Create reports for Bayesian models. The description of the parameters follows the Sequential Effect eXistence and sIgnificance Testing framework (see SEXIT documentation).
Usage
# S3 method for class 'brmsfit'
report(x, ...)Value
An object of class report().
See also
Specific components of reports (especially for stats models):
Other types of reports:
Methods:
Template file for supporting new models:
Examples
# \donttest{
# Bayesian models
library(brms)
model <- suppressWarnings(brm(mpg ~ qsec + wt, data = mtcars, refresh = 0, iter = 300))
#> Compiling Stan program...
#> Start sampling
r <- report(model, verbose = FALSE)
#> Start sampling
r
#> We fitted a Bayesian linear model (estimated using MCMC sampling with 4 chains
#> of 300 iterations and a warmup of 150) to predict mpg with qsec and wt
#> (formula: mpg ~ qsec + wt). Priors over parameters were set as student_t
#> (location = 19.20, scale = 5.40) distributions. The model's explanatory power
#> is substantial (R2 = 0.82, 95% CI [0.75, 0.85], adj. R2 = 0.79). Within this
#> model:
#>
#> - The effect of b Intercept (Median = 20.01, 95% CI [8.31, 31.44]) has a 99.67%
#> probability of being positive (> 0), 99.67% of being significant (> 0.30), and
#> 99.67% of being large (> 1.81). The estimation successfully converged (Rhat =
#> 1.003) but the indices are unreliable (ESS = 636)
#> - The effect of b qsec (Median = 0.91, 95% CI [0.32, 1.51]) has a 99.83%
#> probability of being positive (> 0), 97.50% of being significant (> 0.30), and
#> 0.50% of being large (> 1.81). The estimation successfully converged (Rhat =
#> 1.001) but the indices are unreliable (ESS = 731)
#> - The effect of b wt (Median = -5.09, 95% CI [-6.14, -3.96]) has a 100.00%
#> probability of being negative (< 0), 100.00% of being significant (< -0.30),
#> and 100.00% of being large (< -1.81). The estimation successfully converged
#> (Rhat = 1.000) but the indices are unreliable (ESS = 519)
#>
#> Following the Sequential Effect eXistence and sIgnificance Testing (SEXIT)
#> framework, we report the median of the posterior distribution and its 95% CI
#> (Highest Density Interval), along the probability of direction (pd), the
#> probability of significance and the probability of being large. The thresholds
#> beyond which the effect is considered as significant (i.e., non-negligible) and
#> large are |0.30| and |1.81| (corresponding respectively to 0.05 and 0.30 of the
#> outcome's SD). Convergence and stability of the Bayesian sampling has been
#> assessed using R-hat, which should be below 1.01 (Vehtari et al., 2019), and
#> Effective Sample Size (ESS), which should be greater than 1000 (Burkner,
#> 2017)., We fitted a Bayesian linear model (estimated using MCMC sampling with 4
#> chains of 300 iterations and a warmup of 150) to predict mpg with qsec and wt
#> (formula: mpg ~ qsec + wt). Priors over parameters were set as uniform
#> (location = , scale = ) distributions. The model's explanatory power is
#> substantial (R2 = 0.82, 95% CI [0.75, 0.85], adj. R2 = 0.79). Within this
#> model:
#>
#> - The effect of b Intercept (Median = 20.01, 95% CI [8.31, 31.44]) has a 99.67%
#> probability of being positive (> 0), 99.67% of being significant (> 0.30), and
#> 99.67% of being large (> 1.81). The estimation successfully converged (Rhat =
#> 1.003) but the indices are unreliable (ESS = 636)
