Extracts the prognostic_info
list element from an rctglm_prog
object. See
'Value' at rctglm_with_prognosticscore for more details.
Arguments
- x
an object of class
rctglm_prog
(returned by rctglm_with_prognosticscore)
Value
a list with the structure described of prognostic_info
in the
Value
section of rctglm_with_prognosticscore.
See also
The generic rctglm_with_prognosticscore()
for which this method
works.
Examples
# Generate some data
n <- 100
b0 <- 1
b1 <- 1.5
b2 <- 2
W1 <- runif(n, min = -2, max = 2)
exposure_prob <- .5
dat_treat <- glm_data(
Y ~ b0+b1*abs(sin(W1))+b2*A,
W1 = W1,
A = rbinom(n, 1, exposure_prob)
)
dat_notreat <- glm_data(
Y ~ b0+b1*abs(sin(W1)),
W1 = W1
)
learners <- list(
mars = list(
model = parsnip::set_engine(
parsnip::mars(
mode = "regression", prod_degree = 3
),
"earth"
)
)
)
ate <- rctglm_with_prognosticscore(
formula = Y ~ .,
exposure_indicator = A,
exposure_prob = exposure_prob,
data = dat_treat,
family = gaussian(),
estimand_fun = "ate",
data_hist = dat_notreat,
learners = learners)
#>
#> ── Fitting prognostic model ──
#>
#> ℹ Created formula for fitting prognostic model as: Y ~ .
#> ℹ Fitting learners
#> • mod_mars
#> i No tuning parameters. `fit_resamples()` will be attempted
#> i 1 of 1 resampling: mod_mars
#> ✔ 1 of 1 resampling: mod_mars (128ms)
#> ℹ Model with lowest RMSE: mod_mars
#> ℹ Investigate trained learners and fitted model in `prognostic_info` list element
#>
#> ── Symbolic differentiation of estimand function ──
#>
#> ℹ Symbolically deriving partial derivative of the function 'psi1 - psi0' with respect to 'psi0' as: '-1'.
#> • Alternatively, specify the derivative through the argument
#> `estimand_fun_deriv0`
#> ℹ Symbolically deriving partial derivative of the function 'psi1 - psi0' with respect to 'psi1' as: '1'.
#> • Alternatively, specify the derivative through the argument
#> `estimand_fun_deriv1`
prog(ate)
#> $formula
#> Y ~ .
#> <environment: 0x559defd19040>
#>
#> $model_fit
#> ══ Workflow [trained] ══════════════════════════════════════════════════════════
#> Preprocessor: Formula
#> Model: mars()
#>
#> ── Preprocessor ────────────────────────────────────────────────────────────────
#> Y ~ .
#>
#> ── Model ───────────────────────────────────────────────────────────────────────
#> Selected 3 of 7 terms, and 1 of 1 predictors
#> Termination condition: RSq changed by less than 0.001 at 7 terms
#> Importance: W1
#> Number of terms at each degree of interaction: 1 2 (additive model)
#> GCV 0.9169908 RSS 81.02531 GRSq 0.07979358 RSq 0.1703965
#>
#> $learners
#> $learners$mars
#> $learners$mars$model
#> MARS Model Specification (regression)
#>
#> Main Arguments:
#> prod_degree = 3
#>
#> Computational engine: earth
#>
#>
#>
#>
#> $cv_folds
#> [1] 5
#>
#> $data
#> Y W1
#> 1 2.72131967 1.384982192
#> 2 1.96536934 1.193408270
#> 3 0.28597650 -1.369564363
