Summarizes a fitted LAME (Longitudinal Additive and Multiplicative Effects) model, including parameter estimates, standard errors, credible intervals, and model diagnostics.
# S3 method for lame
summary(object, ...)A list of class "summary.lame" containing:
The original function call
Matrix of regression coefficient estimates and statistics
Matrix of variance component estimates
Number of time periods in the longitudinal data
an object of class "lame", typically the result of fitting a
longitudinal AME model using the lame function
additional parameters (currently not used)
Cassy Dorff, Shahryar Minhas, Tosin Salau
The summary includes:
Posterior means, posterior standard deviations, z-values, approximate p-values, and 95% credible intervals for dyadic, sender, and receiver covariates. Note: the z-values are computed as posterior mean / posterior SD, and the p-values are derived from a normal approximation. These are convenient screening statistics but are not formal frequentist test statistics. For rigorous inference, use the credible intervals or examine the full posterior via the BETA matrix directly.
Estimates and standard errors for:
Variance of additive sender/row effects
Covariance between sender and receiver effects
Variance of additive receiver/column effects
Dyadic correlation (reciprocity)
Residual variance
Only printed when the fit was
produced with dynamic_beta on at least one coefficient. The
table has one row per coefficient with columns:
average of the per-period posterior means across t
smallest and largest per-period posterior mean
Max - Min: the absolute range of the
per-period posterior means, in coefficient units
100 * Drift / |Mean|, the drift as a
percentage of the average level. Reported as NA when
the time-average is near zero (within 5\
range), because a trajectory that crosses zero makes the
percentage explode; read Drift in that case
"Y" if the coefficient was flagged as
dynamic, "N" if it was held static
The block also prints the per-block AR(1) hyperparameters
(rho_beta = ...). For per-period credible intervals use
confint.lame.
lame, print.summary.lame