compare_performance: Compare performance of different models

In performance: Assessment of Regression Models Performance

Compare performance of different models

Description

compare_performance() computes indices of model performance for different models at once and hence allows comparison of indices across models.

Usage

compare_performance(
  ...,
  metrics = "all",
  rank = FALSE,
  estimator = "ML",
  verbose = TRUE
)

Arguments

...	Multiple model objects (also of different classes).
metrics	Can be "all", "common" or a character vector of metrics to be computed. See related documentation() of object's class for details.
rank	Logical, if TRUE, models are ranked according to 'best' overall model performance. See 'Details'.
estimator	Only for linear models. Corresponds to the different estimators for the standard deviation of the errors. If estimator = "ML" (default, except for performance_aic() when the model object is of class lmerMod), the scaling is done by n (the biased ML estimator), which is then equivalent to using AIC(logLik()). Setting it to "REML" will give the same results as AIC(logLik(..., REML = TRUE)).
verbose	Toggle warnings.

Details

Model Weights

When information criteria (IC) are requested in metrics (i.e., any of "all", "common", "AIC", "AICc", "BIC", "WAIC", or "LOOIC"), model weights based on these criteria are also computed. For all IC except LOOIC, weights are computed as w = exp(-0.5 * delta_ic) / sum(exp(-0.5 * delta_ic)), where delta_ic is the difference between the model's IC value and the smallest IC value in the model set (Burnham and Anderson, 2002). For LOOIC, weights are computed as "stacking weights" using loo::stacking_weights().

Ranking Models

When rank = TRUE, a new column Performance_Score is returned. This score ranges from 0\ performance. Note that all score value do not necessarily sum up to 100\ Rather, calculation is based on normalizing all indices (i.e. rescaling them to a range from 0 to 1), and taking the mean value of all indices for each model. This is a rather quick heuristic, but might be helpful as exploratory index.

In particular when models are of different types (e.g. mixed models, classical linear models, logistic regression, ...), not all indices will be computed for each model. In case where an index can't be calculated for a specific model type, this model gets an NA value. All indices that have any NAs are excluded from calculating the performance score.

There is a plot()-method for compare_performance(), which creates a "spiderweb" plot, where the different indices are normalized and larger values indicate better model performance. Hence, points closer to the center indicate worse fit indices (see online-documentation for more details).

REML versus ML estimator

By default, estimator = "ML", which means that values from information criteria (AIC, AICc, BIC) for specific model classes (like models from lme4) are based on the ML-estimator, while the default behaviour of AIC() for such classes is setting REML = TRUE. This default is intentional, because comparing information criteria based on REML fits is usually not valid (it might be useful, though, if all models share the same fixed effects - however, this is usually not the case for nested models, which is a prerequisite for the LRT). Set estimator = "REML" explicitly return the same (AIC/...) values as from the defaults in AIC.merMod().

Value

A data frame with one row per model and one column per "index" (see metrics).

Note

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

References

Burnham, K. P., and Anderson, D. R. (2002). Model selection and multimodel inference: A practical information-theoretic approach (2nd ed.). Springer-Verlag. \Sexpr[results=rd]{tools:::Rd_expr_doi("10.1007/b97636")}

Examples

data(iris)
lm1 <- lm(Sepal.Length ~ Species, data = iris)
lm2 <- lm(Sepal.Length ~ Species + Petal.Length, data = iris)
lm3 <- lm(Sepal.Length ~ Species * Petal.Length, data = iris)
compare_performance(lm1, lm2, lm3)
compare_performance(lm1, lm2, lm3, rank = TRUE)

m1 <- lm(mpg ~ wt + cyl, data = mtcars)
m2 <- glm(vs ~ wt + mpg, data = mtcars, family = "binomial")
m3 <- lme4::lmer(Petal.Length ~ Sepal.Length + (1 | Species), data = iris)
compare_performance(m1, m2, m3)

performance documentation built on Oct. 19, 2024, 1:07 a.m.