This function predicts the discrete choice behavior
Usage
# S3 method for class 'RprobitB_fit'
predict(object, data = NULL, overview = TRUE, digits = 2, ...)Arguments
- object
An object of class
RprobitB_fit.- data
Either
NULL, using the data inobject,an object of class
RprobitB_data, for example the test part generated bytrain_test,or a data frame of custom choice characteristics. It must have the same structure as
choice_dataused inprepare_data. Missing columns orNAvalues are set to 0.
- overview
If
TRUE, returns a confusion matrix.- digits
The number of digits of the returned choice probabilities.
digits = 2per default.- ...
Ignored.
Details
Predictions are made based on the maximum predicted probability for each choice alternative. See the vignette on choice prediction for a demonstration on how to visualize the model's sensitivity and specificity by means of a receiver operating characteristic (ROC) curve.
Examples
data <- simulate_choices(
form = choice ~ cov, N = 10, T = 10, J = 2, seed = 1
)
data <- train_test(data, test_proportion = 0.5)
model <- fit_model(data$train)
#> Computing sufficient statistics - 0 of 4
#> Computing sufficient statistics - 1 of 4
#> Computing sufficient statistics - 2 of 4
#> Computing sufficient statistics - 3 of 4
#> Computing sufficient statistics - 4 of 4
#> MCMC iteration - 1 of 1000
#> MCMC iteration - 10 of 1000
#> MCMC iteration - 20 of 1000
#> MCMC iteration - 30 of 1000
#> MCMC iteration - 40 of 1000
#> MCMC iteration - 50 of 1000
#> MCMC iteration - 60 of 1000
#> MCMC iteration - 70 of 1000
#> MCMC iteration - 80 of 1000
#> MCMC iteration - 90 of 1000
#> MCMC iteration - 100 of 1000
#> MCMC iteration - 110 of 1000
#> MCMC iteration - 120 of 1000
#> MCMC iteration - 130 of 1000
#> MCMC iteration - 140 of 1000
#> MCMC iteration - 150 of 1000
#> MCMC iteration - 160 of 1000
#> MCMC iteration - 170 of 1000
#> MCMC iteration - 180 of 1000
#> MCMC iteration - 190 of 1000
#> MCMC iteration - 200 of 1000
#> MCMC iteration - 210 of 1000
#> MCMC iteration - 220 of 1000
#> MCMC iteration - 230 of 1000
#> MCMC iteration - 240 of 1000
#> MCMC iteration - 250 of 1000
#> MCMC iteration - 260 of 1000
#> MCMC iteration - 270 of 1000
#> MCMC iteration - 280 of 1000
#> MCMC iteration - 290 of 1000
#> MCMC iteration - 300 of 1000
#> MCMC iteration - 310 of 1000
#> MCMC iteration - 320 of 1000
#> MCMC iteration - 330 of 1000
#> MCMC iteration - 340 of 1000
#> MCMC iteration - 350 of 1000
#> MCMC iteration - 360 of 1000
#> MCMC iteration - 370 of 1000
#> MCMC iteration - 380 of 1000
#> MCMC iteration - 390 of 1000
#> MCMC iteration - 400 of 1000
#> MCMC iteration - 410 of 1000
#> MCMC iteration - 420 of 1000
#> MCMC iteration - 430 of 1000
#> MCMC iteration - 440 of 1000
#> MCMC iteration - 450 of 1000
#> MCMC iteration - 460 of 1000
#> MCMC iteration - 470 of 1000
#> MCMC iteration - 480 of 1000
#> MCMC iteration - 490 of 1000
#> MCMC iteration - 500 of 1000
#> MCMC iteration - 510 of 1000
#> MCMC iteration - 520 of 1000
#> MCMC iteration - 530 of 1000
#> MCMC iteration - 540 of 1000
#> MCMC iteration - 550 of 1000
#> MCMC iteration - 560 of 1000
#> MCMC iteration - 570 of 1000
#> MCMC iteration - 580 of 1000
#> MCMC iteration - 590 of 1000
