Type:	Package
Title:	Tools for Developing Binary Logistic Regression Models
Version:	0.3.1
Description:	Tools designed to make it easier for beginner and intermediate users to build and validate binary logistic regression models. Includes bivariate analysis, comprehensive regression output, model fit statistics, variable selection procedures, model validation techniques and a 'shiny' app for interactive model building.
Depends:	R(≥ 3.5)
Imports:	car, data.table, ggplot2, gridExtra, Rcpp, stats, utils
Suggests:	covr, grid, ineq, knitr, magrittr, rmarkdown, testthat (≥ 3.0.0), vdiffr, xplorerr
License:	MIT + file LICENSE
URL:	https://blorr.rsquaredacademy.com/, https://github.com/rsquaredacademy/blorr
BugReports:	https://github.com/rsquaredacademy/blorr/issues
VignetteBuilder:	knitr
Encoding:	UTF-8
LazyData:	true
RoxygenNote:	7.3.2
LinkingTo:	Rcpp
Config/testthat/edition:	3
NeedsCompilation:	yes
Packaged:	2024-11-11 11:47:50 UTC; HP
Author:	Aravind Hebbali [aut, cre]
Maintainer:	Aravind Hebbali <hebbali.aravind@gmail.com>
Repository:	CRAN
Date/Publication:	2024-11-11 12:40:05 UTC

blorr package

Description

Tools for developing binary logistic regression models

Details

See the README on GitHub

Author(s)

Maintainer: Aravind Hebbali hebbali.aravind@gmail.com (ORCID)

See Also

Useful links:

• https://blorr.rsquaredacademy.com/

• https://github.com/rsquaredacademy/blorr

• Report bugs at https://github.com/rsquaredacademy/blorr/issues

Bank marketing data set

Description

The data is related with direct marketing campaigns of a Portuguese banking institution. The marketing campaigns were based on phone calls. Often, more than one contact to the same client was required, in order to access if the product (bank term deposit) would be ('yes') or not ('no') subscribed.

Usage

bank_marketing

Format

A tibble with 4521 rows and 17 variables:

age

age of the client

job

type of job

marital

marital status

education

education level of the client

default

has credit in default?

housing

has housing loan?

loan

has personal loan?

contact

contact communication type

month

last contact month of year

day_of_week

last contact day of the week

duration

last contact duration, in seconds

campaign

number of contacts performed during this campaign and for this client

pdays

number of days that passed by after the client was last contacted from a previous campaign

previous

number of contacts performed before this campaign and for this clien

poutcome

outcome of the previous marketing campaign

y

has the client subscribed a term deposit?

Source

[Moro et al., 2014] S. Moro, P. Cortez and P. Rita. A Data-Driven Approach to Predict the Success of Bank Telemarketing. Decision Support Systems, Elsevier, 62:22-31, June 2014

Bivariate analysis

Description

Information value and likelihood ratio chi square test for initial variable/predictor selection. Currently avialable for categorical predictors only.

Usage

blr_bivariate_analysis(data, response, ...)

## Default S3 method:
blr_bivariate_analysis(data, response, ...)

Arguments

Value

A tibble with the following columns:

See Also

Other bivariate analysis procedures: blr_segment(), blr_segment_dist(), blr_segment_twoway(), blr_woe_iv(), blr_woe_iv_stats()

Examples

blr_bivariate_analysis(hsb2, honcomp, female, prog, race, schtyp)

Collinearity diagnostics

Description

Variance inflation factor, tolerance, eigenvalues and condition indices.

Usage

blr_coll_diag(model)

blr_vif_tol(model)

blr_eigen_cindex(model)

Arguments

Details

Collinearity implies two variables are near perfect linear combinations of one another. Multicollinearity involves more than two variables. In the presence of multicollinearity, regression estimates are unstable and have high standard errors.

Tolerance

Percent of variance in the predictor that cannot be accounted for by other predictors.

Variance Inflation Factor

Variance inflation factors measure the inflation in the variances of the parameter estimates due to collinearities that exist among the predictors. It is a measure of how much the variance of the estimated regression coefficient \beta_k is inflated by the existence of correlation among the predictor variables in the model. A VIF of 1 means that there is no correlation among the kth predictor and the remaining predictor variables, and hence the variance of \beta_k is not inflated at all. The general rule of thumb is that VIFs exceeding 4 warrant further investigation, while VIFs exceeding 10 are signs of serious multicollinearity requiring correction.

Condition Index

Most multivariate statistical approaches involve decomposing a correlation matrix into linear combinations of variables. The linear combinations are chosen so that the first combination has the largest possible variance (subject to some restrictions), the second combination has the next largest variance, subject to being uncorrelated with the first, the third has the largest possible variance, subject to being uncorrelated with the first and second, and so forth. The variance of each of these linear combinations is called an eigenvalue. Collinearity is spotted by finding 2 or more variables that have large proportions of variance (.50 or more) that correspond to large condition indices. A rule of thumb is to label as large those condition indices in the range of 30 or larger.

Value

blr_coll_diag returns an object of class "blr_coll_diag". An object of class "blr_coll_diag" is a list containing the following components:

References

Belsley, D. A., Kuh, E., and Welsch, R. E. (1980). Regression Diagnostics: Identifying Influential Data and Sources of Collinearity. New York: John Wiley & Sons.

Examples

# model
model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

# vif and tolerance
blr_vif_tol(model)

# eigenvalues and condition indices
blr_eigen_cindex(model)

# collinearity diagnostics
blr_coll_diag(model)

Confusion matrix

Description

Confusion matrix and statistics.

Usage

blr_confusion_matrix(model, cutoff = 0.5, data = NULL, ...)

## Default S3 method:
blr_confusion_matrix(model, cutoff = 0.5, data = NULL, ...)

Arguments

Value

Confusion matix.

