This function generates random values from the expression of
y, and keeps all the right hand side information in a data frame.
Arguments
- n
Integer. Number of observations.
- fit_model
Boolean. Whether or not to fit a null model to obtain the fitted values and the residuals. Default is
TRUE.- test
Boolean. Whether or not to test the null model against the alternative model to obtain the test statistic and the p-value. Default is
FALSE.- computed
List. Default is
NULL. If it is provided, random variables or random closed form expression will use the values from the list, which makes the expression potentially deterministic.
Examples
# Instantiate
x <- rand_uniform()
e <- rand_normal()
test <- vi_model(prm = list(x = x, e = e),
prm_type = list(x = "r", e = "r"),
formula = y ~ 1 + x + x^2 + e,
null_formula = y ~ x,
alt_formula = y ~ x + I(x^2))
dat <- test$gen(10)
dat
#> y x e .resid .fitted
#> 1 2.181303 0.34361211 0.7196220 0.04673363 2.134570
#> 2 2.709697 0.50525009 0.9491690 0.63606571 2.073631
#> 3 3.336069 0.54693797 1.4899895 1.27815418 2.057914
#> 4 2.682229 0.31685982 1.2649687 0.53757303 2.144656
#> 5 2.316093 0.67233648 0.1917197 0.30545430 2.010638
#> 6 0.352242 0.36084107 -1.1388054 -1.77583238 2.128074
#> 7 1.124684 0.42776140 -0.4860573 -0.97816100 2.102845
#> 8 1.391063 0.54282316 -0.4464167 -0.66840227 2.059466
#> 9 2.890814 0.02153749 1.8688128 0.63481978 2.255994
#> 10 2.159453 0.23409623 0.8705559 -0.01640497 2.175858
test$gen(10, computed = list(e = dat$e))
#> y e x .resid .fitted
#> 1 1.8513290 0.7196220 0.11782441 0.67867725 1.1726518
#> 2 2.6769460 0.9491690 0.48882608 0.25067664 2.4262694
#> 3 3.4897471 1.4899895 0.61792557 0.62724944 2.8624976
#> 4 3.4519712 1.2649687 0.69875040 0.31636582 3.1356054
#> 5 1.2983932 0.1917197 0.09722147 0.19535891 1.1030343
#> 6 0.1578863 -1.1388054 0.23938600 -1.42552308 1.5834094
#> 7 0.5492292 -0.4860573 0.03412225 -0.34059226 0.8898215
#> 8 1.8720756 -0.4464167 0.75239464 -1.44479406 3.3168697
#> 9 3.6836295 1.8688128 0.53189955 1.11181445 2.5718150
#> 10 2.8265758 0.8705559 0.59818938 0.03076689 2.7958089
test$gen(10, test = TRUE)
#> y x e .resid .fitted test_name statistic
#> 1 1.0953586 0.3539549 -0.38388032 -0.50698122 1.602340 F-test 0.6208182
#> 2 1.3896059 0.5508355 -0.46464934 -0.18939569 1.579002 F-test 0.6208182
#> 3 1.5968128 0.7216158 -0.64553227 0.03805569 1.558757 F-test 0.6208182
#> 4 -0.6144918 0.3004186 -2.00516171 -2.22317787 1.608686 F-test 0.6208182
#> 5 2.3348543 0.5050097 0.57480978 0.75042050 1.584434 F-test 0.6208182
#> 6 2.0964468 0.6854306 -0.05879878 0.53340026 1.563047 F-test 0.6208182
#> 7 1.7458138 0.5190429 -0.04263452 0.16304358 1.582770 F-test 0.6208182
#> 8 1.3239188 0.8703345 -1.30389782 -0.21720916 1.541128 F-test 0.6208182
#> 9 1.7273424 0.7745808 -0.64721396 0.17486373 1.552479 F-test 0.6208182
#> 10 3.1093524 0.1006041 1.99862713 1.47698016 1.632372 F-test 0.6208182
#> p_value
#> 1 0.4565906
#> 2 0.4565906
#> 3 0.4565906
#> 4 0.4565906
#> 5 0.4565906
#> 6 0.4565906
#> 7 0.4565906
#> 8 0.4565906
#> 9 0.4565906
#> 10 0.4565906