Learn R Programming
⚠️There's a newer version (0.22.0) of this package.Take me there.

parameters

Describe and understand your model’s parameters!

parameters’ primary goal is to provide utilities for processing the parameters of various statistical models. Beyond computing p-values, CIs, Bayesian indices and other measures for a wide variety of models, this package implements features like bootstrapping of parameters and models, feature reduction (feature extraction and variable selection).

Installation

Run the following:

install.packages("parameters")
library("parameters")

Documentation

Click on the buttons above to access the package documentation and the easystats blog, and check-out these vignettes:

Features

Model’s parameters description

The model_parameters() function (that can be accessed via the parameters() shortcut) allows you to extract the parameters and their characteristics from various models in a consistent way. It can be considered as a lightweight alternative to broom::tidy(), with some notable differences:

  • The column names of the returned data frame are specific to their content. For instance, the column containing the statistic is named following the statistic name, i.e., t, z, etc., instead of a generic name such as statistic (however, you can get standardized (generic) column names using standardize_names()).
  • It is able to compute or extract indices not available by default, such as p-values, CIs, etc.
  • It includes feature engineering capabilities, including parameters bootstrapping.

Classical Regression Models

model <- lm(Sepal.Width ~ Petal.Length * Species + Petal.Width, data = iris)

# regular model parameters
model_parameters(model)
# Parameter                           | Coefficient |   SE |         95% CI |     t |  df |      p
# ------------------------------------------------------------------------------------------------
# (Intercept)                         |        2.89 | 0.36 | [ 2.18,  3.60] |  8.01 | 143 | < .001
# Petal.Length                        |        0.26 | 0.25 | [-0.22,  0.75] |  1.07 | 143 | 0.287 
# Species [versicolor]                |       -1.66 | 0.53 | [-2.71, -0.62] | -3.14 | 143 | 0.002 
# Species [virginica]                 |       -1.92 | 0.59 | [-3.08, -0.76] | -3.28 | 143 | 0.001 
# Petal.Width                         |        0.62 | 0.14 | [ 0.34,  0.89] |  4.41 | 143 | < .001
# Petal.Length * Species [versicolor] |       -0.09 | 0.26 | [-0.61,  0.42] | -0.36 | 143 | 0.721 
# Petal.Length * Species [virginica]  |       -0.13 | 0.26 | [-0.64,  0.38] | -0.50 | 143 | 0.618

# standardized parameters
model_parameters(model, standardize = "refit")
# Parameter                           | Coefficient |   SE |         95% CI |     t |  df |      p
# ------------------------------------------------------------------------------------------------
# (Intercept)                         |        3.59 | 1.30 | [ 1.01,  6.17] |  2.75 | 143 | 0.007 
# Petal.Length                        |        1.07 | 1.00 | [-0.91,  3.04] |  1.07 | 143 | 0.287 
# Species [versicolor]                |       -4.62 | 1.31 | [-7.21, -2.03] | -3.53 | 143 | < .001
# Species [virginica]                 |       -5.51 | 1.38 | [-8.23, -2.79] | -4.00 | 143 | < .001
# Petal.Width                         |        1.08 | 0.24 | [ 0.59,  1.56] |  4.41 | 143 | < .001
# Petal.Length * Species [versicolor] |       -0.38 | 1.06 | [-2.48,  1.72] | -0.36 | 143 | 0.721 
# Petal.Length * Species [virginica]  |       -0.52 | 1.04 | [-2.58,  1.54] | -0.50 | 143 | 0.618

Mixed Models

library(lme4)

model <- lmer(Sepal.Width ~ Petal.Length + (1|Species), data = iris)

# model parameters with CI, df and p-values based on Wald approximation
model_parameters(model)
# Parameter    | Coefficient |   SE |       95% CI |    t |  df |      p
# ----------------------------------------------------------------------
# (Intercept)  |        2.00 | 0.56 | [0.90, 3.10] | 3.56 | 146 | < .001
# Petal.Length |        0.28 | 0.06 | [0.17, 0.40] | 4.75 | 146 | < .001

# model parameters with CI, df and p-values based on Kenward-Roger approximation
model_parameters(model, df_method = "kenward")
# Parameter    | Coefficient |   SE |       95% CI |    t |     df |      p
# -------------------------------------------------------------------------
# (Intercept)  |        2.00 | 0.57 | [0.89, 3.11] | 3.53 |   2.67 | 0.046 
# Petal.Length |        0.28 | 0.06 | [0.16, 0.40] | 4.58 | 140.99 | < .001

