Reducing Sources of Error in Data Collection

This chapter considers how weaknesses in different aspects of data collection can affect the accuracy of our results. There are two main sections: concepts of error and methods to reduce error. The first section introduces the general idea of survey error, discusses the concepts of bias and variance, and provides an overview of unit and item nonresponse. The main measures of survey quality that these core concepts suggest are then summarized. We note the increase in unit nonresponse in recent years and suggest a framework for selecting procedures to address that problem. This background sets the stage for the second part of the chapter in which we consider methods to reduce the sources of error. 1 Some sources of error are common to both interviewer-administered and self-administered surveys. We will deal with interviewer-administered surveys first, and note issues common to both data collection modes. Last, we take up issues Imagine ...

Users without a subscription are not able to see the full content on this page. Please, subscribe or login to access all Methods content.

Click here to see full text

Articles in SAGE Journals by

Articles in Google Scholar by