Two-stage residual inclusion estimation(R语言例子)_科研之家网

http://blog.sina.com.cn/u/1706201501

首页博文目录关于我

个人资料

微博

加好友发纸条

写留言加关注

博客等级：
博客积分：

博客访问：
关注人气：
获赠金笔：0支
赠出金笔：0支
荣誉徽章：

正文字体大小：大中小

Two-stage residual inclusion estimation(R语言例子)

(2013-05-29 19:26:16)

分类： 04STATA数据处理

# lets see if region is a reasonable IV

setwd("/Users/leopekelis/Desktop/13_youssef_mac")

code.data <- read.csv("seer minor salivary gland 1988-2008 - staged and coded v1.1 - Coded Data.csv")

bkgd.data <- read.csv("seer minor salivary gland 1988-2008 - staged and coded v1.1 - Background Data.csv")

loc.data <- read.csv("seer minor salivary gland 1988-2008 - staged and coded v1.1 - Registry ID.csv")

seer.data = merge(merge(code.data, bkgd.data, by = "Patient.ID"),

loc.data, by = "Patient.ID")

covs = c("Age.at.diagnosis", "Sex", "Race", "Year.of.diagnosis",

"Tumor.location", "T", "N", "Grade", "Histology", "Surgery")

RT.unknown = which(seer.data$Radiation.sequence.with.surgery == 7) #remove these

seer.data = seer.data[-RT.unknown, ]

seer.data$Adj.RT = seer.data$Radiation.sequence.with.surgery %in%

c(1, 3)

factor.idx = c(3, 4, 6, 7, 8, 10, 11, 28)

for (i in factor.idx) {

seer.data[, i] = as.factor(seer.data[, i])

}

form = as.formula(paste("Adj.RT ~ Registry.ID + ", paste(covs, collapse = "+")))

# combine some locations

temp = seer.data$Registry.ID

levels(temp) <- c("Alaska/Hawaii - 1973+", levels(temp)[2:6], "Alaska/Hawaii - 1973+",

levels(temp)[8], "Kentucky / Rural Georgia - 1992+", levels(temp)[10:13],

"Kentucky / Rural Georgia - 1992+", "California SF/SJM/LA - 1973+", "California SF/SJM/LA - 1973+",

levels(temp)[17:18])

temp = factor(levels(temp)[as.numeric(temp)], levels = c(levels(temp)[3],

levels(temp)[-3]))

seer.data$Registry.ID = temp

adj.rt.vec = NULL

for (i in levels(seer.data$Registry.ID)) {

Adj.RT.temp = seer.data$Adj.RT[seer.data$Registry.ID == i]

adj.rt.vec[i] = sum(Adj.RT.temp)/length(Adj.RT.temp)

}

IV.data = cbind(round(adj.rt.vec, 2), round(table(seer.data$Registry.ID)/dim(seer.data)[1],

2))

colnames(IV.data) = c("Adj.RT.Percent", "Percent.Obs")

print(IV.data) #lets get an overview of locations

## Adj.RT.Percent Percent.Obs

## California excluding SF/SJM/LA - 2000+ 0.22 0.15

## Alaska/Hawaii - 1973+ 0.19 0.02

## Atlanta (Metropolitan) - 1975+ 0.31 0.05

## Connecticut - 1973+ 0.23 0.06

## Detroit (Metropolitan) - 1973+ 0.25 0.10

## Greater Georgia - 2000+ 0.32 0.04

## Iowa - 1973+ 0.23 0.06

## Kentucky / Rural Georgia - 1992+ 0.28 0.04

## Los Angeles - 1992+ 0.23 0.14

## Louisiana - 2000+ 0.33 0.03

## New Jersey - 2000+ 0.28 0.05

## New Mexico - 1973+ 0.21 0.03

## California SF/SJM/LA - 1973+ 0.30 0.13

## Seattle (Puget Sound) - 1974+ 0.22 0.08

## Utah - 1973+ 0.16 0.03

IV.glm = glm(form, data = seer.data, family = binomial)

summary(IV.glm)

