used to illustrate the most common options and features of the software. Keywords: User guide, MAREG, WinMAREG. 1 Introduction This quick start will give the user a short introduction into the handling of WinMAREG. We present the analysis of two data sets, which are provided with the software. These are the `Respiratory Disorder Data' described in Miller, Davis and Landis (1993) and the `Ohio Children Data' described e. g. in Fitzmaurice and Laird (1993). Most of the features and options are presented. A detailled description can be found in the (context sensitive) online help or in Fieger, Heumann and Kastner (1996). Starting the program displays the main window of WinMAREG presented in figure 1. The menubar consists of the usual file menu (opening and closing data files), the options menu, the two statistics menues (ML and GEE1) and a help menu. The options menu provides entrys that determine the appeara. Minimize

Contributors:

The Pennsylvania State University CiteSeerX Archives

Year of Publication:

2009-04-12

Source:

ftp://ftp.stat.uni-muenchen.de/pub/sfb386/paper108.ps.Z

ftp://ftp.stat.uni-muenchen.de/pub/sfb386/paper108.ps.Z Minimize

Document Type:

text

Language:

en

Rights:

Metadata may be used without restrictions as long as the oai identifier remains attached to it.

URL:

Content Provider:

My Lists:

My Tags:

Notes:

Title:

Familial Associations of Lipid Profiles: A Generalised Estimating Equations Approach

Author:

Description:

Elevated plasma levels of apolipoproteins A1 (apoA1) and B (apoB) are important protective factors and risk factors, respectively, for atherosclerosis and coronary heart disease. It is well known that both apoA1 and apoB reveal strong familial aggregation. Our goal was to investigate whether exogenous variables influence these associations. We u...

Elevated plasma levels of apolipoproteins A1 (apoA1) and B (apoB) are important protective factors and risk factors, respectively, for atherosclerosis and coronary heart disease. It is well known that both apoA1 and apoB reveal strong familial aggregation. Our goal was to investigate whether exogenous variables influence these associations. We used marginal regression models for the mean and association structure (Generalised Estimating Equations 2; GEE2) to analyse data from 1435 family members within 469 families of different sizes included in the Donolo-Tel Aviv Three-Generation Offspring Study. The usual robust variance matrix was approximated by extensions of jackknife estimators of variance to GEE2 models. Upon use of this approach estimation of standard errors in models with quite complex correlation structures was possible. All analyses were easily carried out using a menu-driven stand-alone software tool for marginal regression modelling. We demonstrate that a var. Minimize

Contributors:

The Pennsylvania State University CiteSeerX Archives

Year of Publication:

2009-04-13

Source:

ftp://ftp.stat.uni-muenchen.de/pub/sfb386/paper168.ps.Z

ftp://ftp.stat.uni-muenchen.de/pub/sfb386/paper168.ps.Z Minimize

Document Type:

text

Language:

en

Subjects:

Apolipoprotein ; Atherosclerosis ; Correlated Data Analysis ; Familial Aggregation ; Family Data ; Generalised Estimating Equations ; Jackknife ; Marginal Model

Apolipoprotein ; Atherosclerosis ; Correlated Data Analysis ; Familial Aggregation ; Family Data ; Generalised Estimating Equations ; Jackknife ; Marginal Model Minimize

DDC:

310 Collections of general statistics *(computed)*

Rights:

Metadata may be used without restrictions as long as the oai identifier remains attached to it.

URL:

Content Provider:

My Lists:

My Tags:

Notes:

Title:

The Generalized Estimating Equations in the Past Ten Years: An Overview and A Biomedical Application

Author:

Description:

The Generalized Estimating Equations (GEE) proposed by Liang and Zeger (1986) have found considerable attention in the last years and several extensions have been proposed. This paper will give a more intuitive description how GEE have been developed during the last years. Additionally we will describe the advantages and disadvantages of the dif...

The Generalized Estimating Equations (GEE) proposed by Liang and Zeger (1986) have found considerable attention in the last years and several extensions have been proposed. This paper will give a more intuitive description how GEE have been developed during the last years. Additionally we will describe the advantages and disadvantages of the different parametrisations that have been proposed in the literature. We will also give a brief review of the literature available on this topic. Keywords: Generalized Estimating Equations, Marginal Models, Correlated Data Analysis 1 Introduction The primary goal of the analysis is in most regression models to investigate the influence of certain covariates on the response variable. Theoretical results for estimating parameters in regression models are available mainly for continuous and normal distributed response variables. However, in praxis the response variable is often binary or categorical and only recently some theoretical work has been pu. Minimize

Contributors:

The Pennsylvania State University CiteSeerX Archives

Year of Publication:

2009-04-12

Source:

ftp://ftp.stat.uni-muenchen.de/pub/sfb386/paper24.ps.Z

ftp://ftp.stat.uni-muenchen.de/pub/sfb386/paper24.ps.Z Minimize

Document Type:

text

Language:

en

Subjects:

Generalized Estimating Equations ; Marginal Models ; Correlated Data Analysis

Generalized Estimating Equations ; Marginal Models ; Correlated Data Analysis Minimize

DDC:

310 Collections of general statistics *(computed)*

Rights:

Metadata may be used without restrictions as long as the oai identifier remains attached to it.

