Respondent-Driven Sampling: An Assessment of Current Methodology

Respondent-Driven Sampling (RDS) employs a variant of a link-tracing network sampling strategy to collect data from hard-to-reach populations. By tracing the links in the underlying social network, the process exploits the social structure to expand the sample and reduce its dependence on the initial (convenience) sample.The current estimators of population averages make strong assumptions in order to treat the data as a probability sample. We evaluate three critical sensitivities of the estimators: to bias induced by the initial sample, to uncontrollable features of respondent behavior, and to the without-replacement structure of sampling.Our analysis indicates: (1) that the convenience sample of seeds can induce bias, and the number of sample waves typically used in RDS is likely insufficient for the type of nodal mixing required to obtain the reputed asymptotic unbiasedness; (2) that preferential referral behavior by respondents leads to bias; (3) that when a substantial fraction of the target population is sampled the current estimators can have substantial bias.This paper sounds a cautionary note for the users of RDS. While current RDS methodology is powerful and clever, the favorable statistical properties claimed for the current estimates are shown to be heavily dependent on often unrealistic assumptions. We recommend ways to improve the methodology.     

Overseas Field Placement: An Educational Experiment

This paper describes an educational experiment with the placement of second-year students in field settings in the United Kingdom. The practicum assignments were in a rural area of Northern Scotland and in London. The paper also includes a preliminary analysis of the educational goals and the unique personal and professional gains for faculty and students.     

An Experiment with a Confidentiality Reminder in a Telephone Survey

The effect of a confidentiality reminder was tested during atelephone survey of the general public of a metropolitan area.One-half of the sample was administered the reminder just priorto the demographic questions; the other half of the sample didnot receive the treatment. The results showed no significantdifferences on the distribution of nonsubstantive responsesbetween the two groups. There was some evidence that the confidentialityreminder had a negative effect on data quality.     

An Experiment in Teaching Social Relationships

In an age of increasing global and multicultural forces, the social studies is usually the subject charged with promoting a deeper level of understanding in regards to cultural diversity. To achieve this mission, many social studies teachers have turned to the use of world fairs. However, these activities often end up promoting surface level understandings, and may even end up reinforcing existing stereotypes amongst students. In this article, the authors, based upon key research in this area, provide a meaningful framework for teachers, when using world fairs. This framework better situates students for a deeper, more substantive understanding of culture.     

An Experiment in Overseas Field Instruction

This paper reports on a study that examined the knowledge needed for practice in community mental health and the primary source for this knowledge. Differences were found in knowledge areas needed for practice in community mental health settings when contrasted with practice in more traditional mental health agencies. The most frequently indicated source of knowledge for social work roles in community mental health was on-the-job experience. Courses in social work schools were not a primary source of knowledge for the many nonclinical roles undertaken by social workers in community mental health.     

An Experiment to Modify Self-Concept and School Performance

Abstract

The joint or combined effects of age level, sex differences, and social factors in fear of crime are systematically investigated using elaboration analysis with 1976 NORC data. Findings reveal that while the elderly are somewhat more likely to report fear of crime when compared with young and middle-aged groups, many more women express apprehension than men at each age level. Fear of being victimized is especially prevalent among those segments of the population that are the most isolated and vulnerable, notably elderly and middle-aged black women, unmarried older women living alone, elderly women in poor health, and women of all ages who had been burglarized.     

An Experiment Inspired by Fourier: J.B. Godin's Familistere in Guise

Founded in 1859 by Jean‐Baptiste Godin, the Familistere in Guise (France) is one of the rare, if not the only Fourierist experiment to pass successfully the test of time. Like C. Fourier, who inspired him, Godin thought and acted above all in terms of social experimentation. What were the main social innovations to see the light within the scope of such research? In what way could they be said to have remained faithful to Fourier? And, in the end, how can we explain that Godin succeeded where so many other Fourierists had failed? In order to answer this question, a first section sketches the portrait and trajectory of Godin. The paper then mentions Godin's principal belief and analyzes a few Fourier‐inspired experiments carried out by Godin in order to promote industrial democracy. It also points to the limits of the schemes imagined by Godin to permit a community of sometimes nearly 2,000 men, women and children to exist.     

