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

blr_gains_table(model, data = NULL)

# S3 method for 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, ...)

## Arguments

model An object of class glm. A tibble or a data.frame. An object of class blr_gains_table. Plot title. X axis title. Y axis title. Diagonal line color. Color of the lift curve. Horizontal justification on the plot title. Other inputs.

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 Valid-ation Methodology, Moody’s Investors Service.

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,
# gains table
blr_gains_table(model)#> # A tibble: 10 x 12
#>    decile total   1   0    ks    tp    tn    fp    fn sensitivity
#>     <dbl> <int> <int> <int> <dbl> <int> <int> <int> <int>       <dbl>
#>  1   1.00    20    14     6  22.3    14   141     6    39        26.4
#>  2   2.00    20    13     7  42.1    27   134    13    26        50.9
#>  3   3.00    20    10    10  54.2    37   124    23    16        69.8
#>  4   4.00    20     7    13  58.5    44   111    36     9        83.0
#>  5   5.00    20     3    17  52.6    47    94    53     6        88.7
#>  6   6.00    20     3    17  46.7    50    77    70     3        94.3
#>  7   7.00    20     1    19  35.7    51    58    89     2        96.2
#>  8   8.00    20     2    18  27.2    53    40   107     0       100
#>  9   9.00    20     0    20  13.6    53    20   127     0       100
#> 10  10.0     20     0    20   0      53     0   147     0       100
#> # ... with 2 more variables: specificity <dbl>, accuracy <dbl>
# lift chart
k <- blr_gains_table(model)
plot(k)