Non-sampling errors can generally be divided into three types:sampling frame errors,non-response errors and measurement errors.Missing target units in the sam-pling frame,improper handling of non-responses,and misrepo...Non-sampling errors can generally be divided into three types:sampling frame errors,non-response errors and measurement errors.Missing target units in the sam-pling frame,improper handling of non-responses,and misreporting or underreport-ing of key variables in the questionnaire can all cause deviations in a survey’s results.The widespread application of Computer-Assisted Personal Interviewing(CAPI)systems and the inclusion of administrative records from government sources in sur-veys has strengthened the ability to control non-sampling errors.Taking a national fertility sampling survey as an example,this study summarizes the sources of var-ious non-sampling errors and explains how to harness big data resources such as administrative records to control non-sampling errors throughout the survey.The study analyzes the impact of three types of non-sampling errors on the results of the fertility survey and examines the strategies used to address the problems caused by these non-sampling errors.The findings indicate that non-sampling errors were the main source of total error in the survey,and that the errors found came mainly from sampling frame errors;non-response errors and measurement errors were controlled and had little impact on the survey results.展开更多
This paper proposes some exponential ratio type estimators of population mean under the situations when certain observations for some sampling units are missing. These missing observations may be for either auxiliary ...This paper proposes some exponential ratio type estimators of population mean under the situations when certain observations for some sampling units are missing. These missing observations may be for either auxiliary variable or study variable. The biases and mean square errors of the proposed estimators have been derived, up to the first order of approximation. The proposed estimators are compared theoretically with that of the existing ratio type estimators defined by [1]. It has been found that the proposed exponential ratio type estimators perform better than the mean per unit estimator even for the low positive correlation between study variable and auxiliary variable. Moreover, we obtained the conditions for which our proposed estimators are better than the corresponding ratio type estimators of [1]. To verify the theoretical results obtained, a simulation study is carried out finally.展开更多
基金sponsored by the Follow-up Research on Fertility Level and Fertility Intentions with the Help of Big Data(No.21BRK001)a research project funded by the National Social Science Fund of China.
文摘Non-sampling errors can generally be divided into three types:sampling frame errors,non-response errors and measurement errors.Missing target units in the sam-pling frame,improper handling of non-responses,and misreporting or underreport-ing of key variables in the questionnaire can all cause deviations in a survey’s results.The widespread application of Computer-Assisted Personal Interviewing(CAPI)systems and the inclusion of administrative records from government sources in sur-veys has strengthened the ability to control non-sampling errors.Taking a national fertility sampling survey as an example,this study summarizes the sources of var-ious non-sampling errors and explains how to harness big data resources such as administrative records to control non-sampling errors throughout the survey.The study analyzes the impact of three types of non-sampling errors on the results of the fertility survey and examines the strategies used to address the problems caused by these non-sampling errors.The findings indicate that non-sampling errors were the main source of total error in the survey,and that the errors found came mainly from sampling frame errors;non-response errors and measurement errors were controlled and had little impact on the survey results.
文摘This paper proposes some exponential ratio type estimators of population mean under the situations when certain observations for some sampling units are missing. These missing observations may be for either auxiliary variable or study variable. The biases and mean square errors of the proposed estimators have been derived, up to the first order of approximation. The proposed estimators are compared theoretically with that of the existing ratio type estimators defined by [1]. It has been found that the proposed exponential ratio type estimators perform better than the mean per unit estimator even for the low positive correlation between study variable and auxiliary variable. Moreover, we obtained the conditions for which our proposed estimators are better than the corresponding ratio type estimators of [1]. To verify the theoretical results obtained, a simulation study is carried out finally.