## Call:

## glm(formula = form, family = binomial, data = seer.data)

## Deviance Residuals:

## Min 1Q Median 3Q Max

## -2.846 -0.542 -0.343 0.248 2.595

## Coefficients:

## Estimate Std. Error z value

## (Intercept) -4.65e+01 3.99e+02 -0.12

## Registry.IDAlaska/Hawaii - 1973+ -5.15e-01 5.70e-01 -0.90

## Registry.IDAtlanta (Metropolitan) - 1975+ 6.81e-01 3.43e-01 1.98

## Registry.IDConnecticut - 1973+ 1.61e-01 3.29e-01 0.49

## Registry.IDDetroit (Metropolitan) - 1973+ 3.37e-01 2.83e-01 1.19

## Registry.IDGreater Georgia - 2000+ 6.73e-01 3.51e-01 1.92

## Registry.IDIowa - 1973+ 1.11e-01 3.31e-01 0.33

## Registry.IDKentucky / Rural Georgia - 1992+ 4.71e-01 3.74e-01 1.26

## Registry.IDLos Angeles - 1992+ -8.03e-02 2.57e-01 -0.31

## Registry.IDLouisiana - 2000+ 3.00e-01 3.85e-01 0.78

## Registry.IDNew Jersey - 2000+ 1.38e-01 3.25e-01 0.42

## Registry.IDNew Mexico - 1973+ 1.69e-01 4.57e-01 0.37

## Registry.IDCalifornia SF/SJM/LA - 1973+ 6.00e-01 2.55e-01 2.36

## Registry.IDSeattle (Puget Sound) - 1974+ 3.09e-01 3.01e-01 1.03

## Registry.IDUtah - 1973+ -8.82e-01 5.13e-01 -1.72

## Age.at.diagnosis -2.61e-04 3.99e-03 -0.07

## Sex2 1.58e-01 1.32e-01 1.19

## Race2 1.53e-01 3.13e-01 0.49

## Race3 4.73e-03 2.04e-01 0.02

## Race4 -5.03e-02 6.28e-01 -0.08

## Year.of.diagnosis 1.32e-02 2.29e-02 0.58

## Tumor.location2 -7.77e-01 2.68e-01 -2.90

## Tumor.location3 3.57e-01 7.45e-01 0.48

## Tumor.location4 -2.41e-01 4.63e-01 -0.52

## Tumor.location5 -1.34e+00 4.84e-01 -2.76

## Tumor.location6 1.27e-02 4.97e-01 0.03

## Tumor.location7 1.70e-01 3.17e-01 0.53

## Tumor.location8 -1.88e-01 7.61e-01 -0.25

## Tumor.location9 8.66e-02 3.23e-01 0.27

## Tumor.location10 4.83e-01 5.40e-01 0.90

## T2 2.74e-01 1.88e-01 1.46

## T3 1.09e+00 2.43e-01 4.47

## T4 1.18e+00 1.92e-01 6.13

## T5 -4.16e-01 2.32e-01 -1.79

## N2 1.14e+00 3.74e-01 3.05

## N3 1.11e+00 2.64e-01 4.20

## N4 8.20e-02 7.78e-01 0.11

## N5 -4.41e-01 1.97e-01 -2.24

## Grade 6.87e-01 8.33e-02 8.24

## Histology2 -1.81e+00 9.57e-01 -1.89

## Histology3 -6.12e-01 9.63e-01 -0.63

## Histology4 -2.32e+00 9.55e-01 -2.43

## Histology5 -1.87e+01 2.24e+03 -0.01

## Histology6 -8.94e-01 1.62e+00 -0.55

## Histology7 1.28e+00 6.53e+03 0.00

## Histology8 -1.95e+01 4.55e+03 0.00

## Histology9 -1.51e+00 1.07e+00 -1.41

## Histology10 -1.60e+00 1.07e+00 -1.50

## Histology11 -1.81e+00 1.00e+00 -1.81

## Surgery2 1.93e+01 3.97e+02 0.05

## Surgery3 1.93e+01 3.97e+02 0.05

## Surgery4 1.90e+01 3.97e+02 0.05

## Surgery5 1.90e+01 3.97e+02 0.05

## Surgery6 1.96e+01 3.97e+02 0.05

## Surgery7 1.92e+01 3.97e+02 0.05

## Surgery8 2.01e+01 3.97e+02 0.05

## Pr(>|z|)

## (Intercept) 0.9073

## Registry.IDAlaska/Hawaii - 1973+ 0.3667

## Registry.IDAtlanta (Metropolitan) - 1975+ 0.0473 *

## Registry.IDConnecticut - 1973+ 0.6251

## Registry.IDDetroit (Metropolitan) - 1973+ 0.2342

## Registry.IDGreater Georgia - 2000+ 0.0550 .

