The effect of non-normality on estimating the variance of the combined ratio estimate in complex surveys

The performance of the balanced half-sample, jackknife and linearization methods for estimating the variance of the combined ratio estimate is studied by means of a computer simulation using artificially generated non-normally distributed populations.

The results of this investigation demonstrate that the variance estimates for the combined ratio estimate may be highly biased and unstable when the underlying distributions are non-normal. This is particularly true when the number of observations available from each stratum is small. The jack-     

Changes in HIV/AIDS knowledge and testing behavior in Africa: how much and for whom?

Demographic and Health Survey data from nine African countries make it clear that HIV/AIDS prevention knowledge has been increasing. Still, in many cases, fewer than half of adult respondents can identify specific prevention behaviors. Knowledge is lowest in rural areas and among women. HIV testing generally remains rare but is highly variable across countries, likely reflecting differences in the supply of testing services. In most cases, schooling and wealth impacts on prevention knowledge have either been stable or have increased; hence, in the majority of contexts, initial disparities in knowledge by education and wealth levels have persisted or widened.

Eye-tracking methodology: exploring the processing of question formats in web surveys

In social research, the use of agree/disagree (A/D) questions is a popular method for measuring attitudes. Research has shown that A/D questions require complex cognitive processing and are susceptible to response bias. Thus, some researchers recommend the use of item-specific (IS) questions. This study examines the processing of A/D and IS questions, using eye-tracking methodology. By recording respondents’ eye movements, how respondents process survey questions can be evaluated. The results reveal that IS questions cause more and longer fixations. However, this only applies to the response categories. There are no differences regarding the question stems. Altogether, it seems that IS response categories trigger deeper cognitive processing than A/D response categories.     

Demographic differences in response rates for PHQ9 in a university student population

Objective: To examine differences in complete response rates for depression screening questions based on demographic characteristics. Methods: Cross-sectional study examining associations between demographic characteristics and completely responding depression-screening questions. Participants: “Healthy Minds Study” data, collected in a public University in February 2016, where 7,326 students participated. Results: women (AOR: 0.69; 95% CI =0.57–0.83) and gay/lesbian students (AOR: 0.24; 95% CI =0.10–0.60) had better complete response rates. Non-US (AOR: 1.46; 95% CI =1.03–2.07), black (AOR: 3.32; 95% CI =1.92–5.77), and Middle-Eastern students (AOR: 3.73; 95% CI =1.73–8.02) had lower complete response rates. Conclusions: Our study shows sex, gender, citizenship, and race categories have significant differences in complete response rates for the outcome. Our findings have several implications; including recognizing interventions for depression based on responders may not target those that tend to be “partial-responders”. Efforts in survey design, recruiting and completion of surveys should be maximized.     

Measuring the health patterns of the ‘mixed/multiple’ ethnic group in Britain: data quality problems,reporting issues,and implications for policy

The ‘mixed’ group, officially recognised in the 2001 Census, is one of the most rapidly growing ethnic groups in Britain. Although ‘mixed’ categorisation was added to ethnic coding in NHS datasets, our knowledge of health patterns for this population is meagre. Data quality problems remain a key obstacle, including poor reproducibility of the data and constraints on reporting due to sparse data bias. The consequent minimal and indicative evidence base has focused mainly on risky health behaviours, mental health and generic measures of self-rated health, as it has in the U.S.A. and Canada. There is negligible information on the main underlying causes of death, such as neoplasms, heart disease and stroke. Consideration should be given to pooling data across multiple years of health and general purpose surveys to enable reporting for the four ‘mixed’ categories and adjustment for mediating factors and relevant confounders, such as measures of socio-economic status.     

Is the web a promising tool for data collection in developing countries? An analysis of the sample bias of 10 web and face-to-face surveys from Africa,Asia, and South America

Whereas the sample composition biases of web surveys have been discussed extensively for developed countries, studies for developing countries are scarce. This article helps to fill that gap by comparing similar non-probability-based web surveys (WEB) and probability-based face-to-face (F2F) surveys both to each other and to the labor force. An analysis of WageIndicator data on work and wages derived from surveys held in 2009–2013 in 10 developing countries (WEB-sample N = 9135; F2F-sample N = 14,659), shows that F2F samples resemble the labor force to a larger extent than web samples do. In both cases, individuals in their 20s and early 30s are overrepresented, and younger and older respondents are underrepresented. This trend is more pronounced in WEB than in F2F samples. However, the differences converge in countries with higher Internet usage. A comparison of the WEB and F2F samples shows that compositions differ greatly, with web respondents being younger, more often male, more often living alone, and higher educated, although these differences are smaller in countries with higher Internet usage. Given the cost differences between the two survey modes, one should nevertheless consider the potential of web surveys as an instrument to gain explorative insights, specifically when searching for individuals with particular characteristics.     

Modelling period fertility: Schooling and intervals following a birth in Eastern Africa

We describe a regression-based approach to the modelling of age-, order-, and duration-specific period fertility, using retrospective survey data. The approach produces results that are free of selection biases and can be used to study differential fertility. It is applied to Demographic and Health Survey data for Ethiopia, Kenya, Tanzania, and Zimbabwe to investigate differential trends in fertility by education. Parity progression fell and the intervals following each birth lengthened between the 1970s and 2000s in all four countries. Fertility fell most among women with secondary education. In contrast to other world regions, postponement of successive births for extended periods accounted for much of the initial drop in fertility in these African countries. However, family size limitation by women with secondary education in Ethiopia and Kenya and longer birth spacing in Zimbabwe also played significant roles. Thus, birth control is being adopted in Eastern Africa in response to diverse changes in fertility preferences.     

How useful are the demographic surveys in explaining the determinants of early marriage of girls in the Terai of Nepal?

In recent decades significant changes in Nepalese society have greatly contributed to the increase in age at marriage of girls in Nepal. Factors responsible for these changes include educational development, urbanization and development of mass communications. However, many parents still marry their daughters at very young ages and this practice is particularly prevalent in the Terai region. This paper examines several demographic data sets with a view to assessing their utility for understanding the determinants of early age of marriage of girls in the Terai. The Nepal Family Health Survey (1996), Nepal Demographic and Health Surveys (2001, 2006), the Nepal Adolescents and Young Adults Survey (1999) and the 2001 Population Census of Nepal describe changes in at marriage over time. Factors such as sex, religion, education, geographic region, place of residence (rural/urban), economic status of the household and of women, and occupation are included in these data sets. However, other factors such as age at menarche, dowry and cost of marriage and cross-border marriage migration, which have been found to affect the prevalence of the lower age at marriage of girls in the Terai region, have not been included in the existing demographic surveys. Findings from the current study suggest that these variables should be included in future demographic surveys.     

Keeping Surveys Valid,Reliable, and Useful: A Tutorial

This tutorial focuses on how to produce reliable and generalizable data from random‐digit‐dialing (RDD) landline and cell phone surveys. The article notes that RDD response rates have declined and explores the impact of this pronounced decline. The tutorial addresses order, response mode, and many other biases, sample size, cooperation and response rates, weighting, and hybrid designs‐all using examples from risk analysis to illustrate the key points. The article ends with a brief review of the advantages and disadvantages of major Internet and paper surveys tools, and how these can be molded and sometimes combined in repeated, longitudinal, and other designs to answer questions about risk preferences and perceptions.