For each of the top models (shown in columns), the following information is printed: the model representation using variable inclusion indicators, its marginal likelihood (in log scale), the R2, the model dimension, the Bayes factor, posterior odds (comparison made with the highest posterior probability model) and posterior probability. An additional column with the posterior inclusion probabilities of the explanatory variables is also printed.
# S3 method for pep
print(
x,
n.models = 5,
actual.PO = FALSE,
digits = max(3L, getOption("digits") - 3L),
...
)No return value, used for printing the results on the R console.
An object of class pep (e.g., output of pep.lm).
Positive integer, the number of top models for which information is provided. Default value=5.
Logical, relevant for the MC3 algorithm. If TRUE
then apart from the estimated posterior odds, the actual posterior
odds of the MAP model versus the top models (i.e., ratios based on the marginal likelihood
times prior probability) are also printed --- which could be used as a
convergence indicator of the algorithm. Default value=FALSE.
Positive integer, the number of digits for printing numbers.
Default value=max(3L, getOption("digits") - 3L).
Additional parameters to be passed to
print.default.
The number of models for which information is provided, is computed as the minimum
between the number asked by the user and the number of models present in
the object x.
data(UScrime_data)
res <- pep.lm(y~.,data=UScrime_data)
print(res)
Run the code above in your browser using DataLab