See Also

Other model validation techniques: blr_decile_capture_rate(), blr_decile_lift_chart(), blr_gains_table(), blr_gini_index(), blr_ks_chart(), blr_lorenz_curve(), blr_roc_curve(), blr_test_hosmer_lemeshow()

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
            family = binomial(link = 'logit'))

blr_confusion_matrix(model, cutoff = 0.4)

Event rate by decile

Description

Visualize the decile wise event rate.

Usage

blr_decile_capture_rate(
  gains_table,
  xaxis_title = "Decile",
  yaxis_title = "Capture Rate",
  title = "Capture Rate by Decile",
  bar_color = "blue",
  text_size = 3.5,
  text_vjust = -0.3,
  print_plot = TRUE
)

Arguments

See Also

Other model validation techniques: blr_confusion_matrix(), blr_decile_lift_chart(), blr_gains_table(), blr_gini_index(), blr_ks_chart(), blr_lorenz_curve(), blr_roc_curve(), blr_test_hosmer_lemeshow()

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
             family = binomial(link = 'logit'))
gt <- blr_gains_table(model)
blr_decile_capture_rate(gt)

Decile lift chart

Description

Decile wise lift chart.

Usage

blr_decile_lift_chart(
  gains_table,
  xaxis_title = "Decile",
  yaxis_title = "Decile Mean / Global Mean",
  title = "Decile Lift Chart",
  bar_color = "blue",
  text_size = 3.5,
  text_vjust = -0.3,
  print_plot = TRUE
)

Arguments

See Also

Other model validation techniques: blr_confusion_matrix(), blr_decile_capture_rate(), blr_gains_table(), blr_gini_index(), blr_ks_chart(), blr_lorenz_curve(), blr_roc_curve(), blr_test_hosmer_lemeshow()

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
             family = binomial(link = 'logit'))
gt <- blr_gains_table(model)
blr_decile_lift_chart(gt)

Gains table & lift chart

Description

Compute sensitivity, specificity, accuracy and KS statistics to generate the lift chart and the KS chart.

Usage

blr_gains_table(model, data = NULL)

## S3 method for class 'blr_gains_table'
plot(
  x,
  title = "Lift Chart",
  xaxis_title = "% Population",
  yaxis_title = "% Cumulative 1s",
  diag_line_col = "red",
  lift_curve_col = "blue",
  plot_title_justify = 0.5,
  print_plot = TRUE,
  ...
)

Arguments

Value

A tibble.

References

Agresti, A. (2007), An Introduction to Categorical Data Analysis, Second Edition, New York: John Wiley & Sons.

Agresti, A. (2013), Categorical Data Analysis, Third Edition, New York: John Wiley & Sons.

Thomas LC (2009): Consumer Credit Models: Pricing, Profit, and Portfolio. Oxford, Oxford Uni-versity Press.

Sobehart J, Keenan S, Stein R (2000): Benchmarking Quantitative Default Risk Models: A Validation Methodology, Moody’s Investors Service.

See Also

Other model validation techniques: blr_confusion_matrix(), blr_decile_capture_rate(), blr_decile_lift_chart(), blr_gini_index(), blr_ks_chart(), blr_lorenz_curve(), blr_roc_curve(), blr_test_hosmer_lemeshow()

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
             family = binomial(link = 'logit'))
# gains table
blr_gains_table(model)

# lift chart
k <- blr_gains_table(model)
plot(k)

Gini index

Description

Gini index is a measure of inequality and was developed to measure income inequality in labour market. In the predictive model, Gini Index is used for measuring discriminatory power.

Usage

blr_gini_index(model, data = NULL)

Arguments

Value

Gini index.

References

Siddiqi N (2006): Credit Risk Scorecards: developing and implementing intelligent credit scoring. New Jersey, Wiley.

Müller M, Rönz B (2000): Credit Scoring using Semiparametric Methods. In: Franke J, Härdle W, Stahl G (Eds.): Measuring Risk in Complex Stochastic Systems. New York, Springer-Verlag.

See Also

Other model validation techniques: blr_confusion_matrix(), blr_decile_capture_rate(), blr_decile_lift_chart(), blr_gains_table(), blr_ks_chart(), blr_lorenz_curve(), blr_roc_curve(), blr_test_hosmer_lemeshow()

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

blr_gini_index(model)

KS chart

Description

Kolmogorov-Smirnov (KS) statistics is used to assess predictive power for marketing or credit risk models. It is the maximum difference between cumulative event and non-event distribution across score/probability bands. The gains table typically has across score bands and can be used to find the KS for a model.

Usage

blr_ks_chart(
  gains_table,
  title = "KS Chart",
  yaxis_title = " ",
  xaxis_title = "Cumulative Population %",
  ks_line_color = "black",
  print_plot = TRUE
)

Arguments

References

https://pubmed.ncbi.nlm.nih.gov/843576/

See Also

Other model validation techniques: blr_confusion_matrix(), blr_decile_capture_rate(), blr_decile_lift_chart(), blr_gains_table(), blr_gini_index(), blr_lorenz_curve(), blr_roc_curve(), blr_test_hosmer_lemeshow()

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
             family = binomial(link = 'logit'))
gt <- blr_gains_table(model)
blr_ks_chart(gt)

Launch shiny app

Description

Launches shiny app for interactive model building.

Usage

blr_launch_app()

Examples

## Not run: 
blr_launch_app()

## End(Not run)

Model specification error

Description

Test for model specification error.

Usage

blr_linktest(model)

Arguments

Value

An object of class glm.

References

Pregibon, D. 1979. Data analytic methods for generalized linear models. PhD diss., University of Toronto.

Pregibon, D. 1980. Goodness of link tests for generalized linear models.

Tukey, J. W. 1949. One degree of freedom for non-additivity.

