Search

There is an ongoing debate in the survey research literature about whether and when probability and nonprobability sample surveys produce accurate estimates of a larger population. Statistical theory provides a justification for confidence in probability sampling as a function of the survey design, whereas inferences based on nonprobability sampling are entirely dependent on models for validity. This article reviews the current debate about probability and nonprobability sample surveys. We describe the conditions under which nonprobability sample surveys may provide accurate results in theory and discuss empirical evidence on which types of samples produce the highest accuracy in practice. From these theoretical and empirical considerations, we derive best-practice recommendations and outline paths for future research.

Latent class (LC) analysis is a widely used method for extracting meaningful groups (LCs) from data. The basic concept was introduced by Paul Lazarsfeld in 1950 for building typologies (or clusters) from dichotomous variables as part of his more general latent structure analysis. In 1974, Leo Goodman operationalized and extended LC analysis using maximum likelihood methods, which resolved previous implementation problems. After 1995, extensions to traditional LC modeling took place, and Jeroen K. Vermunt and Jay Magidson defined the LC model more generally as any model where some parameters differ across unobserved subgroups called LCs. LC modeling has since become a general multivariate modeling approach for revealing latent segments based on any set of observed indicators, across a wide range of applications. In particular, LC generalizes traditional cluster, factor, and item response theory analyses and also generalizes various kinds of regression modeling where the parameters that differ for different classes are the regression coefficients. This entry discusses traditional LC modeling, tools for determining the number of classes, approaches for identifying meaningful classes, and advanced LC regression models for analyzing ratings and choice data. Several other topics—such as dealing with covariates using one-step and three-step approaches, multilevel LC models, latent Markov models, and LC growth models—are also briefly discussed.

Interviewing older persons requires specific attention to a number of age-related issues. These may include changes in cognitive processes, hearing and seeing impairments, and other health issues but also a different pace of life or increased tiredness. In addition, older persons have a lifetime of experience from which they can draw. Paying careful attention to these aspects when interviewing older persons can increase rapport and trust and consequently enhance the depth of these interviews. This entry outlines some ways in which interviewers can accomplish such depth. Instead of focusing on general methodological interview procedures and skills, this entry focuses on the more subtle level of views, attitude, and reflective openness.

This chapter offers readers a general overview of proxy reporting in health surveys. The primary objective of health surveys is to collect high quality information from a sample of persons carefully selected from the population of interest. The chapter first reviews the rationale for collecting proxy reports as a substitute for self-reports. Second, a description of three target populations that are commonly the focus of proxy reporting (children, elderly, and disabled) and the extent to which proxy reporting is used for each is provided. Examples of measures commonly collected using proxy respondents are then examined. The chapter also reviews the quality issues surrounding the collection of proxy reports and how such reports may impact the survey results. Lastly, some general conclusions about proxy reporting in health surveys are outlined.

Regression discontinuity design (RDD) is a causal inference technique that can be used with observational data. Social scientists are often faced with challenges when using observational data in contexts where an experimental design is infeasible. In such contexts, under fewer assumptions relative to other causal inference techniques, an RDD may be useful to isolate causal effects. RDD has gained traction over the past decades in various disciplines, including economics, political science, sociology, and epidemiology, to an