Fitting a linear model to survey data when the long-term average daily intake of a dietary component is an explanatory variable
Titelübersetzung:Verbesserung eines linearen Modells von Längsschnittdaten zur Nahrungsmittelaufnahme von diätetischen Komponenten als erklärende Variable von Gesundheit
Autor/in:
Kott, Phillip S.; Guenther, Patricia M.; Wagstaff, David A.; Juan, WenYen; Kranz, Sibylle
Quelle: Survey Research Methods, 3 (2009) 3, S 157-165
Inhalt: "The National Health and Nutrition Examination Survey (NHANES) collects information on both dietary intake and health conditions from a complex sample of individuals in the US. Instrumental-variable regression can be used to model an individual's health-related attribute as a linear function of explanatory variables including the average daily intake of dietary components. This overcomes the apparent limitation of the NHANES collecting dietary intake data on only two days per sampled individual because the averages of two days per individual exhibit considerable intra-individual variability. Readily available software routines can perform survey-sensitive instrumental-variable regression with data like that collected by the NHANES, but the relevant quantitative literature is not clear about what parameters these routines are actually estimating. The authors fit the long-term (usual) serum beta-carotene level of a population of women aged 20-64 to a linear function of each woman's long-term average (usual) daily beta-carotene intake from food and other explanatory variables using survey-sensitive instrumental regression and provide two interpretations of the results." (author's abstract)
Schlagwörter:nutrition; Gesundheit; North America; regression analysis; Nahrungsmittel; ernährungsbedingte Krankheit; health consequences; nutrition-related illness; Nordamerika; remuneration for members of parliament; Lebensalter; United States of America; Verhalten; food; Lebenserwartung; behavior; Regressionsanalyse; life expectancy; Lebensmittel; Mittelwert; USA; woman; Ernährung; gesundheitliche Folgen; mean; Diäten; age; health
SSOAR Kategorie:Forschungsarten der Sozialforschung, Erhebungstechniken und Analysetechniken der Sozialwissenschaften, Gesundheitspolitik
Impact of mixed survey modes on physical activity and fruit/ vegetable consumption: a longitudinal study
Titelübersetzung:Einsatz gemischter Umfragemethoden über körperliche Aktivitäten und Obst-/ Gemüseverbrauch: eine Längsschnittuntersuchung
Autor/in:
Nigg, Claudio R.; Motl, Robert W.; Wong, Kristin T.; Yoda, Lisa U.; McCurdy, Dana K.; Paxton, Raheem; Horwath, Caroline C.; Dishman, Rod K.
Quelle: Survey Research Methods, 3 (2009) 2, S 81-90
Inhalt: "It is recommended that researchers who use mixed modal methods for data collection compare their impact on outcome measures. The purpose of this study was to examine the physical activity and fruit/ vegetable consumption behaviors of a multiethnic sample of adults, comparing participants who continued a telephone survey and those who transitioned from a telephone to a web-based survey for a follow-up data collection point. This longitudinal study used a random sample of 700 Hawaii residents (63.3% Female; Mean age=47, SD=17.1). At baseline, participants completed a computer-assisted telephone interview assessing the stage, behavior, and decisional balance of both physical activity and fruit/ vegetable consumption. For the three-month follow-up survey, participants were given the option of completing the survey either on the web or by phone. Repeated measures analysis of variance (ANOVA) was computed for related physical activity scales and fruit/ vegetable consumption variables to compare the change in response across time between a web group and phone group. For both physical activity and fruit/ vegetable consumption, all mode-by-time interactions were significant). The participants who preferred the telephone survey maintained their levels, whereas those who preferred the web survey reported a decrease in each variable. These results suggest that changing the mode of a survey may introduce a systematic bias in data and that researchers should proceed with caution when using mixed modes of data collection." (author's abstract)
Schlagwörter:US citizen; vegetarianism; online survey; Internet; North America; comparison of methods; eating behavior; Agrarprodukt; telephone interview; Verbraucher; Nordamerika; Vegetarismus; influence; consumer; Telefoninterview; United States of America; Essverhalten; Methodenvergleich; activity; sports; Online-Befragung; Sport; US-Amerikaner; USA; Einfluss; Konsumverhalten; consumption behavior; Internet; Aktivität; gender-specific factors; agricultural product
SSOAR Kategorie:Forschungsarten der Sozialforschung, Erhebungstechniken und Analysetechniken der Sozialwissenschaften