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

blr_linktest(model)

Lorenz curve

Description

Lorenz curve is a visual representation of inequality. It is used to measure the discriminatory power of the predictive model.

Usage

blr_lorenz_curve(
  model,
  data = NULL,
  title = "Lorenz Curve",
  xaxis_title = "Cumulative Events %",
  yaxis_title = "Cumulative Non Events %",
  diag_line_col = "red",
  lorenz_curve_col = "blue",
  print_plot = TRUE
)

Arguments

See Also

Other model validation techniques: blr_confusion_matrix(), blr_decile_capture_rate(), blr_decile_lift_chart(), blr_gains_table(), blr_gini_index(), blr_ks_chart(), blr_roc_curve(), blr_test_hosmer_lemeshow()

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

blr_lorenz_curve(model)

Model fit statistics

Description

Model fit statistics.

Usage

blr_model_fit_stats(model, ...)

Arguments

References

Menard, S. (2000). Coefficients of determination for multiple logistic regression analysis. The American Statistician, 54(1), 17-24.

Windmeijer, F. A. G. (1995). Goodness-of-fit measures in binary choice models. Econometric Reviews, 14, 101-116.

Hosmer, D.W., Jr., & Lemeshow, S. (2000), Applied logistic regression(2nd ed.). New York: John Wiley & Sons.

J. Scott Long & Jeremy Freese, 2000. "FITSTAT: Stata module to compute fit statistics for single equation regression models," Statistical Software Components S407201, Boston College Department of Economics, revised 22 Feb 2001.

Freese, Jeremy and J. Scott Long. Regression Models for Categorical Dependent Variables Using Stata. College Station: Stata Press, 2006.

Long, J. Scott. Regression Models for Categorical and Limited Dependent Variables. Thousand Oaks: Sage Publications, 1997.

See Also

Other model fit statistics: blr_multi_model_fit_stats(), blr_pairs(), blr_rsq_adj_count(), blr_rsq_cox_snell(), blr_rsq_effron(), blr_rsq_mcfadden_adj(), blr_rsq_mckelvey_zavoina(), blr_rsq_nagelkerke(), blr_test_lr()

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
            family = binomial(link = 'logit'))

blr_model_fit_stats(model)

Multi model fit statistics

Description

Measures of model fit statistics for multiple models.

Usage

blr_multi_model_fit_stats(model, ...)

## Default S3 method:
blr_multi_model_fit_stats(model, ...)

Arguments

Value

A tibble.

See Also

Other model fit statistics: blr_model_fit_stats(), blr_pairs(), blr_rsq_adj_count(), blr_rsq_cox_snell(), blr_rsq_effron(), blr_rsq_mcfadden_adj(), blr_rsq_mckelvey_zavoina(), blr_rsq_nagelkerke(), blr_test_lr()

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

model2 <- glm(honcomp ~ female + read + math, data = hsb2,
family = binomial(link = 'logit'))

blr_multi_model_fit_stats(model, model2)

Concordant & discordant pairs

Description

Association of predicted probabilities and observed responses.

Usage

blr_pairs(model)

Arguments

Value

A tibble.

See Also

Other model fit statistics: blr_model_fit_stats(), blr_multi_model_fit_stats(), blr_rsq_adj_count(), blr_rsq_cox_snell(), blr_rsq_effron(), blr_rsq_mcfadden_adj(), blr_rsq_mckelvey_zavoina(), blr_rsq_nagelkerke(), blr_test_lr()

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

blr_pairs(model)

CI Displacement C vs fitted values plot

Description

Confidence interval displacement diagnostics C vs fitted values plot.

Usage

blr_plot_c_fitted(
  model,
  point_color = "blue",
  title = "CI Displacement C vs Fitted Values Plot",
  xaxis_title = "Fitted Values",
  yaxis_title = "CI Displacement C"
)

Arguments

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

blr_plot_c_fitted(model)

CI Displacement C vs leverage plot

Description

Confidence interval displacement diagnostics C vs leverage plot.

Usage

blr_plot_c_leverage(
  model,
  point_color = "blue",
  title = "CI Displacement C vs Leverage Plot",
  xaxis_title = "Leverage",
  yaxis_title = "CI Displacement C"
)

Arguments

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

blr_plot_c_leverage(model)

Deviance vs fitted values plot

Description

Deviance vs fitted values plot.

Usage

blr_plot_deviance_fitted(
  model,
  point_color = "blue",
  line_color = "red",
  title = "Deviance Residual vs Fitted Values",
  xaxis_title = "Fitted Values",
  yaxis_title = "Deviance Residual"
)

Arguments

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

blr_plot_deviance_fitted(model)

Deviance residual values

Description

Deviance residuals plot.

Usage

blr_plot_deviance_residual(
  model,
  point_color = "blue",
  title = "Deviance Residuals Plot",
  xaxis_title = "id",
  yaxis_title = "Deviance Residuals"
)

Arguments

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

blr_plot_deviance_residual(model)

DFBETAs panel

Description

Panel of plots to detect influential observations using DFBETAs.

Usage

blr_plot_dfbetas_panel(model, print_plot = TRUE)

Arguments

Details

DFBETA measures the difference in each parameter estimate with and without the influential point. There is a DFBETA for each data point i.e if there are n observations and k variables, there will be n * k DFBETAs. In general, large values of DFBETAS indicate observations that are influential in estimating a given parameter. Belsley, Kuh, and Welsch recommend 2 as a general cutoff value to indicate influential observations and 2/\sqrt(n) as a size-adjusted cutoff.

Value

list; blr_dfbetas_panel returns a list of tibbles (for intercept and each predictor) with the observation number and DFBETA of observations that exceed the threshold for classifying an observation as an outlier/influential observation.