#> MCMC iteration - 600 of 1000
#> MCMC iteration - 610 of 1000
#> MCMC iteration - 620 of 1000
#> MCMC iteration - 630 of 1000
#> MCMC iteration - 640 of 1000
#> MCMC iteration - 650 of 1000
#> MCMC iteration - 660 of 1000
#> MCMC iteration - 670 of 1000
#> MCMC iteration - 680 of 1000
#> MCMC iteration - 690 of 1000
#> MCMC iteration - 700 of 1000
#> MCMC iteration - 710 of 1000
#> MCMC iteration - 720 of 1000
#> MCMC iteration - 730 of 1000
#> MCMC iteration - 740 of 1000
#> MCMC iteration - 750 of 1000
#> MCMC iteration - 760 of 1000
#> MCMC iteration - 770 of 1000
#> MCMC iteration - 780 of 1000
#> MCMC iteration - 790 of 1000
#> MCMC iteration - 800 of 1000
#> MCMC iteration - 810 of 1000
#> MCMC iteration - 820 of 1000
#> MCMC iteration - 830 of 1000
#> MCMC iteration - 840 of 1000
#> MCMC iteration - 850 of 1000
#> MCMC iteration - 860 of 1000
#> MCMC iteration - 870 of 1000
#> MCMC iteration - 880 of 1000
#> MCMC iteration - 890 of 1000
#> MCMC iteration - 900 of 1000
#> MCMC iteration - 910 of 1000
#> MCMC iteration - 920 of 1000
#> MCMC iteration - 930 of 1000
#> MCMC iteration - 940 of 1000
#> MCMC iteration - 950 of 1000
#> MCMC iteration - 960 of 1000
#> MCMC iteration - 970 of 1000
#> MCMC iteration - 980 of 1000
#> MCMC iteration - 990 of 1000
#> MCMC iteration - 1000 of 1000
#> Computing log-likelihood
predict(model)
#> predicted
#> true A B
#> A 11 2
#> B 0 37
predict(model, overview = FALSE)
#> id idc A B true predicted correct
#> 1 1 1 0.18 0.82 B B TRUE
#> 2 1 2 0.10 0.90 B B TRUE
#> 3 1 3 0.13 0.87 B B TRUE
#> 4 1 4 0.00 1.00 B B TRUE
#> 5 1 5 0.00 1.00 B B TRUE
#> 6 1 6 1.00 0.00 A A TRUE
#> 7 1 7 0.37 0.63 B B TRUE
#> 8 1 8 0.31 0.69 B B TRUE
#> 9 1 9 0.08 0.92 B B TRUE
#> 10 1 10 1.00 0.00 A A TRUE
#> 11 2 1 0.00 1.00 B B TRUE
#> 12 2 2 0.00 1.00 B B TRUE
#> 13 2 3 1.00 0.00 A A TRUE
#> 14 2 4 1.00 0.00 A A TRUE
#> 15 2 5 0.00 1.00 B B TRUE
#> 16 2 6 0.03 0.97 B B TRUE
#> 17 2 7 0.04 0.96 B B TRUE
#> 18 2 8 0.00 1.00 B B TRUE
#> 19 2 9 0.04 0.96 B B TRUE
#> 20 2 10 0.00 1.00 B B TRUE
#> 21 3 1 0.00 1.00 B B TRUE
#> 22 3 2 0.70 0.30 A A TRUE
#> 23 3 3 0.05 0.95 B B TRUE
#> 24 3 4 1.00 0.00 A A TRUE
#> 25 3 5 0.00 1.00 B B TRUE
#> 26 3 6 0.85 0.15 A A TRUE
#> 27 3 7 0.24 0.76 B B TRUE
#> 28 3 8 1.00 0.00 A A TRUE
#> 29 3 9 0.07 0.93 B B TRUE
#> 30 3 10 0.00 1.00 B B TRUE
#> 31 4 1 0.00 1.00 B B TRUE
#> 32 4 2 0.02 0.98 B B TRUE
#> 33 4 3 0.29 0.71 A B FALSE
#> 34 4 4 0.00 1.00 B B TRUE
#> 35 4 5 1.00 0.00 A A TRUE
#> 36 4 6 0.00 1.00 B B TRUE
#> 37 4 7 0.25 0.75 B B TRUE
#> 38 4 8 0.02 0.98 B B TRUE
#> 39 4 9 0.00 1.00 B B TRUE
#> 40 4 10 0.00 1.00 B B TRUE
#> 41 5 1 0.00 1.00 B B TRUE
#> 42 5 2 1.00 0.00 A A TRUE
#> 43 5 3 0.00 1.00 B B TRUE
#> 44 5 4 0.00 1.00 B B TRUE
#> 45 5 5 0.02 0.98 B B TRUE
#> 46 5 6 0.15 0.85 A B FALSE
#> 47 5 7 1.00 0.00 A A TRUE
#> 48 5 8 0.00 1.00 B B TRUE
#> 49 5 9 0.00 1.00 B B TRUE
#> 50 5 10 0.00 1.00 B B TRUE
predict(model, data = data$test)
#> predicted
#> true A B
#> A 15 3
#> B 6 26
predict(
model,
data = data.frame("cov_A" = c(1, 1, NA, NA), "cov_B" = c(1, NA, 1, NA)),
overview = FALSE
)
#> Checking for missing covariates
#> id idc A B prediction
#> 1 1 1 0.18 0.82 B
#> 2 2 1 0.00 1.00 B
#> 3 3 1 0.95 0.05 A
#> 4 4 1 0.18 0.82 B