• No results found

Uncertainty Intervals and Sensitivity Analysis for Missing Data

N/A
N/A
Info
Download
Protected

Academic year: 2022

Share "Uncertainty Intervals and Sensitivity Analysis for Missing Data"

Copied!
2
0
0

Loading.... (view fulltext now)

Download now ( 2 Page )

Full text

(1)

Deparment of statistics

Umeå School of Business and Economics Umeå University

Umeå 2016

Statistical Studies No. 50

Uncertainty Intervals and

Sensitivity Analysis for Missing Data

Minna Genbäck

Akademisk avhandling

som med vederbörligt tillstånd av Rektor vid Umeå universitet för avläggande av filosofie doktorsexamen framläggs till offentligt försvar i Hörsal E, Humanisthuset, fredagen den 25 november, kl. 10:00.

Avhandlingen kommer att försvaras på engelska.

Fakultetsopponent: Docent, Arvid Sjölander,

Institutionen för medicinsk epidemiologi och biostatistik, Karolinska

Institutet, Stockholm, Sverige.

(2)

Organization Document type

Date of publication

Umeå University Doctoral thesis 4 November 2016

Department of statistics Umeå School of Business and Economics

Author

Minna Genbäck

Title

Uncertainty Intervals and Sensitivity Analysis for Missing Data

Abstract

In this thesis we develop methods for dealing with missing data in a univariate response variable when estimating regression parameters. Missing outcome data is a problem in a number of applications, one of which is follow-up studies. In follow-up studies data is collected at two (or more) occasions, and it is common that only some of the initial participants return at the second occasion. This is the case in Paper II, where we investigate predictors of decline in self reported health in older populations in Sweden, the Netherlands and Italy. In that study, around 50% of the study participants drop out. It is common that researchers rely on the assumption that the missingness is independent of the outcome given some observed covariates. This assumption is called data missing at random (MAR) or ignorable missingness mechanism. However, MAR cannot be tested from the data, and if it does not hold, the estimators based on this assumption are biased. In the study of Paper II, we suspect that some of the individuals drop out due to bad health.

If this is the case the data is not MAR. One alternative to MAR, which we pursue, is to incorporate the uncertainty due to missing data into interval estimates instead of point estimates and uncertainty intervals instead of confidence intervals. An uncertainty interval is the analog of a confidence interval but wider due to a relaxation of assumptions on the missing data. These intervals can be used to visualize the consequences deviations from MAR have on the conclusions of the study. That is, they can be used to perform a sensitivity analysis of MAR.

The thesis covers different types of linear regression. In Paper I and III we have a continuous outcome, in Paper II a binary outcome, and in Paper IV we allow for mixed effects with a continuous outcome. In Paper III we estimate the effect of a treatment, which can be seen as an example of missing outcome data.

Keywords

missing data, missing not at random, non-ignorable, set identification, uncertainty intervals, sensitivity analysis, self reported health, average causal effect, average causal effect on the treated, mixed-effects models

Language

ISBN ISSN

Number of pages

English 978-91-7601-555-1 1100-8989 13 + 4 papers

References

Download now ( PDF - 2 Page - 73.48 KB )

Related documents

Load-Adjusted Video Quality Prediction Methods for Missing Data

the server and client service metrics. We develop a system characterization model in Section III which describes how the server and client’s service level metrics behave under

Kartläggning och analys av patientflödet genom Käkkirurgen vid Linköpings Universitetssjukhus : Genomloppstidsförkortning för patientärenden som passerar genom Käkkirurgen vid Linköpings Universitetssjukhus

Enheten har gjort en del satsningar för att minska kön till att få komma till nybesök, bland annat har personal kallats in för att arbeta under helger och kvällar och under

A Framework for Evaluation and Design of an Integrated Public Transport System

The kind of integrated services that combines a fixed route service and a demand responsive service has not been studied in the same way, especially not for local area

Analysis of 2-visit COPDgene data with consideration of missing data

[r]

Causal discovery in the presence of missing data

De- pending on how they are missing, the (conditional) independence rela- tions in the observed data may be different from those for the complete data generated by the underlying

Missing Data - A Gentle Introduction

Looking at the results from the normal data, it can be seen that maximum likelihood seem to produce more narrow confidence intervals compared to multiple imputation, but the

Reasons for Missing Data of Risk Categorisation in NPCR

In contrast to men missing data for risk stage category in general, men that are younger, have lower CCI, and/or are discovered by non symptomatic reasons, attending

Empirical Bayes methods for missing data analysis

From the results in chapter 5.2.2 we can conclude that the Empirical Bayes method gives better estimates of the true value of π i compared to the other general imputation methods.