#> - The effect of b qsec (Median = 0.91, 95% CI [0.32, 1.51]) has a 99.83%
#> probability of being positive (> 0), 97.50% of being significant (> 0.30), and
#> 0.50% of being large (> 1.81). The estimation successfully converged (Rhat =
#> 1.001) but the indices are unreliable (ESS = 731)
#> - The effect of b wt (Median = -5.09, 95% CI [-6.14, -3.96]) has a 100.00%
#> probability of being negative (< 0), 100.00% of being significant (< -0.30),
#> and 100.00% of being large (< -1.81). The estimation successfully converged
#> (Rhat = 1.000) but the indices are unreliable (ESS = 519)
#>
#> Following the Sequential Effect eXistence and sIgnificance Testing (SEXIT)
#> framework, we report the median of the posterior distribution and its 95% CI
#> (Highest Density Interval), along the probability of direction (pd), the
#> probability of significance and the probability of being large. The thresholds
#> beyond which the effect is considered as significant (i.e., non-negligible) and
#> large are |0.30| and |1.81| (corresponding respectively to 0.05 and 0.30 of the
#> outcome's SD). Convergence and stability of the Bayesian sampling has been
#> assessed using R-hat, which should be below 1.01 (Vehtari et al., 2019), and
#> Effective Sample Size (ESS), which should be greater than 1000 (Burkner,
#> 2017)., We fitted a Bayesian linear model (estimated using MCMC sampling with 4
#> chains of 300 iterations and a warmup of 150) to predict mpg with qsec and wt
#> (formula: mpg ~ qsec + wt). Priors over parameters were set as uniform
#> (location = , scale = ) distributions. The model's explanatory power is
#> substantial (R2 = 0.82, 95% CI [0.75, 0.85], adj. R2 = 0.79). Within this
#> model:
#>
#> - The effect of b Intercept (Median = 20.01, 95% CI [8.31, 31.44]) has a 99.67%
#> probability of being positive (> 0), 99.67% of being significant (> 0.30), and
#> 99.67% of being large (> 1.81). The estimation successfully converged (Rhat =
#> 1.003) but the indices are unreliable (ESS = 636)
#> - The effect of b qsec (Median = 0.91, 95% CI [0.32, 1.51]) has a 99.83%
#> probability of being positive (> 0), 97.50% of being significant (> 0.30), and
#> 0.50% of being large (> 1.81). The estimation successfully converged (Rhat =
#> 1.001) but the indices are unreliable (ESS = 731)
#> - The effect of b wt (Median = -5.09, 95% CI [-6.14, -3.96]) has a 100.00%
#> probability of being negative (< 0), 100.00% of being significant (< -0.30),
#> and 100.00% of being large (< -1.81). The estimation successfully converged
#> (Rhat = 1.000) but the indices are unreliable (ESS = 519)
#>
#> Following the Sequential Effect eXistence and sIgnificance Testing (SEXIT)
#> framework, we report the median of the posterior distribution and its 95% CI
#> (Highest Density Interval), along the probability of direction (pd), the
#> probability of significance and the probability of being large. The thresholds
#> beyond which the effect is considered as significant (i.e., non-negligible) and
#> large are |0.30| and |1.81| (corresponding respectively to 0.05 and 0.30 of the
#> outcome's SD). Convergence and stability of the Bayesian sampling has been
#> assessed using R-hat, which should be below 1.01 (Vehtari et al., 2019), and
#> Effective Sample Size (ESS), which should be greater than 1000 (Burkner, 2017).
