Missing Data in Quantitative Social Research

Almost invariably, the data available to the social scientist display one or more characteristics of missing information. Even though reasons for non response are varied, most frequently, they reflect the unwillingness of respondents to provide information on undesirable social behaviours and on issues considered as private. Besides these, sloppy research designs often leads to ambiguous and poorly structured survey questions which provide a recipe for low response. Longitudinal surveys also suffer from incompleteness due to attrition resulting from death and emigration, while in retrospective surveys, memory effect might be a major source of non-response. While there is no consensus among methodologists on the single most effective technique of handling missing information, certain pertinent questions need to be addressed: should we completely ignore the missing data and proceed with the analysis? What are the implicit assumptions if one adopts such an approach and how unbiased will our estimates be? This paper reviews a variety of methods of handling missing information