Maximizing log-likelihood function of Binary Logistic Regression and estimating probabilities of the dependent variable equaling 1:
maximize
logexp_sum(matrix_1)
Value:
logistic(matrix_1)
OR (equivalently):
maximize
logexp_sum(matrix_1)
calculate
Point: point_problem_1
Value:
logistic(matrix_1)
where
matrix_1:
x1 |
x2 |
x3 |
x4 |
scenario_benchmark |
1 1 1 1 1 1 |
-4 5 8 -3 -2 2 |
-8 -4 1 4 -4 8 |
-3 6 -4 -9 -1 7 |
0 1 1 0 1 0 |
The matrix_1 is in file matrix_1.txt in PSG Matrix format (see, PSG Matrix in General (Text) Format).
Optimal point (estimates of regression coefficients):
Component_name |
Value |
x1 x2 x3 x4 |
6.69e+001 6.38e+001 -1.69e+001 -1.13e+001 |
Value of the logistic function (estimates of probabilities):
value |
6.52e-009 1e+000 1e+000 5.27e-040 9.99e-001 1.65e-009 |
Files problem_logistic_regression_Calculate_test.txt, problem_logistic_regression_test.txt, and matrix_1.txt are in folder .\Aorda\PSG\Examples\Functions\logistic_regression_test.