References

Belsley, David A.; Kuh, Edwin; Welsh, Roy E. (1980). Regression Diagnostics: Identifying Influential Data and Sources of Collinearity. Wiley Series in Probability and Mathematical Statistics. New York: John Wiley & Sons. pp. ISBN 0-471-05856-4.

Examples

## Not run: 
model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

blr_plot_dfbetas_panel(model)

## End(Not run)

CI Displacement C plot

Description

Confidence interval displacement diagnostics C plot.

Usage

blr_plot_diag_c(
  model,
  point_color = "blue",
  title = "CI Displacement C Plot",
  xaxis_title = "id",
  yaxis_title = "CI Displacement C"
)

Arguments

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

blr_plot_diag_c(model)

CI Displacement CBAR plot

Description

Confidence interval displacement diagnostics CBAR plot.

Usage

blr_plot_diag_cbar(
  model,
  point_color = "blue",
  title = "CI Displacement CBAR Plot",
  xaxis_title = "id",
  yaxis_title = "CI Displacement CBAR"
)

Arguments

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

blr_plot_diag_cbar(model)

Delta chisquare plot

Description

Diagnostics for detecting ill fitted observations.

Usage

blr_plot_diag_difchisq(
  model,
  point_color = "blue",
  title = "Delta Chisquare Plot",
  xaxis_title = "id",
  yaxis_title = "Delta Chisquare"
)

Arguments

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

blr_plot_diag_difchisq(model)

Delta deviance plot

Description

Diagnostics for detecting ill fitted observations.

Usage

blr_plot_diag_difdev(
  model,
  point_color = "blue",
  title = "Delta Deviance Plot",
  xaxis_title = "id",
  yaxis_title = "Delta Deviance"
)

Arguments

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

blr_plot_diag_difdev(model)

Fitted values diagnostics plot

Description

Diagnostic plots for fitted values.

Usage

blr_plot_diag_fit(model, print_plot = TRUE)

Arguments

Value

A panel of diagnostic plots for fitted values.

References

Fox, John (1991), Regression Diagnostics. Newbury Park, CA: Sage Publications.

Cook, R. D. and Weisberg, S. (1982), Residuals and Influence in Regression, New York: Chapman & Hall.

See Also

Other diagnostic plots: blr_plot_diag_influence(), blr_plot_diag_leverage()

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

blr_plot_diag_fit(model)

Influence diagnostics plot

Description

Reisudal diagnostic plots for detecting influential observations.

Usage

blr_plot_diag_influence(model, print_plot = TRUE)

Arguments

Value

A panel of influence diagnostic plots.

References

Fox, John (1991), Regression Diagnostics. Newbury Park, CA: Sage Publications.

Cook, R. D. and Weisberg, S. (1982), Residuals and Influence in Regression, New York: Chapman & Hall.

See Also

Other diagnostic plots: blr_plot_diag_fit(), blr_plot_diag_leverage()

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

blr_plot_diag_influence(model)

Leverage diagnostics plot

Description

Diagnostic plots for leverage.

Usage

blr_plot_diag_leverage(model, print_plot = TRUE)

Arguments

Value

A panel of diagnostic plots for leverage.

References

Fox, John (1991), Regression Diagnostics. Newbury Park, CA: Sage Publications.

Cook, R. D. and Weisberg, S. (1982), Residuals and Influence in Regression, New York: Chapman & Hall.

See Also

Other diagnostic plots: blr_plot_diag_fit(), blr_plot_diag_influence()

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

blr_plot_diag_leverage(model)

Delta chi square vs fitted values plot

Description

Delta Chi Square vs fitted values plot for detecting ill fitted observations.

Usage

blr_plot_difchisq_fitted(
  model,
  point_color = "blue",
  title = "Delta Chi Square vs Fitted Values Plot",
  xaxis_title = "Fitted Values",
  yaxis_title = "Delta Chi Square"
)

Arguments

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

blr_plot_difchisq_fitted(model)

Delta chi square vs leverage plot

Description

Delta chi square vs leverage plot.

Usage

blr_plot_difchisq_leverage(
  model,
  point_color = "blue",
  title = "Delta Chi Square vs Leverage Plot",
  xaxis_title = "Leverage",
  yaxis_title = "Delta Chi Square"
)

Arguments

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

blr_plot_difchisq_leverage(model)

Delta deviance vs fitted values plot

Description

Delta deviance vs fitted values plot for detecting ill fitted observations.

Usage

blr_plot_difdev_fitted(
  model,
  point_color = "blue",
  title = "Delta Deviance vs Fitted Values Plot",
  xaxis_title = "Fitted Values",
  yaxis_title = "Delta Deviance"
)

Arguments

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

blr_plot_difdev_fitted(model)

Delta deviance vs leverage plot

Description

Delta deviance vs leverage plot.

Usage

blr_plot_difdev_leverage(
  model,
  point_color = "blue",
  title = "Delta Deviance vs Leverage Plot",
  xaxis_title = "Leverage",
  yaxis_title = "Delta Deviance"
)

Arguments

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

blr_plot_difdev_leverage(model)

Fitted values vs leverage plot

Description

Fitted values vs leverage plot.

Usage

blr_plot_fitted_leverage(
  model,
  point_color = "blue",
  title = "Fitted Values vs Leverage Plot",
  xaxis_title = "Leverage",
  yaxis_title = "Fitted Values"
)

Arguments

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

blr_plot_fitted_leverage(model)

Leverage plot

Description

Leverage plot.

Usage

blr_plot_leverage(
  model,
  point_color = "blue",
  title = "Leverage Plot",
  xaxis_title = "id",
  yaxis_title = "Leverage"
)

Arguments

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

blr_plot_leverage(model)

Leverage vs fitted values plot

Description

Leverage vs fitted values plot

Usage

blr_plot_leverage_fitted(
  model,
  point_color = "blue",
  title = "Leverage vs Fitted Values",
  xaxis_title = "Fitted Values",
  yaxis_title = "Leverage"
)

Arguments

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

blr_plot_leverage_fitted(model)

Residual values plot

Description

Standardised pearson residuals plot.

