Premium
PREFACE
Author(s) -
Lo KwangJuei,
Chang Chungming
Publication year - 1993
Publication title -
journal of gastroenterology and hepatology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.214
H-Index - 130
eISSN - 1440-1746
pISSN - 0815-9319
DOI - 10.1111/j.1440-1746.1993.tb01664.x
Subject(s) - citation , library science , medicine , computer science
When I was a graduate student more than twenty five years ago, I was struggling to read many statistical research papers. This is particularly true at the time when I had passed my Ph.D. qualification examination. The goal of this book is to make it easier for Ph.D. students and new researchers to embark in their research area. During the past 30 years, statistics has become more an applied and more diversified science. In response to this trend, I have tried to cover as many different topics as possible. My main research interest focuses on likelihood-based inferences, which includes parametric likelihood, biased sampling likelihood, semiparametric likelihood, empirical likelihood and Godambe’s estimating function theory. This book is devoted to biased sampling problems (also called choice-based sampling in econometric parlance) and over-identified parameter estimation problems. When a proper randomization cannot be achieved, the observed sample will not be representative of the population of interest. This biased sampling problem appears frequently since in the real world, truly random sampling is not easily achievable or practically feasible. Biased sampling problems appear in many areas of research, including medicine, epidemiology and public health, social sciences and economics. As pointed out by Prof. James Heckman (1979), the 2000 Nobel Laureate in Economics, “Sample selection bias may arise in practice for two reasons. First, there may be self selection by the individuals or data units being investigated. Second, sample selection decisions by analysts or data processors operate in much the same fashion as self selection”. This book would be of interest to those who work in the health, biological, social and physical sciences, as well as those who are interested in survey methodology and other areas of statistical science, among others. Due to its convenience and cost effectiveness, one of the most efficient designs in health sciences research is the case-control design. Under this design, individuals (called cases) with the condition of interest (for example, cancer) are sampled. Their risk profiles for the condition are collected. Then some controls (do not satisfy the condition of interest, for example cancer free) are enrolled along with their risk profiles are also recorded. Since the numbers of cases and controls are fixed by