#> and We fitted a Bayesian linear model (estimated using MCMC sampling with 4
#> chains of 300 iterations and a warmup of 150) to predict mpg with qsec and wt
#> (formula: mpg ~ qsec + wt). Priors over parameters were set as student_t
#> (location = 0.00, scale = 5.40) distributions. The model's explanatory power is
#> substantial (R2 = 0.82, 95% CI [0.75, 0.85], adj. R2 = 0.79). Within this
#> model:
#>
#> - The effect of b Intercept (Median = 20.01, 95% CI [8.31, 31.44]) has a 99.67%
#> probability of being positive (> 0), 99.67% of being significant (> 0.30), and
#> 99.67% of being large (> 1.81). The estimation successfully converged (Rhat =
#> 1.003) but the indices are unreliable (ESS = 636)
#> - The effect of b qsec (Median = 0.91, 95% CI [0.32, 1.51]) has a 99.83%
#> probability of being positive (> 0), 97.50% of being significant (> 0.30), and
#> 0.50% of being large (> 1.81). The estimation successfully converged (Rhat =
#> 1.001) but the indices are unreliable (ESS = 731)
#> - The effect of b wt (Median = -5.09, 95% CI [-6.14, -3.96]) has a 100.00%
#> probability of being negative (< 0), 100.00% of being significant (< -0.30),
#> and 100.00% of being large (< -1.81). The estimation successfully converged
#> (Rhat = 1.000) but the indices are unreliable (ESS = 519)
#>
#> Following the Sequential Effect eXistence and sIgnificance Testing (SEXIT)
#> framework, we report the median of the posterior distribution and its 95% CI
#> (Highest Density Interval), along the probability of direction (pd), the
#> probability of significance and the probability of being large. The thresholds
#> beyond which the effect is considered as significant (i.e., non-negligible) and
#> large are |0.30| and |1.81| (corresponding respectively to 0.05 and 0.30 of the
#> outcome's SD). Convergence and stability of the Bayesian sampling has been
#> assessed using R-hat, which should be below 1.01 (Vehtari et al., 2019), and
#> Effective Sample Size (ESS), which should be greater than 1000 (Burkner, 2017).
summary(r)
#> We fitted a Bayesian linear model to predict mpg with qsec and wt. Priors over
#> parameters were set as student_t (location = 19.20, scale = 5.40)
#> distributions. The model's explanatory power is substantial (R2 = 0.82, adj. R2
#> = 0.79). Within this model:
#>
#> - The effect of b Intercept (Median = 20.01, 95% CI [8.31, 31.44]) has 99.67%,
#> 99.67% and 99.67% probability of being positive (> 0), significant (> 0.30) and
#> large (> 1.81). The estimation successfully converged (Rhat = 1.003) but the
#> indices are unreliable (ESS = 636)
#> - The effect of b qsec (Median = 0.91, 95% CI [0.32, 1.51]) has 99.83%, 97.50%
#> and 0.50% probability of being positive (> 0), significant (> 0.30) and large
#> (> 1.81). The estimation successfully converged (Rhat = 1.001) but the indices
#> are unreliable (ESS = 731)
#> - The effect of b wt (Median = -5.09, 95% CI [-6.14, -3.96]) has 100.00%,
#> 100.00% and 100.00% probability of being negative (< 0), significant (< -0.30)
#> and large (< -1.81). The estimation successfully converged (Rhat = 1.000) but
#> the indices are unreliable (ESS = 519), We fitted a Bayesian linear model to
#> predict mpg with qsec and wt. Priors over parameters were set as uniform
#> (location = , scale = ) distributions. The model's explanatory power is
#> substantial (R2 = 0.82, adj. R2 = 0.79). Within this model:
#>
#> - The effect of b Intercept (Median = 20.01, 95% CI [8.31, 31.44]) has 99.67%,
#> 99.67% and 99.67% probability of being positive (> 0), significant (> 0.30) and
#> large (> 1.81). The estimation successfully converged (Rhat = 1.003) but the
#> indices are unreliable (ESS = 636)
#> - The effect of b qsec (Median = 0.91, 95% CI [0.32, 1.51]) has 99.83%, 97.50%
#> and 0.50% probability of being positive (> 0), significant (> 0.30) and large
