Efficiency of two-phase single and multiple response-dependent sampling designs

Nirmalkanna, Ananthika (2018) Efficiency of two-phase single and multiple response-dependent sampling designs. Masters thesis, Memorial University of Newfoundland.

[img] [English] PDF - Accepted Version
Available under License - The author retains copyright ownership and moral rights in this thesis. Neither the thesis nor substantial extracts from it may be printed or otherwise reproduced without the author's permission.

Download (640kB)

Abstract

In some observational studies, it may be relatively more affordable to measure the response variable, while some covariates' data might be expensive to obtain. Therefore, collection of the covariate information might be restricted by the available budget of the study. In this situation, we need to consider sampling designs which yield powerful association tests for a given sample size by selecting more informative subjects. Using cost-efficient response-dependent two-phase sampling designs is a way to select more informative sampling units. In phase I, we have easily measured variables including the response variable for all individuals in the cohort or in a large random sample from the population, and in phase II, we obtain expensive variables for a subset of individuals selected according to their response variable and inexpensive covariates obtained in phase I. We consider the likelihood and pseudo-likelihood based methods for incomplete data analysis to make inference on the association between the expensive covariate and the response variable. We also consider multiple response-dependent sampling designs. The objective is to compare the efficiency of estimators and to identify efficient sampling design settings under each estimation method.

Item Type: Thesis (Masters)
URI: http://research.library.mun.ca/id/eprint/13715
Item ID: 13715
Additional Information: Includes bibliographical references (pages 90-94).
Keywords: Two-Phase Response-Dependent Sampling Designs
Department(s): Science, Faculty of > Mathematics and Statistics
Date: December 2018
Date Type: Submission

Actions (login required)

View Item View Item

Downloads

Downloads per month over the past year

View more statistics