MAIL SURVEY RESPONSE RATE: A META-ANALYSIS OF SELECTED TECHNIQUES FOR INDUCING RESPONSE

This article reports the results of a meta-analysis of experimentalstudies which have examined ten different factors felt to influenceresponse rates to mail surveys. The form of meta-analysis usedclearly defines the individual impact of each of the factorsexamined. Results indicate that prenotification and follow-upsincrease the response rate, as does the type of outgoing postageused. Furthermore, studies sponsored by a university receivegreater returns. Increases in the size of the monetary incentiveused appear to have decreasing marginal gains. Finally, someevidence exists to suggest that the color of the questionnaireinfluences response rate.     

RESPONSE

In this engagement with the idea of the common in contemporary South Africa, the author uses three episodes from his own experience in and of South Africa – a performance at the National Arts Festival in Grahamstown in 2009; a bus journey from Cape Town in 2010; news of the Marikana mine massacre in August 2012 – as well as recent work by theorists Lauren Berlant, Bernard Stiegler and Paolo Virno, as prompts to explore how issues of public and private feature in recent representations and experiences of the South African postcolony. In responding to several of the essays included in this issue, the author also discusses the role of the institutions and infrastructures of cultural mediation in the production of cultural products that engage with these issues, and gestures towards the responsibilities of intellectuals and artists in interrogating their own positions in relation to the idea of the commons in South Africa.     

RESPONSE RATES AND RESPONSE CONTENT IN MAIL VERSUS FACE-TO-FACE SURVEYS

Two surveys were administered based on the same area probabilitysampling frame and with some of the same questions: one samplewas used for hour-long face-to-face interviewing in the 1992Detroit Area Study; the other sample received a much shorterquestionnaire in the mail for sell-administration. The samplesegments had previously been stratified in terms of the percentagethat was black. For the predominantly white stratum, there wasonly a small difference in response rates due to mode of administration.For the predominantly black stratum, the mail survey obtaineda considerably lower response rate then the face-to-face survey.Within the predominantly white stratum, there were no cleardifferences between results for the two modes of administrationin demographic variables or in gross housing characteristics.However, the mail survey respondents expressed more negativeattitudes toward racial integration and affirmative action thandid the face-to-face respondents. Because the mail sample ofthe predominantly black stratum was small, it was not possibleto carry out similar analyses of demographic or attitudinaldifferences, or to determine whether its lower response ratewas due mainly to race, to correlates of race such as incomeor education, or even to problems with mail delivery in centralcities.     

MEASURING EXTREME RESPONSE STYLE

Research on extreme response style (ERS) in rating scale responseshas been characterized by conflicting findings and little agreementover how to assemble and validate ERS measures. This articleproposes that, when ERS is defined as a proportion of extremeresponses, an ERS measure will be more accurate if the itemsare uncorrelated and have equal extreme response proportions.Furthermore, appropriate stochastic models should be used toassess the internal reliability and convergent validity of thesemeasures. An ERS measure is created and validated with thismethod, using items from a survey administered in 1975 and 1987to large samples of U.S. adults serving on a consumer panel.We find that ERS is stable over a lengthy survey compared toa benchmark stability for a "perfect" measure. Furthermore,the distribution of ERS over this population is stable overtime. Respondents' ERS is related to their age, education level,and household income but not to their gender.     

RESPONSE EFFECTS IN MAIL SURVEYS

A variety of response effects that had been found previouslyin interview surveys were tested in a mail survey of a heterogeneouslocal population. These included experiments on question orderresponse order, no-opinion filters, middle-response alternatives,and acquiescence. The results generally supported earlier findingsbased on student samples which had shown that order efects wereeliminated in self-administered surveys but that question-formeffects occurred as in interview surveys. One question-ordereffect, however, was found in the mail survey, and a type ofresponse-order effect (a primacy effect) that had not been previouslytested also occured. Interactions between education and responseeffects that had sometimes been found in interview surveys werenot present in the mail survey.     

KEEPING SYMBOLIC INTERACTION SAFE FROM SEMIOTICS: A RESPONSE TO HARMAN

This article provides a critique of the particular way in which Lesley D. Harman has proposed to accommodate Symbolic Interaction to semiotic theory and method. Harman's argument rests on a belief in the reality of the nature/culture dimension as prior to semiotic or sociological theory. According to Harman's view, nature is the realm of determinism, culture is the realm of freedom, and social theory ought to align itself with freedom and culture. A semiotic alternative based on Peirce's concept of the sign is suggested. The alternative socio-semiotic approach opens the possibility of studying both cultural determinism and creative processes in nature.     

TASK CONDITIONS, RESPONSE FORMULATION PROCESSES, AND RESPONSE ACCURACY FOR BEHAVIORAL FREQUENCY QUESTIONS IN SURVEYS

Results from two studies confirm recent findings that (1) surveyrespondents often use nonepisodic processes to answer frequencyquestions about autobiographical events, and (2) task conditions,such as the number of events to be reported and the time usedin response formulation, affect the processes used. Resultssuggest that cognitive mechanisms other than episode omissionand episode telescoping contribute to response errors. It appearsthat new methodological approaches, such as directly or indirectlymanipulating the response formulation process, may be usefulin attempts to improve the accuracy of behavioral frequencyreports in surveys.     

CONFIDENTIALITY ASSURANCES AND RESPONSE: A QUANTITATIVE REVIEW OF THE EXPERIMENTAL LITERATURE

This article tests the general hypothesis that a stronger assuranceof confidentiality improves survey response by means of a meta-analysisof the experimental literature. No support is found for thegeneral hypothesis, but the subsidiary hypothesis, that confidentialityassurances improve response when the data asked about are sensitive,is supported. Under those circumstances, the effect of confidentialityassurances is small but statistically significant and is robustin the presence of a variety of control variables.     

INDUSTRIAL RESPONSE TO ELECTRICITY REAL-TIME PRICES: SHORT RUN AND LONG RUN

Real-time pricing reduces summer peak demand by approximately 8% for 110 Duke Energy industrial customers. With up to six summers on the rate, the aggregate customer response increases with experience. Examining individual customers, only a subset respond significantly, primarily those who can self-generate or with discrete (batch) production processes. These customers respond significantly above a threshold level of price. Although elasticities decrease slightly at the highest temperatures, the absolute quantity reductions are largest at these times.