#> 4 1.52027982 -0.443691538
#> 5 1.56707286 -0.187557026
#> 6 1.99316477 -1.142904804
#> 7 3.65908575 0.759210528
#> 8 1.31386678 0.002638961
#> 9 0.81196794 1.980248458
#> 10 1.26812618 -1.529962860
#> 11 1.06862939 1.857370362
#> 12 1.91084450 0.565919823
#> 13 2.10114176 -1.564187960
#> 14 1.75812226 -0.834586513
#> 15 1.38984169 -0.103746382
#> 16 4.05054962 1.023317943
#> 17 2.95210537 -1.483048798
#> 18 2.28907930 -0.097032987
#> 19 1.07991083 1.181269797
#> 20 1.55647248 -1.534684835
#> 21 2.07366418 0.893202768
#> 22 0.15454935 -0.190888042
#> 23 0.79115571 -0.981938925
#> 24 0.59658917 -1.042243558
#> 25 -0.09781132 0.095488627
#> 26 1.40642497 -1.788098332
#> 27 1.72804520 -1.417561601
#> 28 1.44827133 0.759996420
#> 29 3.02302248 1.353978418
#> 30 2.47968123 1.612627343
#> 31 2.32637267 -1.646279992
#> 32 3.76014950 -1.787805090
#> 33 1.06753206 -1.478330033
#> 34 4.25406830 -1.577669651
#> 35 -0.58200448 0.363677772
#> 36 3.47921389 1.772761269
#> 37 2.72956722 -1.388085473
#> 38 2.12239233 1.579245754
#> 39 2.86090478 -1.446541916
#> 40 0.02582534 -0.331721296
#> 41 3.39992264 -1.641866679
#> 42 1.65839378 -0.954397969
#> 43 1.51910524 -0.561635143
#> 44 3.03131420 0.620070576
#> 45 2.37780501 -1.582823326
#> 46 1.89846981 1.640790832
#> 47 1.91595912 -1.505982758
#> 48 1.20912163 -0.059998618
#> 49 1.79745562 -0.302318255
#> 50 1.95474197 0.826663015
#> 51 2.49580175 -0.771183933
#> 52 2.18475463 1.836358662
#> 53 2.65592965 -0.722274201
#> 54 3.71480819 -0.508814248
#> 55 1.87943689 1.367007247
#> 56 2.37425858 -0.690988204
#> 57 2.78085001 1.594292774
#> 58 -0.09784400 0.645300754
#> 59 2.60088513 0.924540984
#> 60 3.86364762 -1.609956257
#> 61 2.87412768 -0.699418604
#> 62 1.63140152 1.010322550
#> 63 1.87219306 0.797926514
#> 64 2.12459863 0.761499645
#> 65 2.87909681 0.552423899
#> 66 1.60015317 1.700073148
#> 67 2.90624178 0.356230548
#> 68 2.74988455 1.545411798
#> 69 1.98788870 1.798755240
#> 70 2.10797146 0.377036167
#> 71 2.57142560 -1.211364707
#> 72 1.42425606 -0.469872492
#> 73 3.00885879 -1.856295628
#> 74 1.78750964 1.667663256
#> 75 1.56814662 -0.538129904
#> 76 0.90807385 -1.032231587
#> 77 3.83350260 -1.934395369
#> 78 3.06762363 1.874492300
#> 79 1.73673745 -0.213957776
#> 80 2.77273994 1.857513856
#> 81 2.52606720 -0.419701044
#> 82 1.84679252 -1.649829350
#> 83 1.14039857 0.503861475
#> 84 2.82844152 -0.494098693
#> 85 1.85712427 0.809858762
#> 86 1.84675947 -1.383845829
#> 87 3.12141511 -0.023786677
#> 88 1.94054367 -0.919254839
#> 89 3.75327233 1.394406566
#> 90 1.24555988 -0.454942441
#> 91 3.01590511 -1.840850134
#> 92 2.91345858 1.736370123
#> 93 3.03651709 -1.526609730
#> 94 1.34966077 0.573839966
#> 95 3.71272288 -1.616502794
#> 96 1.70989426 -0.031969011
#> 97 1.14458593 -0.794610540
#> 98 1.68390987 -1.345750707
#> 99 3.38403512 -1.398603517
#> 100 3.27314061 -1.677519421
#>