Generate model predictions against a specified set of explanatory levels with bootstrapped confidence intervals.
Arguments
- fit
An object of class lm or glm
- newdata
A data.frame
- R
Number of simulations. Note default R=100 is very low.
- type
he type of prediction required, see predict.glm. The default for glm models is on the scale of the response variable. Thus for a binomial model the default predictions are predicted probabilities.
- ...
Further arguments to be passed to boot::boot
Examples
data(GBSG2,package="TH.data")
fit=glm(cens~horTh+pnodes,data=GBSG2,family="binomial")
newdata=expand.grid(horTh=factor(c(1,2),labels=c("no","yes")),pnodes=1:51)
bootPredict(fit,newdata)
#> horTh pnodes estimate lower upper
#> 1 no 1 0.3671628 0.3126764 0.4269445
#> 2 yes 1 0.2814584 0.2252174 0.3593819
#> 3 no 2 0.3927672 0.3417797 0.4458494
#> 4 yes 2 0.3039568 0.2480698 0.3771263
#> 5 no 3 0.4189750 0.3706082 0.4681277
#> 6 yes 3 0.3274340 0.2703583 0.3949465
#> 7 no 4 0.4456481 0.3993581 0.4907026
#> 8 yes 4 0.3518080 0.2905775 0.4146516
#> 9 no 5 0.4726379 0.4244542 0.5222734
#> 10 yes 5 0.3769795 0.3053335 0.4371384
#> 11 no 6 0.4997887 0.4480589 0.5553061
#> 12 yes 6 0.4028326 0.3189937 0.4657147
#> 13 no 7 0.5269407 0.4676993 0.5859942
#> 14 yes 7 0.4292372 0.3375572 0.4982285
#> 15 no 8 0.5539343 0.4857528 0.6182272
#> 16 yes 8 0.4560509 0.3570262 0.5259330
#> 17 no 9 0.5806134 0.5042088 0.6520915
#> 18 yes 9 0.4831217 0.3769850 0.5529038
#> 19 no 10 0.6068295 0.5257039 0.6841504
#> 20 yes 10 0.5102919 0.3973717 0.5804500
#> 21 no 11 0.6324443 0.5445426 0.7147166
#> 22 yes 11 0.5374015 0.4181180 0.6134194
#> 23 no 12 0.6573325 0.5578985 0.7434084
#> 24 yes 12 0.5642918 0.4391504 0.6482779
#> 25 no 13 0.6813846 0.5756382 0.7699533
#> 26 yes 13 0.5908091 0.4603911 0.6836304
#> 27 no 14 0.7045073 0.5932151 0.7945091
#> 28 yes 14 0.6168084 0.4817593 0.7180994
#> 29 no 15 0.7266252 0.6105566 0.8170642
#> 30 yes 15 0.6421564 0.4993408 0.7501853
#> 31 no 16 0.7476805 0.6276229 0.8389630
#> 32 yes 16 0.6667336 0.5161004 0.7797393
#> 33 no 17 0.7676327 0.6443769 0.8590624
#> 34 yes 17 0.6904365 0.5328297 0.8066977
#> 35 no 18 0.7864578 0.6600467 0.8769103
#> 36 yes 18 0.7131789 0.5494911 0.8310405
#> 37 no 19 0.8041469 0.6739743 0.8926994
#> 38 yes 19 0.7348919 0.5660472 0.8528523
#> 39 no 20 0.8207047 0.6876013 0.9066754
#> 40 yes 20 0.7555247 0.5824617 0.8722809
#> 41 no 21 0.8361480 0.7009224 0.9189932
#> 42 yes 21 0.7750433 0.5986996 0.8894765
#> 43 no 22 0.8505034 0.7139426 0.9298081
#> 44 yes 22 0.7934296 0.6147274 0.9046099