Structural Models

Besides many types of regression models and packages, it also works for other types of models, such as structural models (EFA, CFA, SEM…).

library(psych)

model <- psych::fa(attitude, nfactors = 3)
model_parameters(model)
# # Rotated loadings from Principal Component Analysis (oblimin-rotation)
# 
# Variable   |   MR1 |   MR2 |   MR3 | Complexity | Uniqueness
# ------------------------------------------------------------
# rating     |  0.90 | -0.07 | -0.05 |       1.02 |       0.23
# complaints |  0.97 | -0.06 |  0.04 |       1.01 |       0.10
# privileges |  0.44 |  0.25 | -0.05 |       1.64 |       0.65
# learning   |  0.47 |  0.54 | -0.28 |       2.51 |       0.24
# raises     |  0.55 |  0.43 |  0.25 |       2.35 |       0.23
# critical   |  0.16 |  0.17 |  0.48 |       1.46 |       0.67
# advance    | -0.11 |  0.91 |  0.07 |       1.04 |       0.22
# 
# The 3 latent factors (oblimin rotation) accounted for 66.60% of the total variance of the original data (MR1 = 38.19%, MR2 = 22.69%, MR3 = 5.72%).

Variable and parameters selection

parameters_selection() can help you quickly select and retain the most relevant predictors using methods tailored for the model type.

library(dplyr)

lm(disp ~ ., data = mtcars) %>% 
  select_parameters() %>% 
  model_parameters()
# Parameter   | Coefficient |     SE |            95% CI |     t | df |      p
# ----------------------------------------------------------------------------
# (Intercept) |      141.70 | 125.67 | [-116.62, 400.02] |  1.13 | 26 | 0.270 
# cyl         |       13.14 |   7.90 | [  -3.10,  29.38] |  1.66 | 26 | 0.108 
# hp          |        0.63 |   0.20 | [   0.22,   1.03] |  3.18 | 26 | 0.004 
# wt          |       80.45 |  12.22 | [  55.33, 105.57] |  6.58 | 26 | < .001
# qsec        |      -14.68 |   6.14 | [ -27.31,  -2.05] | -2.39 | 26 | 0.024 
# carb        |      -28.75 |   5.60 | [ -40.28, -17.23] | -5.13 | 26 | < .001

Miscellaneous

This packages also contains a lot of other useful functions:

Describe a Distribution

data(iris)
describe_distribution(iris)
# Variable     | Mean |   SD |  Min |  Max | Skewness | Kurtosis |   n | n_Missing
# --------------------------------------------------------------------------------
# Sepal.Length | 5.84 | 0.83 | 4.30 | 7.90 |     0.31 |    -0.55 | 150 |         0
# Sepal.Width  | 3.06 | 0.44 | 2.00 | 4.40 |     0.32 |     0.23 | 150 |         0
# Petal.Length | 3.76 | 1.77 | 1.00 | 6.90 |    -0.27 |    -1.40 | 150 |         0
# Petal.Width  | 1.20 | 0.76 | 0.10 | 2.50 |    -0.10 |    -1.34 | 150 |         0

Citation

In order to cite this package, please use the following citation:

Corresponding BibTeX entry:

@Article{,
  title = {Describe and understand your model's parameters},
  author = {Dominique Makowski and Mattan S. Ben-Shachar and Daniel
  Lüdecke},
  journal = {CRAN},
  year = {2019},
  note = {R package},
  url = {https://github.com/easystats/parameters},
}

Copy Link

Version

Install

install.packages('parameters')

Monthly Downloads

87,418

Version

0.5.0

License

GPL-3

Maintainer

Daniel Lüdecke

Last Published

February 9th, 2020

Functions in parameters (0.5.0)

check_sphericity

Bartlett's Test of Sphericity
degrees_of_freedom

Degrees of Freedom (DoF)
bootstrap_parameters

Parameters bootstrapping
bootstrap_model

Model bootstrapping
.n_factors_bentler

Bentler and Yuan's Procedure
check_factorstructure

Check suitability of data for Factor Analysis (FA)
check_clusterstructure

Check suitability of data for clustering
convert_efa_to_cfa

Conversion between EFA results and CFA structure
check_multimodal

Check if a distribution is unimodal or multimodal
check_kmo

Kaiser, Meyer, Olkin (KMO) Measure of Sampling Adequacy (MSA) for Factor Analysis
data_partition