## Registry.IDIowa - 1973+ 0.7380

## Registry.IDKentucky / Rural Georgia - 1992+ 0.2085

## Registry.IDLos Angeles - 1992+ 0.7546

## Registry.IDLouisiana - 2000+ 0.4368

## Registry.IDNew Jersey - 2000+ 0.6715

## Registry.IDNew Mexico - 1973+ 0.7119

## Registry.IDCalifornia SF/SJM/LA - 1973+ 0.0185 *

## Registry.IDSeattle (Puget Sound) - 1974+ 0.3043

## Registry.IDUtah - 1973+ 0.0856 .

## Age.at.diagnosis 0.9478

## Sex2 0.2329

## Race2 0.6253

## Race3 0.9815

## Race4 0.9362

## Year.of.diagnosis 0.5624

## Tumor.location2 0.0037 **

## Tumor.location3 0.6312

## Tumor.location4 0.6021

## Tumor.location5 0.0057 **

## Tumor.location6 0.9796

## Tumor.location7 0.5927

## Tumor.location8 0.8043

## Tumor.location9 0.7889

## Tumor.location10 0.3706

## T2 0.1448

## T3 7.7e-06 ***

## T4 8.7e-10 ***

## T5 0.0736 .

## N2 0.0023 **

## N3 2.7e-05 ***

## N4 0.9161

## N5 0.0252 *

## Grade < 2e-16 ***

## Histology2 0.0588 .

## Histology3 0.5255

## Histology4 0.0150 *

## Histology5 0.9933

## Histology6 0.5807

## Histology7 0.9998

## Histology8 0.9966

## Histology9 0.1578

## Histology10 0.1341

## Histology11 0.0704 .

## Surgery2 0.9611

## Surgery3 0.9611

## Surgery4 0.9618

## Surgery5 0.9618

## Surgery6 0.9607

## Surgery7 0.9615

## Surgery8 0.9596

## ---

## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

## (Dispersion parameter for binomial family taken to be 1)

## Null deviance: 2389.7 on 2117 degrees of freedom

## Residual deviance: 1564.6 on 2062 degrees of freedom

## AIC: 1677

## Number of Fisher Scoring iterations: 17

The IV - Geographic Region

Relevance?

not completely insignificant

No unmeasured confounders?

Exclusion restriction

can we check this?

The IV - Geographic Region

# check for exclusion restriction by running cox model

library(survival)

## Loading required package: splines

names(seer.data)[14] = "Survival.Time"

form.ph = as.formula(paste("Surv(Survival.Time,as.numeric(Vital.status.recode)) ~ Adj.RT + Registry.ID + ",

paste(covs, collapse = "+")))

ex.ph = coxph(form.ph, data = seer.data)

## Warning: Loglik converged before variable 43,44,45 ; beta may be infinite.

summary(ex.ph)

