„... useful... for the theoretically inclined surveystatistician...“ (Technometrics, May 2007)
„This impressivepiece of work can be thoroughly recommended to anyone“(Zentralblatt MATH Volume 1079)
Around the world a multitude of surveys are conducted every day, ona variety of subjects, and consequently surveys have become anaccepted part of modern life. However, in recent years surveyestimates have been increasingly affected by rising trends innonresponse, with loss of accuracy as an undesirable result. Whilstit is possible to reduce nonresponse to some degree, it cannot becompletely eliminated. Estimation techniques that accountsystematically for nonresponse and at the same time succeed indelivering acceptable accuracy are much needed.
Estimation in Surveys with Nonresponse provides anoverview of these techniques, presenting the view of nonresponse asa normal (albeit undesirable) feature of a sample survey, one whosepotentially harmful effects are to be minimised.
* Builds in the nonresponse feature of survey data collection asan integral part of the theory, both for point estimation and forvariance estimation.
* Promotes weighting through calibration as a new and powerfultechnique for surveys with nonresponse.
* Highlights the analysis of nonresponse bias in estimates andmethods to minimize this bias.
* Includes computational tools to help identify the bestvariables for calibration.
* Discusses the use of imputation as a complement to weighting bycalibration.
* Contains guidelines for dealing with frame imperfections andcoverage errors.
* Features worked examples throughout the text, using realdata.
The accessible style of Estimation in Surveys withNonresponse will make this an invaluable tool for surveymethodologists in national statistics agencies and private surveyagencies. Researchers, teachers, and students of statistics, socialsciences and economics will benefit from the clear presentation andnumerous examples.
Estimation in Surveys with Nonresponse provides anoverview of these techniques, presenting the view of nonresponse asa normal (albeit undesirable) feature of a sample survey, one whosepotentially harmful effects are to be minimised.
* Builds in the nonresponse feature of survey data collection asan integral part of the theory, both for point estimation and forvariance estimation.
* Promotes weighting through calibration as a new and powerfultechnique for surveys with nonresponse.
* Highlights the analysis of nonresponse bias in estimates andmethods to minimize this bias.
* Includes computational tools to help identify the bestvariables for calibration.
* Discusses the use of imputation as a complement to weighting bycalibration.
* Contains guidelines for dealing with frame imperfections andcoverage errors.
* Features worked examples throughout the text, using realdata.
The accessible style of Estimation in Surveys withNonresponse will make this an invaluable tool for surveymethodologists in national statistics agencies and private surveyagencies. Researchers, teachers, and students of statistics, socialsciences and economics will benefit from the clear presentation andnumerous examples.