Usage

blr_plot_pearson_residual(
  model,
  point_color = "blue",
  title = "Standardized Pearson Residuals",
  xaxis_title = "id",
  yaxis_title = "Standardized Pearson Residuals"
)

Arguments

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

blr_plot_pearson_residual(model)

Residual vs fitted values plot

Description

Residual vs fitted values plot.

Usage

blr_plot_residual_fitted(
  model,
  point_color = "blue",
  line_color = "red",
  title = "Standardized Pearson Residual vs Fitted Values",
  xaxis_title = "Fitted Values",
  yaxis_title = "Standardized Pearson Residual"
)

Arguments

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

blr_plot_residual_fitted(model)

Decile capture rate data

Description

Data for generating decile capture rate.

Usage

blr_prep_dcrate_data(gains_table)

Arguments

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
             family = binomial(link = 'logit'))
gt <- blr_gains_table(model)
blr_prep_dcrate_data(gt)

KS Chart data

Description

Data for generating KS chart.

Usage

blr_prep_kschart_data(gains_table)

blr_prep_kschart_line(gains_table)

blr_prep_ksannotate_y(ks_line)

blr_prep_kschart_stat(ks_line)

blr_prep_ksannotate_x(ks_line)

Arguments

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
             family = binomial(link = 'logit'))
gt <- blr_gains_table(model)
blr_prep_kschart_data(gt)
ks_line <- blr_prep_kschart_line(gt)
blr_prep_kschart_stat(ks_line)
blr_prep_ksannotate_y(ks_line)
blr_prep_ksannotate_x(ks_line)

Lift Chart data

Description

Data for generating lift chart.

Usage

blr_prep_lchart_gmean(gains_table)

blr_prep_lchart_data(gains_table, global_mean)

Arguments

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
             family = binomial(link = 'logit'))
gt <- blr_gains_table(model)
globalmean <- blr_prep_lchart_gmean(gt)
blr_prep_lchart_data(gt, globalmean)

Lorenz curve data

Description

Data for generating Lorenz curve.

Usage

blr_prep_lorenz_data(model, data = NULL, test_data = FALSE)

Arguments

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
             family = binomial(link = 'logit'))
data <- model$data
blr_prep_lorenz_data(model, data, FALSE)

ROC curve data

Description

Data for generating ROC curve.

Usage

blr_prep_roc_data(gains_table)

Arguments

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
             family = binomial(link = 'logit'))
gt <- blr_gains_table(model)
blr_prep_roc_data(gt)

Binary logistic regression

Description

Binary logistic regression.

Usage

blr_regress(object, ...)

## S3 method for class 'glm'
blr_regress(object, odd_conf_limit = FALSE, ...)

Arguments

Examples

# using formula
blr_regress(object = honcomp ~ female + read + science, data = hsb2)

# using a model built with glm
model <- glm(honcomp ~ female + read + science, data = hsb2,
             family = binomial(link = 'logit'))

blr_regress(model)

# odds ratio estimates
blr_regress(model, odd_conf_limit = TRUE)

Residual diagnostics

Description

Diagnostics for confidence interval displacement and detecting ill fitted observations.

Usage

blr_residual_diagnostics(model)

Arguments

Value

C, CBAR, DIFDEV and DIFCHISQ.

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

blr_residual_diagnostics(model)

ROC curve

Description

Receiver operating characteristic curve (ROC) curve is used for assessing accuracy of the model classification.

Usage

blr_roc_curve(
  gains_table,
  title = "ROC Curve",
  xaxis_title = "1 - Specificity",
  yaxis_title = "Sensitivity",
  roc_curve_col = "blue",
  diag_line_col = "red",
  point_shape = 18,
  point_fill = "blue",
  point_color = "blue",
  plot_title_justify = 0.5,
  print_plot = TRUE
)

Arguments

References

Agresti, A. (2007), An Introduction to Categorical Data Analysis, Second Edition, New York: John Wiley & Sons.

Hosmer, D. W., Jr. and Lemeshow, S. (2000), Applied Logistic Regression, 2nd Edition, New York: John Wiley & Sons.

Siddiqi N (2006): Credit Risk Scorecards: developing and implementing intelligent credit scoring. New Jersey, Wiley.

Thomas LC, Edelman DB, Crook JN (2002): Credit Scoring and Its Applications. Philadelphia, SIAM Monographs on Mathematical Modeling and Computation.

See Also

Other model validation techniques: blr_confusion_matrix(), blr_decile_capture_rate(), blr_decile_lift_chart(), blr_gains_table(), blr_gini_index(), blr_ks_chart(), blr_lorenz_curve(), blr_test_hosmer_lemeshow()

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
             family = binomial(link = 'logit'))
k <- blr_gains_table(model)
blr_roc_curve(k)

Adjusted count R2

Description

Adjusted count r-squared.

Usage

blr_rsq_adj_count(model)

Arguments

Value

Adjusted count r-squared.

See Also

Other model fit statistics: blr_model_fit_stats(), blr_multi_model_fit_stats(), blr_pairs(), blr_rsq_cox_snell(), blr_rsq_effron(), blr_rsq_mcfadden_adj(), blr_rsq_mckelvey_zavoina(), blr_rsq_nagelkerke(), blr_test_lr()

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
            family = binomial(link = 'logit'))

blr_rsq_adj_count(model)

Count R2

Description

Count r-squared.

Usage

blr_rsq_count(model)

Arguments

Value

Count r-squared.

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
            family = binomial(link = 'logit'))

blr_rsq_count(model)

Cox Snell R2

Description

Cox Snell pseudo r-squared.