## Call:

## coxph(formula = form.ph, data = seer.data)

## n= 2118, number of events= 576

## coef exp(coef) se(coef)

## Adj.RTTRUE -1.70e-01 8.44e-01 1.15e-01

## Registry.IDAlaska/Hawaii - 1973+ 5.66e-01 1.76e+00 3.53e-01

## Registry.IDAtlanta (Metropolitan) - 1975+ 4.39e-03 1.00e+00 2.37e-01

## Registry.IDConnecticut - 1973+ -3.00e-01 7.41e-01 2.19e-01

## Registry.IDDetroit (Metropolitan) - 1973+ -9.78e-02 9.07e-01 1.87e-01

## Registry.IDGreater Georgia - 2000+ -2.37e-02 9.77e-01 2.43e-01

## Registry.IDIowa - 1973+ -1.65e-01 8.48e-01 2.13e-01

## Registry.IDKentucky / Rural Georgia - 1992+ -3.85e-01 6.81e-01 2.99e-01

## Registry.IDLos Angeles - 1992+ -8.54e-02 9.18e-01 1.78e-01

## Registry.IDLouisiana - 2000+ 5.39e-02 1.06e+00 2.64e-01

## Registry.IDNew Jersey - 2000+ 6.41e-02 1.07e+00 2.37e-01

## Registry.IDNew Mexico - 1973+ 1.05e-01 1.11e+00 3.06e-01

## Registry.IDCalifornia SF/SJM/LA - 1973+ -1.50e-01 8.61e-01 1.82e-01

## Registry.IDSeattle (Puget Sound) - 1974+ 4.47e-02 1.05e+00 2.05e-01

## Registry.IDUtah - 1973+ -6.31e-01 5.32e-01 2.98e-01

## Age.at.diagnosis 5.75e-02 1.06e+00 3.48e-03

## Sex2 3.16e-01 1.37e+00 9.03e-02

## Race2 -5.84e-01 5.58e-01 2.38e-01

## Race3 -1.73e-01 8.41e-01 1.35e-01

## Race4 -1.52e+00 2.19e-01 1.01e+00

## Year.of.diagnosis -3.00e-02 9.70e-01 1.70e-02

## Tumor.location2 -3.25e-01 7.23e-01 1.96e-01

## Tumor.location3 1.66e-02 1.02e+00 3.26e-01

## Tumor.location4 -2.91e-01 7.47e-01 2.65e-01

## Tumor.location5 -2.40e-01 7.86e-01 2.91e-01

## Tumor.location6 -5.44e-02 9.47e-01 3.13e-01

## Tumor.location7 3.38e-01 1.40e+00 2.17e-01

## Tumor.location8 2.92e-01 1.34e+00 3.87e-01

## Tumor.location9 -5.50e-02 9.46e-01 2.30e-01

## Tumor.location10 -2.30e-01 7.94e-01 3.50e-01

## T2 2.13e-01 1.24e+00 1.42e-01

## T3 6.51e-01 1.92e+00 1.59e-01

## T4 6.40e-01 1.90e+00 1.29e-01

## T5 5.83e-02 1.06e+00 1.52e-01

## N2 2.46e-01 1.28e+00 2.13e-01

## N3 8.43e-01 2.32e+00 1.47e-01

## N4 1.64e+00 5.15e+00 3.98e-01

## N5 6.52e-02 1.07e+00 1.15e-01

## Grade 4.97e-01 1.64e+00 5.51e-02

## Histology2 -3.94e-01 6.74e-01 6.01e-01

## Histology3 -2.87e-01 7.51e-01 6.08e-01

## Histology4 -6.85e-01 5.04e-01 6.00e-01

## Histology5 -1.50e+01 3.11e-07 1.14e+03

## Histology6 -1.48e+01 3.69e-07 3.37e+03

## Histology7 -1.68e+01 5.06e-08 6.88e+03

## Histology8 -3.78e-01 6.85e-01 1.18e+00

## Histology9 -3.59e-01 6.98e-01 6.55e-01

## Histology10 -9.10e-01 4.03e-01 8.43e-01

## Histology11 3.31e-01 1.39e+00 6.17e-01

## Surgery2 -5.23e-01 5.93e-01 1.91e-01

## Surgery3 -4.41e-01 6.43e-01 2.90e-01

## Surgery4 -4.77e-01 6.21e-01 2.16e-01

## Surgery5 2.70e-01 1.31e+00 2.74e-01

## Surgery6 -1.13e-01 8.93e-01 