This paper describes the design of the sample for “Understanding Societyâ€. The sample consists of five components. The largest component is a newly-selected general population sample. The other four components are an ethnic minority ‘boost’ sample, a general population...

This paper outlines the strategy for the development and provision of analysis weights for Understanding Society. The strategy is placed within the context of a number of practical and statistical issues in the context of a survey with such a complex design, involving multiple waves, samples,...

The overall sample design for Understanding Society has been described in an earlier working paper in this series (Lynn 2009). This paper describes the special measures taken to boost the sample of members of five key minority ethnic groups in Great Britain. A new method was developed to...

This article describes a randomised experiment with mixed-mode survey designs in the context of a household panel survey. The experiment was designed to allow comparisons between two alternative mixed-mode designs (telephone interviewing plus face-to-face interviewing) and a unimode design...

This paper describes the problem of maintaining cross-sectional representativeness in a longitudinal survey of a changing population. The extent and nature of the problem is outlined and potential solutions are described. The procedures adopted on Understanding Society are described. The main...

Previous evidence suggests that a wave with mixed mode data collection in an otherwise face-to-face panel survey will achieve a lower response rate than other waves. But until now there has been no evidence as to whether the response rate can be expected to recover subsequently. In other words,...

We compare two alternative mixed mode survey designs with face-to-face data collection in terms of differences in estimates. Both mixed mode designs involve face-to-face, telephone and web interviewing. One design uses modes sequentially; the other offers respondents an explicit choice of mode....

It is common practice to adapt the format of a question to the mode of data collection. Multi-coded questions in self-completion and face-to-face modes tend to be transformed for telephone into a series of ’yes/no’ questions. Questions with response scales are often branched in...

Respondents in long telephone survey interviews may adopt satisficing strategies as they approach the end of the questionnaire (Holbrook, Green and Krosnick, 2003). However, there is inconsistency regarding the relationship between questionnaire length and different forms of satisficing. We...

We examine the effects on survey estimates of extended interviewer efforts to gain survey response, including refusal conversion attempts and attempts to make contact with hard-to- contact sample members. Specifically, we update and extend the research of Lynn & Clarke (2002). We estimate bias...