Usage

blr_rsq_cox_snell(model)

Arguments

Value

Cox Snell pseudo r-squared.

References

Cox, D. R., & Snell, E. J. (1989). The analysis of binary data (2nd ed.). London: Chapman and Hall.

Maddala, G. S. (1983). Limited dependent and qualitative variables in economics. New York: Cambridge Press.

See Also

Other model fit statistics: blr_model_fit_stats(), blr_multi_model_fit_stats(), blr_pairs(), blr_rsq_adj_count(), blr_rsq_effron(), blr_rsq_mcfadden_adj(), blr_rsq_mckelvey_zavoina(), blr_rsq_nagelkerke(), blr_test_lr()

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
            family = binomial(link = 'logit'))

blr_rsq_cox_snell(model)

Effron R2

Description

Effron pseudo r-squared.

Usage

blr_rsq_effron(model)

Arguments

Value

Effron pseudo r-squared.

References

Efron, B. (1978). Regression and ANOVA with zero-one data: Measures of residual variation. Journal of the American Statistical Association, 73, 113-121.

See Also

Other model fit statistics: blr_model_fit_stats(), blr_multi_model_fit_stats(), blr_pairs(), blr_rsq_adj_count(), blr_rsq_cox_snell(), blr_rsq_mcfadden_adj(), blr_rsq_mckelvey_zavoina(), blr_rsq_nagelkerke(), blr_test_lr()

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
            family = binomial(link = 'logit'))

blr_rsq_effron(model)

McFadden's R2

Description

McFadden's pseudo r-squared for the model.

Usage

blr_rsq_mcfadden(model)

Arguments

Value

McFadden's r-squared.

References

https://eml.berkeley.edu/reprints/mcfadden/zarembka.pdf

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
            family = binomial(link = 'logit'))

blr_rsq_mcfadden(model)

McFadden's adjusted R2

Description

McFadden's adjusted pseudo r-squared for the model.

Usage

blr_rsq_mcfadden_adj(model)

Arguments

Value

McFadden's adjusted r-squared.

References

https://eml.berkeley.edu/reprints/mcfadden/zarembka.pdf

See Also

Other model fit statistics: blr_model_fit_stats(), blr_multi_model_fit_stats(), blr_pairs(), blr_rsq_adj_count(), blr_rsq_cox_snell(), blr_rsq_effron(), blr_rsq_mckelvey_zavoina(), blr_rsq_nagelkerke(), blr_test_lr()

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
            family = binomial(link = 'logit'))

blr_rsq_mcfadden_adj(model)

McKelvey Zavoina R2

Description

McKelvey Zavoina pseudo r-squared.

Usage

blr_rsq_mckelvey_zavoina(model)

Arguments

Value

Cragg-Uhler (Nagelkerke) R2 pseudo r-squared.

References

McKelvey, R. D., & Zavoina, W. (1975). A statistical model for the analysis of ordinal level dependent variables. Journal of Mathematical Sociology, 4, 103-12.

See Also

Other model fit statistics: blr_model_fit_stats(), blr_multi_model_fit_stats(), blr_pairs(), blr_rsq_adj_count(), blr_rsq_cox_snell(), blr_rsq_effron(), blr_rsq_mcfadden_adj(), blr_rsq_nagelkerke(), blr_test_lr()

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
            family = binomial(link = 'logit'))

blr_rsq_mckelvey_zavoina(model)

Cragg-Uhler (Nagelkerke) R2

Description

Cragg-Uhler (Nagelkerke) R2 pseudo r-squared.

Usage

blr_rsq_nagelkerke(model)

Arguments

Value

Cragg-Uhler (Nagelkerke) R2 pseudo r-squared.

References

Cragg, S. G., & Uhler, R. (1970). The demand for automobiles. Canadian Journal of Economics, 3, 386-406.

Maddala, G. S. (1983). Limited dependent and qualitative variables in economics. New York: Cambridge Press.

Nagelkerke, N. (1991). A note on a general definition of the coefficient of determination.

See Also

Other model fit statistics: blr_model_fit_stats(), blr_multi_model_fit_stats(), blr_pairs(), blr_rsq_adj_count(), blr_rsq_cox_snell(), blr_rsq_effron(), blr_rsq_mcfadden_adj(), blr_rsq_mckelvey_zavoina(), blr_test_lr()

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
            family = binomial(link = 'logit'))

blr_rsq_nagelkerke(model)

Event rate

Description

Event rate by segements/levels of a qualitative variable.

Usage

blr_segment(data, response, predictor)

## Default S3 method:
blr_segment(data, response, predictor)

Arguments

Value

A tibble.

See Also

Other bivariate analysis procedures: blr_bivariate_analysis(), blr_segment_dist(), blr_segment_twoway(), blr_woe_iv(), blr_woe_iv_stats()

Examples

blr_segment(hsb2, honcomp, prog)

Response distribution

Description

Distribution of response variable by segements/levels of a qualitative variable.

Usage

blr_segment_dist(data, response, predictor)

## S3 method for class 'blr_segment_dist'
plot(
  x,
  title = NA,
  xaxis_title = "Levels",
  yaxis_title = "Sample Distribution",
  sec_yaxis_title = "1s Distribution",
  bar_color = "blue",
  line_color = "red",
  print_plot = TRUE,
  ...
)

Arguments

Value

A tibble.

See Also

Other bivariate analysis procedures: blr_bivariate_analysis(), blr_segment(), blr_segment_twoway(), blr_woe_iv(), blr_woe_iv_stats()

Examples

k <- blr_segment_dist(hsb2, honcomp, prog)
k

# plot
plot(k)

Two way event rate

Description

Event rate across two qualitative variables.

Usage

blr_segment_twoway(data, response, variable_1, variable_2)

## Default S3 method:
blr_segment_twoway(data, response, variable_1, variable_2)

Arguments

Value

A tibble.