An Experiment on the Social Facilitation of Gambling Behavior

Research and theory regarding the social facilitation effect generates the expectation that the presence of other gamblers (or co-actors) in a gaming venue is likely to intensify individual gambling behavior and magnify losses. Fifty male and 66 female participants (116 total) played a computer-simulated electronic gaming machine with a fixed winning sequence, followed by an indefinite losing sequence. Measures of the intensity of gambling behavior included the final payout (a direct measure of losses), average bet-size, number of trials played, and the speed of play. Some participants received false feedback from the computer designed to suggest that other gamers in adjacent rooms were playing and sometimes winning at the same game. Persons who received both sight and sound information, including winning bells and instant messages regarding the wins of other (fake) players, placed more bets and lost more money compared to the other conditions with less information.     

Gender,Management and Market Discourse: The Case of Gender Quotas in the Swedish and Finnish Media

In this article we present a comparative study of media texts in Sweden and Finland, two societies traditionally viewed as Nordic welfare states. Focusing on the controversial question of introducing gender‐based quotas on the boards of companies, we analyse how representations of gender and management are affected in Sweden and Finland by contemporary market discourse. We argue that market discourse takes different forms in the two societal contexts and that the space for questioning and criticizing it from a gender equality perspective remains different. Our analysis thus complements recent contributions stressing that both societal particularities and transnational processes must be considered in studies of gender and management ( Calás and Smircich, 2006 ).     

An Experiment on the Measurement of Political Knowledge in Surveys

In a series of articles, Mondak and colleagues argue that theconventional way of measuring political knowledge in surveysis flawed. Personality related "propensity to guess" underestimatesthe level of political knowledge in the population and distortsestimates of between group differences, when a DK alternativeis offered. This has led Mondak to recommend the use of closed-endeditems on which DKs are not explicitly offered, following bestpractice in the field of educational testing. In this article,we present the results of an experimental study which callsinto question the wisdom of this approach. Our results showlittle evidence of partial knowledge concealed within DK responses;when people who initially select a DK alternative are subsequentlyasked to provide a "best guess," they fare statistically nobetter than chance. We conclude that opinion researchers shouldbe cautious about adopting Mondak's recommendations for thedesign of political knowledge items in surveys. Received for publication February 22, 2005. Revision received October 19, 2006. Accepted for publication October 25, 2006.     

An Experiment in Curriculum Innovation in Graduate Social Work Education

This paper reports on the results of an experiment in student-centered learning. Students were randomly assigned to one of nine groups and one faculty member was assigned to each group for a six-week term. A case example served as a point of reference for selecting seminar content. Evaluation of the experience centered on the extent of student learning and the degree to which students and faculty met their objectives. The students showed evidence of learning but future efforts in this area should concentrate on the clear explication of objectives as well as the faculty facilitator's role.     

Betting on Illusory Patterns: Probability Matching in Habitual Gamblers

Why do people gamble? A large body of research suggests that cognitive distortions play an important role in pathological gambling. Many of these distortions are specific cases of a more general misperception of randomness, specifically of an illusory perception of patterns in random sequences. In this article, we provide further evidence for the assumption that gamblers are particularly prone to perceiving illusory patterns. In particular, we compared habitual gamblers to a matched sample of community members with regard to how much they exhibit the choice anomaly ‘probability matching’. Probability matching describes the tendency to match response proportions to outcome probabilities when predicting binary outcomes. It leads to a lower expected accuracy than the maximizing strategy of predicting the most likely event on each trial. Previous research has shown that an illusory perception of patterns in random sequences fuels probability matching. So does impulsivity, which is also reported to be higher in gamblers. We therefore hypothesized that gamblers will exhibit more probability matching than non-gamblers, which was confirmed in a controlled laboratory experiment. Additionally, gamblers scored much lower than community members on the cognitive reflection task, which indicates higher impulsivity. This difference could account for the difference in probability matching between the samples. These results suggest that gamblers are more willing to bet impulsively on perceived illusory patterns.