1,721,096 research outputs found
Doorstep interactions and interviewer effects on the process leading to cooperation or refusal
Full text linkThis article presents an analysis of interviewer effects on the process leading to cooperation or refusal in face-to-face surveys. The focus is on the interaction between the householder and the interviewer on the doorstep, including initial reactions from the householder, and interviewer characteristics, behaviors, and skills. In contrast to most previous research on interviewer effects, which analyzed final response behavior, the focus here is on the analysis of the process that leads to cooperation or refusal. Multilevel multinomial discrete-time event history modeling is used to examine jointly the different outcomes at each call, taking account of the influence of interviewer characteristics, call histories, and sample member characteristics. The study benefits from a rich data set comprising call record data (paradata) from several face-to-face surveys linked to interviewer observations, detailed interviewer information, and census records. The models have implications for survey practice and may be used in responsive survey designs to inform effective interviewer calling strategies
Secondary data analysis using Understanding Society Data
No full textWe analysed the Understanding Society Data from Waves 1 and 2 in our project to explore the uses of paradata in cross-sectional and longitudinal surveys with the aim of gaining knowledge that leads to improvement in field process management and responsive survey designs. </span
Effects of interviewer attitudes and behaviors on refusal in household surveys
Full text linkInterviewers play a crucial role in gaining cooperation from a sample unit. This paper aims to identify the interviewer characteristics that influence survey cooperation. Of principal interest to survey practitioners are interviewer attributes associated with higher cooperation rates, particularly among sample members whose characteristics are traditionally associated with a lower probability of response. Our data source is unusually rich, in that it contains extensive information on interviewers, including their attitudes and behaviors, which are linked to detailed information on both responding and nonresponding sample units. An important value of the data is that they permit examining a host of as yet unanswered questions about whether some interviewer attributes stimulate cooperation among some respondents but not others. In short, we investigate whether some sample units react favorably to certain interviewer characteristics. A multilevel cross-classified logistic model with random interviewer effects is used to account for clustering of households within interviewers, due to unmeasured interviewer attributes, and for the cross-classification of interviewers within areas. The model allows for statistical interactions between interviewer and household characteristics.We find that interviewer confidence and attitudes toward persuading reluctant respondents play an important role in explaining between-interviewer variation in refusal rates. We also find evidence of interaction effects between the interviewer and householder, for example with respect to gender and educational level, supporting the notion of similarity between interviewers and respondents generating higher cooperation. The results are discussed with respect to potential implications for survey practice and desig
Modelling call record data using multilevel modelling: examples from cross-sectional and longitudinal surveys
No full textNCRM's reflections and recommendations following the 2023 ESRC Data Driven Research Skills Report and Response
Full text linkThis document outlines the initial reflections of the UK’s National Centre for Research Methods (NCRM) to the ESRC’s Autumn 2023 publication of their Data Driven Research Skills (DDRS) report and their response to this report. The below sections reflect on these published documents and make suggestions towards achieving the planned vision and published commitments.
As might be expected given its remit, NCRM offers already a wide range of activities and infrastructure in support of DDR and in the training of DDRS. The document outline areas where NCRM could further support the DDRS agenda. Thus, given its relevant infrastructure, on-going training activities, and expertise, NCRM is well placed to help shape and support the investment in DDRS training recommended within the ESRC’s Report
Which schools and pupils respond to educational achievement surveys? A focus on the English PISA sample
No full textNon-response is a major problem facing research in the social sciences including in education surveys. Hence, research is needed to better understand non-response patterns as well as non-response as a social phenomenon. Findings may contribute to improvements in the future designs of such surveys. Using logistic and multilevel logistic modelling we examine correlates of non-response at the school and pupil level in the important educational achievement survey ‘Programme for International Student Assessment (PISA)’ for England. The analysis exploits unusually rich auxiliary information on all schools and pupils sampled for PISA, whether responding or not, from two large-scale administrative sources on pupils’ socio-economic background and results in national public exams. This information correlates highly with the PISA target variable. Findings show that characteristics associated with non-response differ between the school and pupil levels. Our results also indicate that schools matter in explaining pupil level response, which is often ignored in non-response analysis. Our findings have important implications for future education surveys. For example, if replacement schools are used to improve response, our results suggest that it may be more important to match initial and replacement schools on the socio-economic composition of their pupils than on any of the factors currently used
An investigation of interviewer effects on household nonresponse in six UK government surveys
No full textImputation methods in the social sciences: a methodological review
No full textMissing data are often a problem in social science data. Imputation methods fill in the missing responses and lead, under certain conditions, to valid inference. This article reviews several imputation methods used in the social sciences and discusses advantages and disadvantages of these methods in practice. Simpler imputation methods as well as more advanced methods, such as fractional and multiple imputation, are considered. The paper introduces the reader new to the imputation literature to key ideas and methods. For those already familiar with imputation methods the paper highlights some new developments and clarifies some recent misconceptions in the use of imputation methods. The emphasis is on efficient hot deck imputation methods, implemented in either multiple or fractional imputation approaches. Software packages for using imputationmethods in practice are reviewed highlighting newer developments. The paper discusses an example from the social sciences in detail, applying several imputation methods to a missing earnings variable. The objective is to illustrate how to choose between methods in a real data example. A simulation study evaluates various imputation methods, including predictive mean matching, fractional and multiple imputation. Certain forms of fractional and multiple hot deck methods are found to perform well with regards to bias and efficiency of a point estimator and robustness against model misspecifications. Standard parametric imputation methods are not found adequate for the application considered
- …