#> 45 no 23 0.8638059 0.7266170 0.9392721
#> 46 yes 23 0.8106802 0.6305131 0.9173253
#> 47 no 24 0.8760972 0.7389351 0.9475297
#> 48 yes 24 0.8268046 0.6460271 0.9283603
#> 49 no 25 0.8874238 0.7508885 0.9547167
#> 50 yes 25 0.8418238 0.6612418 0.9380151
#> 51 no 26 0.8978357 0.7624703 0.9609580
#> 52 yes 26 0.8557676 0.6761321 0.9464416
#> 53 no 27 0.9073851 0.7736759 0.9663679
#> 54 yes 27 0.8686741 0.6906752 0.9537772
#> 55 no 28 0.9161253 0.7845023 0.9710495
#> 56 yes 28 0.8805867 0.7048511 0.9601486
#> 57 no 29 0.9241097 0.7949479 0.9750950
#> 58 yes 29 0.8915537 0.7186424 0.9656720
#> 59 no 30 0.9313909 0.8050129 0.9785868
#> 60 yes 30 0.9016260 0.7320344 0.9704520
#> 61 no 31 0.9380204 0.8146990 0.9815974
#> 62 yes 31 0.9108563 0.7450148 0.9745829
#> 63 no 32 0.9440478 0.8240091 0.9841909
#> 64 yes 32 0.9192981 0.7575741 0.9781482
#> 65 no 33 0.9495206 0.8329472 0.9864233
#> 66 yes 33 0.9270045 0.7697052 0.9812223
#> 67 no 34 0.9544839 0.8415186 0.9883437
#> 68 yes 34 0.9340278 0.7814034 0.9838703
#> 69 no 35 0.9589802 0.8497295 0.9899948
#> 70 yes 35 0.9404188 0.7926663 0.9861496
#> 71 no 36 0.9630496 0.8575868 0.9914137
#> 72 yes 36 0.9462263 0.8034934 0.9881101
#> 73 no 37 0.9667293 0.8650985 0.9926326
#> 74 yes 37 0.9514970 0.8139206 0.9897956
#> 75 no 38 0.9700539 0.8722730 0.9936792
#> 76 yes 38 0.9562749 0.8240434 0.9912438
#> 77 no 39 0.9730556 0.8791191 0.9945778
#> 78 yes 39 0.9606016 0.8337263 0.9924878
#> 79 no 40 0.9757639 0.8856463 0.9953490
#> 80 yes 40 0.9645161 0.8429762 0.9935559
#> 81 no 41 0.9782061 0.8918643 0.9960108
#> 82 yes 41 0.9680546 0.8518013 0.9944727
#> 83 no 42 0.9804072 0.8977832 0.9965786
#> 84 yes 42 0.9712507 0.8602109 0.9952596
#> 85 no 43 0.9823899 0.9034132 0.9970657
#> 86 yes 43 0.9741357 0.8682154 0.9959347
#> 87 no 44 0.9841753 0.9087645 0.9974836
#> 88 yes 44 0.9767380 0.8758260 0.9965138
#> 89 no 45 0.9857822 0.9138475 0.9978419
#> 90 yes 45 0.9790842 0.8829960 0.9970106
#> 91 no 46 0.9872281 0.9186727 0.9981493
#> 92 yes 46 0.9811982 0.8893224 0.9974366
#> 93 no 47 0.9885287 0.9232503 0.9984129
#> 94 yes 47 0.9831023 0.8953473 0.9978020
#> 95 no 48 0.9896982 0.9275904 0.9986389
#> 96 yes 48 0.9848165 0.9010807 0.9981153
#> 97 no 49 0.9907496 0.9317033 0.9988328
#> 98 yes 49 0.9863593 0.9065329 0.9983840
#> 99 no 50 0.9916946 0.9355987 0.9989990
#> 100 yes 50 0.9877472 0.9117140 0.9986143
#> 101 no 51 0.9925437 0.9392864 0.9991415
#> 102 yes 51 0.9889955 0.9166343 0.9988118
library(survival)
fit=coxph(Surv(time,cens)~age+horTh+progrec+pnodes,data=GBSG2)