URL:

Content Provider:

My Lists:

My Tags:

Notes:

Title:

Identifying Influential Families Using Regression Diagnostics For Generalized Estimating Equations

Author:

Description:

The Generalized Estimating Equations (GEE) is an approach to analyze correlated data. It is applied here to data from an epidemiological study of oesophageal cancer in a high incidence area in China to investigate familial aggregation. Regression diagnostics for mean structures and association structures are used to identify families that influe...

The Generalized Estimating Equations (GEE) is an approach to analyze correlated data. It is applied here to data from an epidemiological study of oesophageal cancer in a high incidence area in China to investigate familial aggregation. Regression diagnostics for mean structures and association structures are used to identify families that influence estimates of these structures. It is shown that most of the families influencing the mean structure have a low age of disease onset in common. Most families identified by regression diagnostics for the association structure influence the parent correlation. It is concluded that regression diagnostic techniques can be used to identify clusters influencing mean and association structures of the models. Keywords: Correlated Data, Familial Aggregation, Marginal Model, Pseudo Maximum Likelihood Estimation 1 Introduction The Generalized Estimating Equations (GEE; Liang and Zeger, 1986; Prentice, 1988) is a method to investigate correlated data. I. Minimize

Contributors:

The Pennsylvania State University CiteSeerX Archives

Year of Publication:

2009-04-13

Source:

ftp://ftp.stat.uni-muenchen.de/pub/sfb386/paper60.ps.Z

ftp://ftp.stat.uni-muenchen.de/pub/sfb386/paper60.ps.Z Minimize

Document Type:

text

Language:

en

Subjects:

Correlated Data ; Familial Aggregation ; Marginal Model ; Pseudo Maximum Likelihood Estimation

Correlated Data ; Familial Aggregation ; Marginal Model ; Pseudo Maximum Likelihood Estimation Minimize

DDC:

310 Collections of general statistics *(computed)*

Rights:

Metadata may be used without restrictions as long as the oai identifier remains attached to it.

URL:

Content Provider:

My Lists:

My Tags:

Notes:

Title:

Longitudinal Data With Dropouts: A Comparison of Pattern Mixture Models With Complete Case Analysis

Author:

Description:

Pattern mixture models constitute an alternative to selection models (Rubin, 1987). Little and Wang (1996) introduced pattern mixture models for analyzing multivariate normal longitudinal data with missing values. This paper was the theoretical foundation and the induce to investigate the small sample properties of pattern mixture models compare...

Pattern mixture models constitute an alternative to selection models (Rubin, 1987). Little and Wang (1996) introduced pattern mixture models for analyzing multivariate normal longitudinal data with missing values. This paper was the theoretical foundation and the induce to investigate the small sample properties of pattern mixture models compared with complete case analysis. The main point of interest, of the simulations, was the mean square error of the estimated model parameters. Parameters estimated by the pattern mixture model are very satisfying under ignorable mechanism but they have to be scanned carefully under nonignorable mechanism. 1 Introduction In longitudinal data often wave nonresponse occurs. In this case Maximum Likelihood (ML) is one possibility to deal with nonresponse (Little and Rubin, 1987). To factorize the likelihood two common approaches exist: selection models (SM) and pattern mixture models (PMM). Where the main interest is not the marginal mean av. Minimize

Contributors:

The Pennsylvania State University CiteSeerX Archives

Year of Publication:

2009-04-14

Source:

ftp://ftp.stat.uni-muenchen.de/pub/sfb386/paper188.ps.Z

ftp://ftp.stat.uni-muenchen.de/pub/sfb386/paper188.ps.Z Minimize

Document Type:

text

Language:

en

DDC:

310 Collections of general statistics *(computed)*

Rights:

Metadata may be used without restrictions as long as the oai identifier remains attached to it.

URL:

Content Provider:

My Lists:

My Tags:

Notes:

Currently in BASE: 69,426,436 Documents of 3,331 Content Sources

http://www.base-search.net