论文信息 - Correlation and Regression Analyses for Randomized Response Data

Correlation and Regression Analyses for Randomized Response Data

January 12, 2016 Type Package Title Correlation and Regression Analyses for Randomized Response Data Author Daniel W. Heck [aut, cre], Morten Moshagen [aut] Maintainer Daniel W. Heck <dheck@mail.uni-mannheim.de> Depends R (>= 3.0.0) Imports parallel, doParallel, foreach, stats, grDevices, graphics, lme4 Suggests knitr Description Univariate and multivariate methods to analyze randomized response (RR) survey designs (e.g., Warner, S. L. (1965). Randomized response: A survey technique for eliminating evasive answer bias. Journal of the American Statistical Association, 60, 63–69). Besides univariate estimates of true proportions, RR variables can be used for correlations, as dependent variable in a logistic regression (with or without random effects), as predictors in a linear regression, or as dependent variable in a beta-binomial ANOVA. For simulation and bootstrap purposes, RR data can be generated according to several models. License GPL-2 Encoding UTF-8 LazyLoad yes

Morten Moshagen | Morten Moshagen | D. Heck | DanielW. Heck

[1] Ardo van den Hout,et al. Estimating the linear regression model with categorical covariates subject to randomized response , 2006, Comput. Stat. Data Anal..

[2] Paul E. Tracy,et al. Measuring associations with randomized response , 1984 .

[3] Peter G. M. van der Heijden,et al. The logistic regression model with response variables subject to randomized response , 2007, Comput. Stat. Data Anal..

[4] S L Warner,et al. Randomized response: a survey technique for eliminating evasive answer bias. , 1965, Journal of the American Statistical Association.