Partition data into a test and a training set
.flatten_list

Flatten a list
equivalence_test.lm

Equivalence test
.n_factors_cng

Cattell-Nelson-Gorsuch CNG Indices
factor_analysis

Factor Analysis (FA)
cluster_analysis

Compute cluster analysis and return group indices
format_parameters

Parameter names formatting
format_p

p-values formatting
model_parameters.default

Parameters from (General) Linear Models
format_model

Model Name formatting
.n_factors_bartlett

Bartlett, Anderson and Lawley Procedures
format_bf

Bayes Factor formatting
ci_kenward

Kenward-Roger approximation for SEs, CIs and p-values
model_parameters.gam

Parameters from Generalized Additive (Mixed) Models
ci_ml1

"m-l-1" approximation for SEs, CIs and p-values
cmds

Classical Multidimensional Scaling (cMDS)
model_parameters.Mclust

Parameters from Mixture Models
.compact_character

remove empty string from character
model_parameters

Model Parameters
cluster_discrimination

Compute a linear discriminant analysis on classified cluster groups
model_parameters.aov

Parameters from ANOVAs
.n_factors_sescree

Standard Error Scree and Coefficient of Determination Procedures
convert_data_to_numeric

Convert data to numeric
format_pd

Probability of direction (pd) formatting
.filter_component

for models with zero-inflation component, return required component of model-summary
.compact_list

remove NULL elements from lists
.find_most_common

Find most common occurence
parameters_type

Type of model parameters
model_parameters.befa

Parameters from PCA/FA
parameters_table

Parameter table formatting
.n_factors_mreg

Multiple Regression Procedure
n_factors

Number of components/factors to retain in PCA/FA
.data_frame

help-functions
smoothness

Quantify the smoothness of a vector
skewness

Compute Skewness and Kurtosis
.n_factors_scree

Non Graphical Cattell's Scree Test
get_scores

Get Scores from Principal Component Analysis (PCA)
model_parameters.BFBayesFactor

Parameters from BayesFactor objects
.factor_to_dummy

Safe transformation from factor/character to numeric
model_parameters.mlm

Parameters from multinomial or cumulative link models
n_parameters

Count number of parameters in a model
.recode_to_zero

Recode a variable so its lowest value is beginning with zero
print

Print model parameters
principal_components

Principal Component Analysis (PCA)
simulate_parameters

Simulate Model Parameters
simulate_model

Simulated draws from model coefficients
.factor_to_numeric

Safe transformation from factor/character to numeric
fish

Sample data set
format_rope

Percentage in ROPE formatting
ci_satterthwaite

Satterthwaite approximation for SEs, CIs and p-values
model_parameters.rma

Parameters from Meta-Analysis
model_parameters.stanreg

Parameters from Bayesian Models
ci_wald

Wald-test approximation for CIs and p-values
model_parameters.PCA

Parameters from Structural Models (PCA, EFA, ...)
model_parameters.htest

Parameters from Correlations and t-tests
select_parameters

Automated selection of model parameters
reshape_loadings

Reshape loadings between wide/long formats
model_parameters.kmeans

Parameters from Cluster Models (k-means, ...)
p_value

p-values
format_algorithm

Model Algorithm formatting
ci_betwithin

Between-within approximation for SEs, CIs and p-values
random_parameters

Summary information from random effects
format_number

Convert number to words
model_parameters.lavaan

Parameters from CFA/SEM models
format_order

Order (first, second, ...) formatting
model_parameters.merMod

Parameters from Mixed Models
n_clusters

Number of clusters to extract
model_parameters.zeroinfl

Parameters from Zero-Inflated Models
reduce_parameters

Dimensionality reduction (DR) / Features Reduction
standard_error

Standard Errors
standard_error_robust

Robust estimation
reexports

Objects exported from other packages
rescale_weights

Rescale design weights for multilevel analysis
standardize_names

Standardize column names
ci.merMod

Confidence Intervals (CI)
ICA

Independent Component Analysis (ICA)
DRR

Dimensionality Reduction via Regression (DRR)
describe_distribution

Describe a distribution
demean

Compute group-meaned and de-meaned variables