Skip to content

Predict Conditional Probabilities from a Fitted bgmCompare Model

Source: R/simulate_predict.R
predict.bgmCompare.Rd

Computes conditional probability distributions for one or more variables given the observed values of other variables in the data, using group-specific parameters from a bgmCompare model.

Usage

# S3 method for class 'bgmCompare'
predict(
  object,
  newdata,
  group,
  variables = NULL,
  type = c("probabilities", "response"),
  method = c("posterior-mean"),
  ...
)

Arguments

object

An object of class bgmCompare.

newdata

A matrix or data frame with n rows and p columns containing the observed data. Must have the same variables (columns) as the original data used to fit the model.

group

Integer specifying which group's parameters to use for prediction (1 to number of groups). Required argument.

variables

Which variables to predict. Can be:

  • A character vector of variable names

  • An integer vector of column indices

  • NULL (default) to predict all variables

type

Character string specifying the type of prediction:

"probabilities"

Return the full conditional probability distribution for each variable and observation.

"response"

Return the predicted category (mode of the conditional distribution).

method

Character string specifying which parameter estimates to use:

"posterior-mean"

Use posterior mean parameters.

...

Additional arguments (currently ignored).

Value

For type = "probabilities": A named list with one element per predicted variable. Each element is a matrix with n rows and num_categories + 1 columns containing \(P(X_j = c | X_{-j})\) for each observation and category.

For type = "response": A matrix with n rows and length(variables) columns containing predicted categories.

Details

Group-specific parameters are obtained by applying the projection matrix to convert baseline parameters and differences into group-level estimates. The function then computes the conditional distribution of target variables given the observed values of all other variables.

See also

predict.bgms for predicting from single-group models, simulate.bgmCompare for simulating from group-comparison models.

Other prediction: predict.bgms(), simulate.bgmCompare(), simulate.bgms(), simulate_mrf()

