latent {boolean} | R Documentation |
Boolean models involve more than one 'path', e.g. if y~a&(b|c), then a, b, and c are paths that are parameterized with explanatory variables. This function extracts estimates of a, b, and c, which are probabilities but not the probability that the dependent variable occurs.
latent(object, probability = FALSE, invMills = FALSE)
object |
An object of class 'booltest' |
probability |
If TRUE, the linear predictor is transformed by the
link function specified in the call to boolean to produce
a vector of probabilities. |
invMills |
If TRUE, the inverse Mills ratio is calculated for paths
where a probit link is specified in the call to boolean |
. Note that if both probabilities and invMills are FALSE (the default), then the linear predictor for each path is returned.
A numeric matrix with columns equal to the number of paths and rows equal to the
number of observations. Whether the matrix contains the linear predictions,
probabilities, or inverse Mills ratios depends on the call to latent
.
Bear F. Braumoeller, Harvard University, braumoeller.1@polisci.osu.edu,
Ben Goodrich, Harvard University, goodrich@fas.harvard.edu, and
Jacob Kline, Harvard University, jkline@fas.harvard.edu
Braumoeller, Bear F. (2003) "Causal Complexity and the Study of Politics." Political Analysis 11(3): 209-233. Nagler, Jonathon. (1994) "Scobit: An Alternative Estimator to Logit and Probit." American Journal of Political Science 38(1): 230-255.