Practical Significance (ps) — p_significance • bayestestR

Compute the probability of Practical Significance (ps), which can be conceptualized as a unidirectional equivalence test. It returns the probability that effect is above a given threshold corresponding to a negligible effect in the median's direction. Mathematically, it is defined as the proportion of the posterior distribution of the median sign above the threshold.

Usage

p_significance(x, ...)

# S3 method for class 'numeric'
p_significance(x, threshold = "default", ...)

# S3 method for class 'get_predicted'
p_significance(
  x,
  threshold = "default",
  use_iterations = FALSE,
  verbose = TRUE,
  ...
)

# S3 method for class 'data.frame'
p_significance(x, threshold = "default", rvar_col = NULL, ...)

# S3 method for class 'stanreg'
p_significance(
  x,
  threshold = "default",
  effects = c("fixed", "random", "all"),
  component = c("location", "all", "conditional", "smooth_terms", "sigma",
    "distributional", "auxiliary"),
  parameters = NULL,
  verbose = TRUE,
  ...
)

# S3 method for class 'brmsfit'
p_significance(
  x,
  threshold = "default",
  effects = c("fixed", "random", "all"),
  component = c("conditional", "zi", "zero_inflated", "all"),
  parameters = NULL,
  verbose = TRUE,
  ...
)

Arguments

x

Vector representing a posterior distribution. Can also be a stanreg or brmsfit model.

...

Currently not used.

threshold

The threshold value that separates significant from negligible effect, which can have following possible values:

"default", in which case the range is set to 0.1 if input is a vector, and based on rope_range() if a (Bayesian) model is provided.
a single numeric value (e.g., 0.1), which is used as range around zero (i.e. the threshold range is set to -0.1 and 0.1, i.e. reflects a symmetric interval)
a numeric vector of length two (e.g., c(-0.2, 0.1)), useful for asymmetric intervals
a list of numeric vectors, where each vector corresponds to a parameter
a list of named numeric vectors, where names correspond to parameter names. In this case, all parameters that have no matching name in threshold will be set to "default".

use_iterations

Logical, if TRUE and x is a get_predicted object, (returned by insight::get_predicted()), the function is applied to the iterations instead of the predictions. This only applies to models that return iterations for predicted values (e.g., brmsfit models).

verbose

Toggle off warnings.

rvar_col

A single character - the name of an rvar column in the data frame to be processed. See example in p_direction().

effects

Should results for fixed effects, random effects or both be returned? Only applies to mixed models. May be abbreviated.

component

Should results for all parameters, parameters for the conditional model or the zero-inflated part of the model be returned? May be abbreviated. Only applies to brms-models.

parameters

Regular expression pattern that describes the parameters that should be returned. Meta-parameters (like lp__ or prior_) are filtered by default, so only parameters that typically appear in the summary() are returned. Use parameters to select specific parameters for the output.

Value

Values between 0 and 1 corresponding to the probability of practical significance (ps).

Details

p_significance() returns the proportion of a probability distribution (x) that is outside a certain range (the negligible effect, or ROPE, see argument threshold). If there are values of the distribution both below and above the ROPE, p_significance() returns the higher probability of a value being outside the ROPE. Typically, this value should be larger than 0.5 to indicate practical significance. However, if the range of the negligible effect is rather large compared to the range of the probability distribution x, p_significance() will be less than 0.5, which indicates no clear practical significance.

Note

There is also a plot()-method implemented in the see-package.

Examples

library(bayestestR)

# Simulate a posterior distribution of mean 1 and SD 1
# ----------------------------------------------------
posterior <- rnorm(1000, mean = 1, sd = 1)
p_significance(posterior)
#> Practical Significance (threshold: 0.10)
#> 
#> Parameter |   ps
#> ----------------
#> Posterior | 0.80

# Simulate a dataframe of posterior distributions
# -----------------------------------------------
df <- data.frame(replicate(4, rnorm(100)))
p_significance(df)
#> Practical Significance (threshold: 0.10)
#> 
#> Parameter |   ps
#> ----------------
#> X1        | 0.51
#> X2        | 0.55
#> X3        | 0.47
#> X4        | 0.47
# \donttest{
# rstanarm models
# -----------------------------------------------
model <- rstanarm::stan_glm(mpg ~ wt + cyl,
  data = mtcars,
  chains = 2, refresh = 0
)
p_significance(model)
#> Practical Significance (threshold: 0.60) 
#> 
#> Parameter   |   ps
#> ------------------
#> (Intercept) | 1.00
#> wt          | 1.00
#> cyl         | 0.98
# multiple thresholds - asymmetric, symmetric, default
p_significance(model, threshold = list(c(-10, 5), 0.2, "default"))
#> Practical Significance 
#> 
#> Parameter   |   ps |           ROPE
#> -----------------------------------
#> (Intercept) | 1.00 | [-10.00, 5.00]
#> wt          | 1.00 | [ -0.20, 0.20]
#> cyl         | 0.98 | [ -0.60, 0.60]
# named thresholds
p_significance(model, threshold = list(wt = 0.2, `(Intercept)` = c(-10, 5)))
#> Practical Significance 
#> 
#> Parameter   |   ps |           ROPE
#> -----------------------------------
#> (Intercept) | 1.00 | [-10.00, 5.00]
#> wt          | 1.00 | [ -0.20, 0.20]
#> cyl         | 0.98 | [ -0.60, 0.60]
# }