Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top

2015 | Book

Statistical Surveys Read chapter Read first chapter

Pseudo-Populations

A Basic Concept in Statistical Surveys

Author: Andreas Quatember

Publisher: Springer International Publishing

Part of: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Login to get access
insite
SEARCH

About this book

This book emphasizes that artificial or pseudo-populations play an important role in statistical surveys from finite universes in two manners: firstly, the concept of pseudo-populations may substantially improve users’ understanding of various aspects in the sampling theory and survey methodology; an example of this scenario is the Horvitz-Thompson estimator. Secondly, statistical procedures exist in which pseudo-populations actually have to be generated. An example of such a scenario can be found in simulation studies in the field of survey sampling, where close-to-reality pseudo-populations are generated from known sample and population data to form the basis for the simulation process.

The chapters focus on estimation methods, sampling techniques, nonresponse, questioning designs and statistical disclosure control.

This book is a valuable reference in understanding the importance of the pseudo-population concept and applying it in teaching and research.

Table of Contents

Frontmatter
Chapter 1. Statistical Surveys
Abstract
Looking at our everyday life, we find that nearly everything that we see, taste, hear, smell, or touch is just a part of a whole. The unconscious conclusion from such information on the specific “reality” incompletely described by these observations has probably always been part of (not only) human behavior. This pattern was originally developed as a survival strategy passed on from one generation to the other. It ensured the survival of the clan (or the pack) through the evaluation of signals with respect to potential food or imminent danger.
Andreas Quatember
Chapter 2. The Pseudo-Population Concept
Abstract
Classical sampling theory addresses the effect of different sampling designs consisting of a sampling method and estimation technique, on the efficiency of the estimation of a parameter under study. Note that sampling design is used with different meanings in the literature (cf., for instance, Särndal et al. 1992, p. 27). In the practice of statistical surveys, totals and functions of totals, such as means, proportions, variances, covariances, correlations, or regression coefficients, cover a large majority of the interesting parameters. Hence, sampling theory traditionally focuses mainly on the estimation of such parameters (cf., for instance, Cochran 1977).
Andreas Quatember
Chapter 3. Nonresponse and Untruthful Answering
Abstract
Classical sampling theory considers only sampling errors and the effects of different sampling designs on this type of errors. Therefore, it can be said to be a pure full response theory with no place for nonresponse or untruthful answers. However, the practice of surveys does not comply with these assumptions. Nonresponse and untruthful answering are sources of so-called non-sampling errors. This term implies that such errors can also occur in a census.
Andreas Quatember
Chapter 4. Simulation Studies in Survey Sampling
Abstract
An example of an application of the concept of pseudo-populations in research comes from the field of computer simulation studies. This term describes a process of conducting experiments, which are actually part of real life, on the computer. In the context of statistics, simulation studies are applied when mathematical derivations of the statistical properties of a method are cumbersome or not available at all.
Andreas Quatember
Chapter 5. The Bootstrap Method in Survey Sampling
Abstract
When no explicit variance formula is available and the calculations for Taylor linearization (cf., for instance, Wolter 2007, p. 230ff) are too cumbersome, so-called computer-intensive methods that use computer power instead of heavy calculations can be applied alternatively. One such procedure is the random group method (cf., for instance, Wolter 2007, Chap. 2). In this case, the sample drawn is divided into different nonoverlapping subsamples, called “random groups,” according to the original sampling design. After calculating the original estimator of the parameter under study in each of the groups, the variance of these estimators serves as the basis for extrapolation regarding the variance of the estimator in the original sample. The calculations are truly simple, but for obvious reasons are often inefficient for complex surveys because the construction of subgroups according to the original sampling design might be difficult.
Andreas Quatember
Chapter 6. Generalized Randomized Response Questioning Designs
Abstract
When questions on sensitive subjects, such as harassment at work, domestic violence, illegal employment, number of abortions, income, or voting behavior, are asked by direct questioning, nonresponse and untruthful answering will occur. As can be seen from Eq. (3.1), in the presence of both, the HT estimator t HT, for instance, is decomposed into three sums: one over the truthful answering set s t of sample s, another over the untruthful answering set s u , and a third over the missing set s m . Hence, such behavior by a respondent may cause serious problems in the analysis of sample and population data because the estimators of population parameters based only on a survey’s available cases may strongly be biased. It is therefore essential for data collectors to not ignore nonresponse or untruthful answering. Before applying such methods as weighting adjustment and data imputation (see Sects. 3.2 and 3.3) to compensate for nonresponse that has already occurred, data collectors should do everything to make the rates of both nonresponse and untruthful answering as small as possible.
Andreas Quatember
Chapter 7. A Unified Framework for Statistical Disclosure Control
Abstract
Among the various application fields of the pseudo-population concept in statistical surveys, the area of methods for statistical disclosure control (SDC) is exceptional in a certain sense. What is unique about SDC methods is that in contrast to almost all other procedures, they are not aimed at improving, but in deliberately reducing the quality of data, which are observed in statistical surveys of the official statistics or other institutions, in a controlled way.
Andreas Quatember
Backmatter
Metadata
Title
Pseudo-Populations
Author
Andreas Quatember
Copyright Year
2015
Electronic ISBN
978-3-319-11785-0
Print ISBN
978-3-319-11784-3
DOI
https://doi.org/10.1007/978-3-319-11785-0

Premium Partner

    Image Credits