Some evidence on validity of survey results

Abstract

Data from sample surveys are subject to many sources of error. The most commonly discussed of these are sampling errors i.e., errors in the estimates which arise as a result of not including the whole population in the enumeration process. However, even when a complete enumeration of the population is carried out, the data obtained (and the conclusions reached) may be subject to serious error due to faults in the method of measurement or observation. These response errors are a component of the total error in the survey estimates and may arise from faults in the questionnaire, from badly conducted fieldwork, or from inaccuracy in the respondent's answers.