1.82e-01

## Surgery7 -4.53e-01 6.36e-01 2.21e-01

## Surgery8 -1.03e+00 3.56e-01 7.30e-01

## z Pr(>|z|)

## Adj.RTTRUE -1.48 0.13891

## Registry.IDAlaska/Hawaii - 1973+ 1.60 0.10900

## Registry.IDAtlanta (Metropolitan) - 1975+ 0.02 0.98523

## Registry.IDConnecticut - 1973+ -1.37 0.17063

## Registry.IDDetroit (Metropolitan) - 1973+ -0.52 0.60067

## Registry.IDGreater Georgia - 2000+ -0.10 0.92215

## Registry.IDIowa - 1973+ -0.78 0.43809

## Registry.IDKentucky / Rural Georgia - 1992+ -1.29 0.19810

## Registry.IDLos Angeles - 1992+ -0.48 0.63161

## Registry.IDLouisiana - 2000+ 0.20 0.83821

## Registry.IDNew Jersey - 2000+ 0.27 0.78732

## Registry.IDNew Mexico - 1973+ 0.34 0.73073

## Registry.IDCalifornia SF/SJM/LA - 1973+ -0.82 0.41079

## Registry.IDSeattle (Puget Sound) - 1974+ 0.22 0.82751

## Registry.IDUtah - 1973+ -2.12 0.03394 *

## Age.at.diagnosis 16.50 < 2e-16 ***

## Sex2 3.50 0.00047 ***

## Race2 -2.45 0.01421 *

## Race3 -1.28 0.20132

## Race4 -1.50 0.13392

## Year.of.diagnosis -1.76 0.07762 .

## Tumor.location2 -1.65 0.09806 .

## Tumor.location3 0.05 0.95945

## Tumor.location4 -1.10 0.27199

## Tumor.location5 -0.82 0.40941

## Tumor.location6 -0.17 0.86208

## Tumor.location7 1.56 0.11811

## Tumor.location8 0.75 0.45067

## Tumor.location9 -0.24 0.81105

## Tumor.location10 -0.66 0.51094

## T2 1.51 0.13169

## T3 4.10 4.2e-05 ***

## T4 4.97 6.7e-07 ***

## T5 0.38 0.70126

## N2 1.16 0.24747

## N3 5.71 1.1e-08 ***

## N4 4.12 3.8e-05 ***

## N5 0.57 0.57101

## Grade 9.03 < 2e-16 ***

## Histology2 -0.66 0.51184

## Histology3 -0.47 0.63718

## Histology4 -1.14 0.25358

## Histology5 -0.01 0.98953

## Histology6 0.00 0.99649

## Histology7 0.00 0.99805

## Histology8 -0.32 0.74849

## Histology9 -0.55 0.58341

## Histology10 -1.08 0.28067

## Histology11 0.54 0.59084

## Surgery2 -2.74 0.00622 **

## Surgery3 -1.52 0.12859

## Surgery4 -2.21 0.02718 *

## Surgery5 0.98 0.32501

## Surgery6 -0.62 0.53421

## Surgery7 -2.05 0.04049 *

## Surgery8 -1.42 0.15682

## ---

## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

## exp(coef) exp(-coef) lower .95

## Adj.RTTRUE 8.44e-01 1.18e+00 0.6741

## Registry.IDAlaska/Hawaii - 1973+ 1.76e+00 5.68e-01 0.8815

## Registry.IDAtlanta (Metropolitan) - 1975+ 1.00e+00 9.96e-01 0.6312

## Registry.IDConnecticut - 1973+ 7.41e-01 1.35e+00 0.4828

## Registry.IDDetroit (Metropolitan) - 1973+ 9.07e-01 1.10e+00 0.6287

## Registry.IDGreater Georgia - 2000+ 9.77e-01 1.02e+00 0.6066

## Registry.IDIowa - 1973+ 8.48e-01 1.18e+00 0.5585

## Registry.IDKentucky / Rural Georgia - 1992+ 6.81e-01 1.47e+00 0.3788

## Registry.IDLos Angeles - 1992+ 9.18e-01 1.09e+00 0.6476