Examples

# \donttest{
# Fit a comparison model
x = Boredom[Boredom$language == "fr", 2:6]
y = Boredom[Boredom$language != "fr", 2:6]
fit = bgmCompare(x, y, chains = 2)
#> Chain 1 (Warmup): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 50/2000 (2.5%)
#> Chain 2 (Warmup): ⦗━╺━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 54/2000 (2.7%)
#> Total   (Warmup): ⦗━╺━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 104/4000 (2.6%)
#> Elapsed: 2s | ETA: 1m 14s
#> Chain 1 (Warmup): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 100/2000 (5.0%)
#> Chain 2 (Warmup): ⦗━━━━╺━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 225/2000 (11.2%)
#> Total   (Warmup): ⦗━━━╺━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 325/4000 (8.1%)
#> Elapsed: 4s | ETA: 45s
#> Chain 1 (Warmup): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 200/2000 (10.0%)
#> Chain 2 (Warmup): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 347/2000 (17.3%)
#> Total   (Warmup): ⦗━━━━━╺━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 547/4000 (13.7%)
#> Elapsed: 5s | ETA: 32s
#> Chain 1 (Warmup): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 350/2000 (17.5%)
#> Chain 2 (Warmup): ⦗━━━━━━━━━━╺━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 509/2000 (25.4%)
#> Total   (Warmup): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 859/4000 (21.5%)
#> Elapsed: 6s | ETA: 22s
#> Chain 1 (Warmup): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 500/2000 (25.0%)
#> Chain 2 (Warmup): ⦗━━━━━━━━━━━━━╺━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 661/2000 (33.1%)
#> Total   (Warmup): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 1161/4000 (29.0%)
#> Elapsed: 6s | ETA: 15s
#> Chain 1 (Warmup): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 650/2000 (32.5%)
#> Chain 2 (Warmup): ⦗━━━━━━━━━━━━━━━━╺━━━━━━━━━━━━━━━━━━━━━━━⦘ 814/2000 (40.7%)
#> Total   (Warmup): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 1464/4000 (36.6%)
#> Elapsed: 7s | ETA: 12s
#> Chain 1 (Warmup): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 800/2000 (40.0%)
#> Chain 2 (Warmup): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 898/2000 (44.9%)
#> Total   (Warmup): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 1698/4000 (42.4%)
#> Elapsed: 7s | ETA: 9s
#> Chain 1 (Warmup): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 900/2000 (45.0%)
#> Chain 2 (Warmup): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 991/2000 (49.5%)
#> Total   (Warmup): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 1890/4000 (47.2%)
#> Elapsed: 8s | ETA: 9s
#> Chain 1 (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 1000/2000 (50.0%)
#> Chain 2 (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 1134/2000 (56.7%)
#> Total   (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━╺━━━━━━━━━━━━━━━━━━⦘ 2134/4000 (53.3%)
#> Elapsed: 9s | ETA: 8s
#> Chain 1 (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 1100/2000 (55.0%)
#> Chain 2 (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 1231/2000 (61.6%)
#> Total   (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━╺━━━━━━━━━━━━━━━━⦘ 2331/4000 (58.3%)
#> Elapsed: 9s | ETA: 6s
#> Chain 1 (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 1200/2000 (60.0%)
#> Chain 2 (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 1328/2000 (66.4%)
#> Total   (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━╺━━━━━━━━━━━━━━⦘ 2528/4000 (63.2%)
#> Elapsed: 10s | ETA: 6s
#> Chain 1 (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 1300/2000 (65.0%)
#> Chain 2 (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 1427/2000 (71.4%)
#> Total   (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━╺━━━━━━━━━━━━⦘ 2727/4000 (68.2%)
#> Elapsed: 10s | ETA: 5s
#> Chain 1 (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 1400/2000 (70.0%)
#> Chain 2 (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╺━━━━━━━━━⦘ 1525/2000 (76.2%)
#> Total   (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╺━━━━━━━━━━⦘ 2925/4000 (73.1%)
#> Elapsed: 11s | ETA: 4s
#> Chain 1 (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 1500/2000 (75.0%)
#> Chain 2 (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╺━━━━━━━⦘ 1625/2000 (81.2%)
#> Total   (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╺━━━━━━━━⦘ 3125/4000 (78.1%)
#> Elapsed: 12s | ETA: 3s
#> Chain 1 (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 1600/2000 (80.0%)
#> Chain 2 (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╺━━━━━⦘ 1725/2000 (86.2%)
#> Total   (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╺━━━━━━⦘ 3325/4000 (83.1%)
#> Elapsed: 12s | ETA: 2s
#> Chain 1 (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 1700/2000 (85.0%)
#> Chain 2 (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╺━━━⦘ 1822/2000 (91.1%)
#> Total   (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╺━━━━⦘ 3522/4000 (88.0%)
#> Elapsed: 13s | ETA: 2s
#> Chain 1 (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 1800/2000 (90.0%)
#> Chain 2 (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╺━⦘ 1923/2000 (96.2%)
#> Total   (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╺━━⦘ 3723/4000 (93.1%)
#> Elapsed: 13s | ETA: 1s
#> Chain 1 (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 1900/2000 (95.0%)
#> Chain 2 (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 2000/2000 (100.0%)
#> Total   (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 3900/4000 (97.5%)
#> Elapsed: 14s | ETA: 0s
#> Chain 1 (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 2000/2000 (100.0%)
#> Chain 2 (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 2000/2000 (100.0%)
#> Total   (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 4000/4000 (100.0%)
#> Elapsed: 14s | ETA: 0s
#> Chain 1 (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 2000/2000 (100.0%)
#> Chain 2 (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 2000/2000 (100.0%)
#> Total   (Sampling): ⦗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⦘ 4000/4000 (100.0%)
#> Elapsed: 14s | ETA: 0s

# Predict conditional probabilities using group 1 parameters
probs_g1 = predict(fit, newdata = x[1:10, ], group = 1)

# Predict responses using group 2 parameters
pred_g2 = predict(fit, newdata = y[1:10, ], group = 2, type = "response")
# }