logit_syn function

Logistic regression : generic synthetic binary/binomial logistic data and model

logit_syn is a generic function for developing synthetic logistic regression data and a model given user defined specifications.

logit_syn(nobs=50000, d=1,  xv  = c(1, 0.5, -1.5))

Arguments

• nobs: number of observations in model, Default is 50000
• d: binomial denominator, Default is 1, a binary logistic model. May use a variable containing different denominator values.
• xv: predictor coefficient values. First argument is intercept. Use as xv = c(intercept , x1_coef, x2_coef, ...)

Details

Create a synthetic logistic regression model using the appropriate arguments. Binomial denominator must be declared. For a binary logistic model, d=1. A variable may be used as the denominator when values differ. See examples.

Returns

• by: binomial logistic numerator; number of successes

• sim.data: synthetic data set

References

Hilbe, J.M. (2011), Negative Binomial Regression, second edition, Cambridge University Press. Hilbe, J.M. (2009), Logistic Regression Models, Chapman & Hall/CRCD

Author(s)

Joseph M. Hilbe, Arizona State University, and Jet Propulsion Laboratory, California Institute of Technology Andrew Robinson, Universty of Melbourne, Australia.

See Also

probit_syn

Examples

# Binary logistic regression (denominator=1)
sim.data <-logit_syn(nobs = 500, d = 1, xv = c(1, .5, -1.5))
mylogit <- glm(cbind(by,dby) ~ ., family=binomial(link="logit"), data = sim.data)
summary(mylogit)
confint(mylogit)

# Binary logistic regression with odds ratios (denominator=1); 3 predictors
sim.data <-logit_syn(nobs = 500, d = 1, xv = c(1, .75, -1.5, 1.15))
mylogit <- glm(cbind(by,dby) ~ ., family=binomial(link="logit"), data = sim.data)
exp(coef(mylogit))
exp(confint(mylogit))

# Binomial or grouped logistic regression with defined denominator, den
den <- rep(1:5, each=100, times=1)*100
sim.data <- logit_syn(nobs = 500, d = den, xv = c(1, .5, -1.5))
gby <- glm(cbind(by,dby) ~ ., family=binomial(link="logit"), data = sim.data)
summary(gby)

## Not run:

# default
sim.data <- logit_syn(nobs=500, d=1,  xv = c(2, -.55, 1.15))
dlogit <- glm(cbind(by,dby) ~ . , family=binomial(link="logit"), data = sim.data)
summary(dlogit)
## End(Not run)