Differential response rates in postal and web-based surveys in older respondents
Titelübersetzung:Unterschiedliche Antwortraten bei postalischen und webbasierten Untersuchungen bei älteren Befragten
Autor/in:
Bech, Mickael; Kristensen, Morton Bo
Quelle: Survey Research Methods, 3 (2009) 1, S 1-6
Inhalt: "Response rates were compared across a postal and a web-based survey containing the same questions about preferences for future for the design of future nursing homes which were sent to a random sample of 10.000 individuals aged 50-75 years. The 10.000 individuals were randomly allocated to receive a postal questionnaire or a letter with a web link to an online version of the same questionnaire. The web-based survey gave a significantly lower response rate than the postal survey. The web-based version improved the sample representativeness with respect to gender but worsened the representativeness with respect to age. Respondents' characteristics in the web-based survey differed significantly from those of respondents in the postal survey with respect to income, education, civil status and health status. The web-based version improved data quality by significantly lowering the number of item non-response and 'don't know' answers. Respondents found it easier to answer the web-based survey. The cost per response was significantly higher for the web-based survey because of the significantly lower response rate compared to the postal survey." (author's abstract)
Schlagwörter:website; alter Mensch; Internet; Pflegeheim; postalische Befragung; Denmark; Datenqualität; questionnaire; data quality; Dänemark; Fragebogen; Antwortverhalten; cost-benefit analysis; representativity; survey; future; Befragung; Zukunft; Website; Kosten-Nutzen-Analyse; Repräsentativität; Internet; mail survey; elderly; response behavior; nursing home
SSOAR Kategorie:Forschungsarten der Sozialforschung, Erhebungstechniken und Analysetechniken der Sozialwissenschaften
Variance estimation for complex indicators of poverty and inequality using linearization techniques
Titelübersetzung:Varianzenschätzung für komplexe Indikatoren von Armut und Ungleichheit bei Verwendung von Linearisierungstechniken
Autor/in:
Osier, Guillaume
Quelle: Survey Research Methods, 3 (2009) 3, S 167-195
Inhalt: "The paper presents the Eurostat experience in calculating measures of precision, including standard errors, confidence intervals and design effect coefficients - the ratio of the variance of a statistic with the actual sample design to the variance of that statistic with a simple random sample of same size - for the 'Laeken' indicators, that is, a set of complex indicators of poverty and inequality which had been set out in the framework of the EU-SILC project (European Statistics on Income and Living Conditions). The Taylor linearization method (Tepping, 1968; Woodru, 1971; Wolter, 1985; Tillé, 2000) is actually a well-established method to obtain variance estimators for nonlinear statistics such as ratios, correlation or regression coefficients. It consists of approximating a nonlinear statistic with a linear function of the observations by using first-order Taylor Series expansions. Then, an easily found variance estimator of the linear approximation is used as an estimator of the variance of the nonlinear statistic. Although the Taylor linearization method handles all the nonlinear statistics which can be expressed as a smooth function of estimated totals, the approach fails to encompass the 'Laeken' indicators since the latter are having more complex mathematical expressions. Consequently, a generalized linearization method (Deville, 1999), which relies on the concept of influence function (Hampel, Ronchetti, Rousseeuw and Stahel, 1986), has been implemented. After presenting the EU-SILC instrument and the main target indicators for which variance estimates are needed, the paper elaborates on the main features of the linearization approach based on influence functions. Ultimately, estimated standard errors, confidence intervals and design effect coefficients obtained from this approach are presented and discussed." (author's abstract)
Schlagwörter:EU; Dauerarbeitslosigkeit; education; European Commission; Schätzung; statistical method; risk; Europäische Kommission; Methode; persistent unemployment; social inequality; Einkommensverteilung; inequality; unemployment; poverty; EU; Bildung; gender; Lebenserwartung; income; analysis of variance; Berichterstattung; statistische Methode; Armut; income distribution; Arbeitslosigkeit; Risiko; life expectancy; method; Lebensbedingungen; Einkommen; living conditions; linear model; estimation; lineares Modell; Ungleichheit; soziale Ungleichheit; reporting; Varianzanalyse
SSOAR Kategorie:Forschungsarten der Sozialforschung, Erhebungstechniken und Analysetechniken der Sozialwissenschaften, Europapolitik, soziale Probleme