The $summary() method runs
summarise_draws() from the posterior
package and returns the output. For MCMC, only post-warmup draws are
included in the summary.
There is also a $print() method that prints the same summary stats but
removes the extra formatting used for printing tibbles and returns the
fitted model object itself. The $print() method may also be faster than
$summary() because it is designed to only compute the summary statistics
for the variables that will actually fit in the printed output whereas
$summary() will compute them for all of the specified variables in order
to be able to return them to the user. See Examples.
summary(variables = NULL, ...)(character vector) The variables to include.
Optional arguments to pass to posterior::summarise_draws().
The $summary() method returns the tibble data frame created by
posterior::summarise_draws().
The $print() method returns the fitted model object itself (invisibly),
which is the standard behavior for print methods in R.
# \dontrun{
fit <- cmdstanr_example("logistic")
fit$summary()
#> # A tibble: 105 × 10
#> variable mean median sd mad q5 q95 rhat ess_bulk
#> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 lp__ -66.0 -65.7 1.48 1.23 -68.9 -64.3 1.00 1956.
#> 2 alpha 0.382 0.381 0.221 0.222 0.0263 0.744 1.00 3982.
#> 3 beta[1] -0.665 -0.661 0.252 0.253 -1.09 -0.264 1.00 4131.
#> 4 beta[2] -0.274 -0.280 0.226 0.226 -0.640 0.0976 1.00 3816.
#> 5 beta[3] 0.675 0.673 0.268 0.265 0.238 1.12 1.00 3963.
#> 6 log_lik[1] -0.514 -0.508 0.0987 0.0980 -0.686 -0.364 1.00 3980.
#> 7 log_lik[2] -0.408 -0.385 0.153 0.142 -0.690 -0.197 1.00 4263.
#> 8 log_lik[3] -0.498 -0.467 0.217 0.204 -0.889 -0.206 1.00 3904.
#> 9 log_lik[4] -0.453 -0.436 0.152 0.148 -0.732 -0.236 1.00 3847.
#> 10 log_lik[5] -1.18 -1.16 0.285 0.281 -1.68 -0.749 1.00 4407.
#> # ℹ 95 more rows
#> # ℹ 1 more variable: ess_tail <dbl>
fit$print()
#> variable mean median sd mad q5 q95 rhat ess_bulk ess_tail
#> lp__ -66.00 -65.68 1.48 1.23 -68.89 -64.30 1.00 1956 2665
#> alpha 0.38 0.38 0.22 0.22 0.03 0.74 1.00 3981 3124
#> beta[1] -0.66 -0.66 0.25 0.25 -1.09 -0.26 1.00 4131 3206
#> beta[2] -0.27 -0.28 0.23 0.23 -0.64 0.10 1.00 3815 2736
#> beta[3] 0.67 0.67 0.27 0.26 0.24 1.12 1.00 3963 3257
#> log_lik[1] -0.51 -0.51 0.10 0.10 -0.69 -0.36 1.00 3979 2841
#> log_lik[2] -0.41 -0.39 0.15 0.14 -0.69 -0.20 1.00 4263 3051
#> log_lik[3] -0.50 -0.47 0.22 0.20 -0.89 -0.21 1.00 3904 3141
#> log_lik[4] -0.45 -0.44 0.15 0.15 -0.73 -0.24 1.00 3847 2904
#> log_lik[5] -1.18 -1.16 0.28 0.28 -1.68 -0.75 1.00 4406 3095
#>
#> # showing 10 of 105 rows (change via 'max_rows' argument or 'cmdstanr_max_rows' option)
fit$print(max_rows = 2) # same as print(fit, max_rows = 2)
#> variable mean median sd mad q5 q95 rhat ess_bulk ess_tail
#> lp__ -66.00 -65.68 1.48 1.23 -68.89 -64.30 1.00 1956 2665
#> alpha 0.38 0.38 0.22 0.22 0.03 0.74 1.00 3981 3124
#>
#> # showing 2 of 105 rows (change via 'max_rows' argument or 'cmdstanr_max_rows' option)
# include only certain variables
fit$summary("beta")
#> # A tibble: 3 × 10
#> variable mean median sd mad q5 q95 rhat ess_bulk ess_tail
#> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 beta[1] -0.665 -0.661 0.252 0.253 -1.09 -0.264 1.00 4131. 3207.
#> 2 beta[2] -0.274 -0.280 0.226 0.226 -0.640 0.0976 1.00 3816. 2736.
#> 3 beta[3] 0.675 0.673 0.268 0.265 0.238 1.12 1.00 3963. 3257.
fit$print(c("alpha", "beta[2]"))
#> variable mean median sd mad q5 q95 rhat ess_bulk ess_tail
#> alpha 0.38 0.38 0.22 0.22 0.03 0.74 1.00 3981 3124
#> beta[2] -0.27 -0.28 0.23 0.23 -0.64 0.10 1.00 3815 2736
# include all variables but only certain summaries
fit$summary(NULL, c("mean", "sd"))
#> # A tibble: 105 × 3
#> variable mean sd
#> <chr> <dbl> <dbl>
#> 1 lp__ -66.0 1.48
#> 2 alpha 0.382 0.221
#> 3 beta[1] -0.665 0.252
#> 4 beta[2] -0.274 0.226
#> 5 beta[3] 0.675 0.268
#> 6 log_lik[1] -0.514 0.0987
#> 7 log_lik[2] -0.408 0.153
#> 8 log_lik[3] -0.498 0.217
#> 9 log_lik[4] -0.453 0.152
#> 10 log_lik[5] -1.18 0.285
#> # ℹ 95 more rows
# can use functions created from formulas
# for example, calculate Pr(beta > 0)
fit$summary("beta", prob_gt_0 = ~ mean(. > 0))
#> # A tibble: 3 × 2
#> variable prob_gt_0
#> <chr> <dbl>
#> 1 beta[1] 0.00325
#> 2 beta[2] 0.114
#> 3 beta[3] 0.997
# can combine user-specified functions with
# the default summary functions
fit$summary(variables = c("alpha", "beta"),
posterior::default_summary_measures()[1:4],
quantiles = ~ quantile2(., probs = c(0.025, 0.975)),
posterior::default_convergence_measures()
)
#> # A tibble: 4 × 10
#> variable mean median sd mad q2.5 q97.5 rhat ess_bulk ess_tail
#> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 alpha 0.382 0.381 0.221 0.222 -0.0413 0.821 1.00 3982. 3124.
#> 2 beta[1] -0.665 -0.661 0.252 0.253 -1.18 -0.185 1.00 4131. 3207.
#> 3 beta[2] -0.274 -0.280 0.226 0.226 -0.715 0.168 1.00 3816. 2736.
#> 4 beta[3] 0.675 0.673 0.268 0.265 0.170 1.20 1.00 3963. 3257.
# the functions need to calculate the appropriate
# value for a matrix input
fit$summary(variables = "alpha", dim)
#> # A tibble: 1 × 3
#> variable dim.1 dim.2
#> <chr> <int> <int>
#> 1 alpha 1000 4
# the usual [stats::var()] is therefore not directly suitable as it
# will produce a covariance matrix unless the data is converted to a vector
fit$print(c("alpha", "beta"), var2 = ~var(as.vector(.x)))
#> variable var2
#> alpha 0.05
#> beta[1] 0.06
#> beta[2] 0.05
#> beta[3] 0.07
# }