See Also

Other bivariate analysis procedures: blr_bivariate_analysis(), blr_segment(), blr_segment_dist(), blr_woe_iv(), blr_woe_iv_stats()

Examples

blr_segment_twoway(hsb2, honcomp, prog, female)

Stepwise AIC backward elimination

Description

Build regression model from a set of candidate predictor variables by removing predictors based on akaike information criterion, in a stepwise manner until there is no variable left to remove any more.

Usage

blr_step_aic_backward(model, ...)

## Default S3 method:
blr_step_aic_backward(model, progress = FALSE, details = FALSE, ...)

## S3 method for class 'blr_step_aic_backward'
plot(x, text_size = 3, print_plot = TRUE, ...)

Arguments

Value

blr_step_aic_backward returns an object of class "blr_step_aic_backward". An object of class "blr_step_aic_backward" is a list containing the following components:

References

Venables, W. N. and Ripley, B. D. (2002) Modern Applied Statistics with S. Fourth edition. Springer.

See Also

Other variable selection procedures: blr_step_aic_both(), blr_step_aic_forward(), blr_step_p_backward(), blr_step_p_forward()

Examples

## Not run: 
model <- glm(honcomp ~ female + read + science + math + prog + socst,
data = hsb2, family = binomial(link = 'logit'))

# elimination summary
blr_step_aic_backward(model)

# print details of each step
blr_step_aic_backward(model, details = TRUE)

# plot
plot(blr_step_aic_backward(model))

# final model
k <- blr_step_aic_backward(model)
k$model


## End(Not run)

Stepwise AIC selection

Description

Build regression model from a set of candidate predictor variables by entering and removing predictors based on akaike information criterion, in a stepwise manner until there is no variable left to enter or remove any more.

Usage

blr_step_aic_both(model, details = FALSE, ...)

## S3 method for class 'blr_step_aic_both'
plot(x, text_size = 3, ...)

Arguments

Value

blr_step_aic_both returns an object of class "blr_step_aic_both". An object of class "blr_step_aic_both" is a list containing the following components:

References

Venables, W. N. and Ripley, B. D. (2002) Modern Applied Statistics with S. Fourth edition. Springer.

See Also

Other variable selection procedures: blr_step_aic_backward(), blr_step_aic_forward(), blr_step_p_backward(), blr_step_p_forward()

Examples

## Not run: 
model <- glm(y ~ ., data = stepwise)

# selection summary
blr_step_aic_both(model)

# print details at each step
blr_step_aic_both(model, details = TRUE)

# plot
plot(blr_step_aic_both(model))

# final model
k <- blr_step_aic_both(model)
k$model


## End(Not run)

Stepwise AIC forward selection

Description

Build regression model from a set of candidate predictor variables by entering predictors based on chi square statistic, in a stepwise manner until there is no variable left to enter any more.

Usage

blr_step_aic_forward(model, ...)

## Default S3 method:
blr_step_aic_forward(model, progress = FALSE, details = FALSE, ...)

## S3 method for class 'blr_step_aic_forward'
plot(x, text_size = 3, print_plot = TRUE, ...)

Arguments

Value

blr_step_aic_forward returns an object of class "blr_step_aic_forward". An object of class "blr_step_aic_forward" is a list containing the following components:

References

Venables, W. N. and Ripley, B. D. (2002) Modern Applied Statistics with S. Fourth edition. Springer.

See Also

Other variable selection procedures: blr_step_aic_backward(), blr_step_aic_both(), blr_step_p_backward(), blr_step_p_forward()

Examples

## Not run: 
model <- glm(honcomp ~ female + read + science, data = hsb2,
family = binomial(link = 'logit'))

# selection summary
blr_step_aic_forward(model)

# print details of each step
blr_step_aic_forward(model, details = TRUE)

# plot
plot(blr_step_aic_forward(model))

# final model
k <- blr_step_aic_forward(model)
k$model


## End(Not run)

Stepwise backward regression

Description

Build regression model from a set of candidate predictor variables by removing predictors based on p values, in a stepwise manner until there is no variable left to remove any more.

Usage

blr_step_p_backward(model, ...)

## Default S3 method:
blr_step_p_backward(model, prem = 0.3, details = FALSE, ...)

## S3 method for class 'blr_step_p_backward'
plot(x, model = NA, print_plot = TRUE, ...)

Arguments

Value

blr_step_p_backward returns an object of class "blr_step_p_backward". An object of class "blr_step_p_backward" is a list containing the following components:

References

Chatterjee, Samprit and Hadi, Ali. Regression Analysis by Example. 5th ed. N.p.: John Wiley & Sons, 2012. Print.

See Also

Other variable selection procedures: blr_step_aic_backward(), blr_step_aic_both(), blr_step_aic_forward(), blr_step_p_forward()

Examples

## Not run: 
# stepwise backward regression
model <- glm(honcomp ~ female + read + science + math + prog + socst,
  data = hsb2, family = binomial(link = 'logit'))
blr_step_p_backward(model)

# stepwise backward regression plot
model <- glm(honcomp ~ female + read + science + math + prog + socst,
  data = hsb2, family = binomial(link = 'logit'))
k <- blr_step_p_backward(model)
plot(k)

# final model
k$model


## End(Not run)

Stepwise regression

Description

Build regression model from a set of candidate predictor variables by entering and removing predictors based on p values, in a stepwise manner until there is no variable left to enter or remove any more.

Usage

blr_step_p_both(model, ...)

## Default S3 method:
blr_step_p_both(model, pent = 0.1, prem = 0.3, details = FALSE, ...)

## S3 method for class 'blr_step_p_both'
plot(x, model = NA, print_plot = TRUE, ...)

Arguments

Value

blr_step_p_both returns an object of class "blr_step_p_both". An object of class "blr_step_p_both" is a list containing the following components:

References

Chatterjee, Samprit and Hadi, Ali. Regression Analysis by Example. 5th ed. N.p.: John Wiley & Sons, 2012. Print.

