sixcitydata {glmfitmiss} | R Documentation |
sixcitydata – A very well published Six city data published in many articles including Ware et al (1984), Ibrahim and Lipsitz (1996). Also avaialble in LogXact User Manual. The dataset is a longitudinal study of the health effects of air pollution (ware et al., 1984).
Description
The 'sixcitydata' dataset contains information on wheezing status, city of residence, maternal smoking habits, socioeconomic status, and medical condition of children at age 11.
The dataset includes the following variables:
Wheeze: Binary response variable indicating wheezing status of children at age 11 (1 for wheeze, 0 for no wheeze).
city: Categorical variable indicating city of residence (1 for polluted city, 0 for Portage or Wisconsin).
smoke: Binary variable indicating mother's smoking habits (1 for >20 cigarettes a day, 0 otherwise).
soc: Binary variable indicating high socioeconomic status of subject (1 for high socioecnomic status, 0 otherwise).
cond: Binary variable indicating previous medical condition of subject (1 for previous medical condition, 0 otherwise).
Usage
sixcitydata
Format
An object of class tbl_df
(inherits from tbl
, data.frame
) with 2106 rows and 5 columns.
References
Cytel Inc (2010). LogXact 9 User Manual: Discrete Regression Analysis. Cambridge, Massachusetts: Cytel Inc.
Ibrahim, J. G. (1990). Incomplete data in generalized linear models. Journal of the American Statistical Association 85, 765–769.
Maiti, T., Pradhan, V. (2009). Bias reduction and a solution of separation of logistic regression with missing covariates. Biometrics, 65, 1262-1269.
Pradhan, V., Nychka, D. and Bandyopadhyay, S. (2025). Beyond the Odds: Fitting Logistic Regression with Missing Data in Small Samples (submitted).
Ware, JH., Dockery, DW., Spiro, A III., Speizer, FE., and Ferris, BG Jr. (1984). Passive smoking, gas cooking, and respiratory health of children living in sex cities. American Review of Respiratory Disease, 129, 366-374.
Examples
data(sixcitydata)
f_fit <- emforbeta(Wheeze ~ city+soc+cond,
data=sixcitydata,
family=binomial(link="logit"), method="glm.fit")
#creates the summary like glm using the return object mfit
summary(f_fit$mfit)
vcov_beta<-f_fit$cvcov #creates variance using Louis (1982)
se_beta_em<-sqrt(diag(vcov_beta))
se_beta_em