#> (> 1.81). The estimation successfully converged (Rhat = 1.001) but the indices
#> are unreliable (ESS = 731)
#> - The effect of b wt (Median = -5.09, 95% CI [-6.14, -3.96]) has 100.00%,
#> 100.00% and 100.00% probability of being negative (< 0), significant (< -0.30)
#> and large (< -1.81). The estimation successfully converged (Rhat = 1.000) but
#> the indices are unreliable (ESS = 519), We fitted a Bayesian linear model to
#> predict mpg with qsec and wt. Priors over parameters were set as uniform
#> (location = , scale = ) distributions. The model's explanatory power is
#> substantial (R2 = 0.82, adj. R2 = 0.79). Within this model:
#>
#> - The effect of b Intercept (Median = 20.01, 95% CI [8.31, 31.44]) has 99.67%,
#> 99.67% and 99.67% probability of being positive (> 0), significant (> 0.30) and
#> large (> 1.81). The estimation successfully converged (Rhat = 1.003) but the
#> indices are unreliable (ESS = 636)
#> - The effect of b qsec (Median = 0.91, 95% CI [0.32, 1.51]) has 99.83%, 97.50%
#> and 0.50% probability of being positive (> 0), significant (> 0.30) and large
#> (> 1.81). The estimation successfully converged (Rhat = 1.001) but the indices
#> are unreliable (ESS = 731)
#> - The effect of b wt (Median = -5.09, 95% CI [-6.14, -3.96]) has 100.00%,
#> 100.00% and 100.00% probability of being negative (< 0), significant (< -0.30)
#> and large (< -1.81). The estimation successfully converged (Rhat = 1.000) but
#> the indices are unreliable (ESS = 519) and We fitted a Bayesian linear model to
#> predict mpg with qsec and wt. Priors over parameters were set as student_t
#> (location = 0.00, scale = 5.40) distributions. The model's explanatory power is
#> substantial (R2 = 0.82, adj. R2 = 0.79). Within this model:
#>
#> - The effect of b Intercept (Median = 20.01, 95% CI [8.31, 31.44]) has 99.67%,
#> 99.67% and 99.67% probability of being positive (> 0), significant (> 0.30) and
#> large (> 1.81). The estimation successfully converged (Rhat = 1.003) but the
#> indices are unreliable (ESS = 636)
#> - The effect of b qsec (Median = 0.91, 95% CI [0.32, 1.51]) has 99.83%, 97.50%
#> and 0.50% probability of being positive (> 0), significant (> 0.30) and large
#> (> 1.81). The estimation successfully converged (Rhat = 1.001) but the indices
#> are unreliable (ESS = 731)
#> - The effect of b wt (Median = -5.09, 95% CI [-6.14, -3.96]) has 100.00%,
#> 100.00% and 100.00% probability of being negative (< 0), significant (< -0.30)
#> and large (< -1.81). The estimation successfully converged (Rhat = 1.000) but
#> the indices are unreliable (ESS = 519)
as.data.frame(r)
#> Parameter | Component | Median | 95% CI | pd | Rhat | ESS | Fit
#> --------------------------------------------------------------------------------------
#> (Intercept) | conditional | 20.01 | [ 8.31, 31.44] | 99.67% | 1.003 | 636.00 |
#> qsec | conditional | 0.91 | [ 0.32, 1.51] | 99.83% | 1.001 | 731.00 |
#> wt | conditional | -5.09 | [-6.14, -3.96] | 100% | 1.000 | 519.00 |
#> sigma | sigma | 2.71 | [ 2.14, 3.47] | 100% | 0.999 | 468.00 |
#> | | | | | | |
#> ELPD | | | | | | | -79.32
#> LOOIC | | | | | | | 158.64
#> WAIC | | | | | | | 158.33
#> R2 | | | | | | | 0.82
#> R2 (adj.) | | | | | | | 0.78
#> Sigma | | | | | | | 2.74
summary(as.data.frame(r))
#> Parameter | Component | Median | 95% CI | pd | Rhat | ESS | Fit
#> ------------------------------------------------------------------------------------
#> (Intercept) | conditional | 20.01 | [ 8.31, 31.44] | 99.67% | 1.003 | 636.00 |
#> qsec | conditional | 0.91 | [ 0.32, 1.51] | 99.83% | 1.001 | 731.00 |
#> wt | conditional | -5.09 | [-6.14, -3.96] | 100% | 1.000 | 519.00 |
#> sigma | sigma | 2.71 | [ 2.14, 3.47] | 100% | 0.999 | 468.00 |
#> | | | | | | |
#> R2 | | | | | | | 0.82
#> R2 (adj.) | | | | | | | 0.78
#> Sigma | | | | | | | 2.74
# }