Examples

## Not run: 
# stepwise regression
model <- glm(y ~ ., data = stepwise)
blr_step_p_both(model)

# stepwise regression plot
model <- glm(y ~ ., data = stepwise)
k <- blr_step_p_both(model)
plot(k)

# final model
k$model


## End(Not run)

Stepwise forward regression

Description

Build regression model from a set of candidate predictor variables by entering predictors based on p values, in a stepwise manner until there is no variable left to enter any more.

Usage

blr_step_p_forward(model, ...)

## Default S3 method:
blr_step_p_forward(model, penter = 0.3, details = FALSE, ...)

## S3 method for class 'blr_step_p_forward'
plot(x, model = NA, print_plot = TRUE, ...)

Arguments

Value

blr_step_p_forward returns an object of class "blr_step_p_forward". An object of class "blr_step_p_forward" is a list containing the following components:

References

Chatterjee, Samprit and Hadi, Ali. Regression Analysis by Example. 5th ed. N.p.: John Wiley & Sons, 2012. Print.

Kutner, MH, Nachtscheim CJ, Neter J and Li W., 2004, Applied Linear Statistical Models (5th edition). Chicago, IL., McGraw Hill/Irwin.

See Also

Other variable selection procedures: blr_step_aic_backward(), blr_step_aic_both(), blr_step_aic_forward(), blr_step_p_backward()

Examples

## Not run: 
# stepwise forward regression
model <- glm(honcomp ~ female + read + science, data = hsb2,
  family = binomial(link = 'logit'))
blr_step_p_forward(model)

# stepwise forward regression plot
model <- glm(honcomp ~ female + read + science, data = hsb2,
  family = binomial(link = 'logit'))
k <- blr_step_p_forward(model)
plot(k)

# final model
k$model


## End(Not run)

Hosmer lemeshow test

Description

Hosmer lemeshow goodness of fit test.

Usage

blr_test_hosmer_lemeshow(model, data = NULL)

Arguments

References

Hosmer, D.W., Jr., & Lemeshow, S. (2000), Applied logistic regression(2nd ed.). New York: John Wiley & Sons.

See Also

Other model validation techniques: blr_confusion_matrix(), blr_decile_capture_rate(), blr_decile_lift_chart(), blr_gains_table(), blr_gini_index(), blr_ks_chart(), blr_lorenz_curve(), blr_roc_curve()

Examples

model <- glm(honcomp ~ female + read + science, data = hsb2,
             family = binomial(link = 'logit'))

blr_test_hosmer_lemeshow(model)

Likelihood ratio test

Description

Performs the likelihood ratio test for full and reduced model.

Usage

blr_test_lr(full_model, reduced_model)

## Default S3 method:
blr_test_lr(full_model, reduced_model)

Arguments

Value

Two tibbles with model information and test results.

See Also

Other model fit statistics: blr_model_fit_stats(), blr_multi_model_fit_stats(), blr_pairs(), blr_rsq_adj_count(), blr_rsq_cox_snell(), blr_rsq_effron(), blr_rsq_mcfadden_adj(), blr_rsq_mckelvey_zavoina(), blr_rsq_nagelkerke()

Examples

# compare full model with intercept only model
# full model
model_1 <- glm(honcomp ~ female + read + science, data = hsb2,
            family = binomial(link = 'logit'))

blr_test_lr(model_1)

# compare full model with nested model
# nested model
model_2 <- glm(honcomp ~ female + read, data = hsb2,
            family = binomial(link = 'logit'))

blr_test_lr(model_1, model_2)

WoE & IV

Description

Weight of evidence and information value. Currently avialable for categorical predictors only.

Usage

blr_woe_iv(data, predictor, response, digits = 4, ...)

## S3 method for class 'blr_woe_iv'
plot(
  x,
  title = NA,
  xaxis_title = "Levels",
  yaxis_title = "WoE",
  bar_color = "blue",
  line_color = "red",
  print_plot = TRUE,
  ...
)

Arguments

Value

A tibble.

References

Siddiqi N (2006): Credit Risk Scorecards: developing and implementing intelligent credit scoring. New Jersey, Wiley.

See Also

Other bivariate analysis procedures: blr_bivariate_analysis(), blr_segment(), blr_segment_dist(), blr_segment_twoway(), blr_woe_iv_stats()

Examples

# woe and iv
k <- blr_woe_iv(hsb2, female, honcomp)
k

# plot woe
plot(k)

Multi variable WOE & IV

Description

Prints weight of evidence and information value for multiple variables. Currently avialable for categorical predictors only.

Usage

blr_woe_iv_stats(data, response, ...)

Arguments

See Also

Other bivariate analysis procedures: blr_bivariate_analysis(), blr_segment(), blr_segment_dist(), blr_segment_twoway(), blr_woe_iv()

Examples

blr_woe_iv_stats(hsb2, honcomp, prog, race, female, schtyp)

High School and Beyond Data Set

Description

A dataset containing demographic information and standardized test scores of high school students.

Usage

hsb2

Format

A data frame with 200 rows and 11 variables:

id

id of the student

female

gender of the student

race

ethnic background of the student

ses

socio-economic status of the student

schtyp

school type

prog

program type

read

scores from test of reading

write

scores from test of writing

math

scores from test of math

science

scores from test of science

socst

scores from test of social studies

honcomp

1 if write > 60, else 0

Source

https://www.openintro.org/data/index.php?data=hsb

Dummy Data Set

Description

Dummy Data Set

Usage

stepwise

Format

An object of class data.frame with 20000 rows and 7 columns.