## Registry.IDLouisiana - 2000+ 1.06e+00 9.47e-01 0.6288

## Registry.IDNew Jersey - 2000+ 1.07e+00 9.38e-01 0.6695

## Registry.IDNew Mexico - 1973+ 1.11e+00 9.00e-01 0.6103

## Registry.IDCalifornia SF/SJM/LA - 1973+ 8.61e-01 1.16e+00 0.6026

## Registry.IDSeattle (Puget Sound) - 1974+ 1.05e+00 9.56e-01 0.6995

## Registry.IDUtah - 1973+ 5.32e-01 1.88e+00 0.2969

## Age.at.diagnosis 1.06e+00 9.44e-01 1.0520

## Sex2 1.37e+00 7.29e-01 1.1488

## Race2 5.58e-01 1.79e+00 0.3498

## Race3 8.41e-01 1.19e+00 0.6452

## Race4 2.19e-01 4.57e+00 0.0300

## Year.of.diagnosis 9.70e-01 1.03e+00 0.9387

## Tumor.location2 7.23e-01 1.38e+00 0.4920

## Tumor.location3 1.02e+00 9.84e-01 0.5362

## Tumor.location4 7.47e-01 1.34e+00 0.4446

## Tumor.location5 7.86e-01 1.27e+00 0.4444

## Tumor.location6 9.47e-01 1.06e+00 0.5128

## Tumor.location7 1.40e+00 7.13e-01 0.9176

## Tumor.location8 1.34e+00 7.47e-01 0.6273

## Tumor.location9 9.46e-01 1.06e+00 0.6030

## Tumor.location10 7.94e-01 1.26e+00 0.3996

## T2 1.24e+00 8.08e-01 0.9379

## T3 1.92e+00 5.22e-01 1.4044

## T4 1.90e+00 5.27e-01 1.4738

## T5 1.06e+00 9.43e-01 0.7870

## N2 1.28e+00 7.82e-01 0.8427

## N3 2.32e+00 4.31e-01 1.7398

## N4 5.15e+00 1.94e-01 2.3615

## N5 1.07e+00 9.37e-01 0.8518

## Grade 1.64e+00 6.08e-01 1.4762

## Histology2 6.74e-01 1.48e+00 0.2076

## Histology3 7.51e-01 1.33e+00 0.2282

## Histology4 5.04e-01 1.98e+00 0.1554

## Histology5 3.11e-07 3.22e+06 0.0000

## Histology6 3.69e-07 2.71e+06 0.0000

## Histology7 5.06e-08 1.98e+07 0.0000

## Histology8 6.85e-01 1.46e+00 0.0680

## Histology9 6.98e-01 1.43e+00 0.1936

## Histology10 4.03e-01 2.48e+00 0.0771

## Histology11 1.39e+00 7.18e-01 0.4160

## Surgery2 5.93e-01 1.69e+00 0.4074

## Surgery3 6.43e-01 1.55e+00 0.3643

## Surgery4 6.21e-01 1.61e+00 0.4064

## Surgery5 1.31e+00 7.63e-01 0.7652

## Surgery6 8.93e-01 1.12e+00 0.6249

## Surgery7 6.36e-01 1.57e+00 0.4120

## Surgery8 3.56e-01 2.81e+00 0.0850

## upper .95

## Adj.RTTRUE 1.057

## Registry.IDAlaska/Hawaii - 1973+ 3.519

## Registry.IDAtlanta (Metropolitan) - 1975+ 1.598

## Registry.IDConnecticut - 1973+ 1.138

## Registry.IDDetroit (Metropolitan) - 1973+ 1.308

## Registry.IDGreater Georgia - 2000+ 1.572

## Registry.IDIowa - 1973+ 1.287

## Registry.IDKentucky / Rural Georgia - 1992+ 1.223

## Registry.IDLos Angeles - 1992+ 1.302

## Registry.IDLouisiana - 2000+ 1.771

## Registry.IDNew Jersey - 2000+ 1.698

## Registry.IDNew Mexico - 1973+ 2.022

## Registry.IDCalifornia SF/SJM/LA - 1973+ 1.230

## Registry.IDSeattle (Puget Sound) - 1974+ 1.563

## Registry.IDUtah - 1973+ 0.953

## Age.at.diagnosis 1.066

## Sex2 1.637

## Race2 0.889

## Race3 1.097

## Race4 1.596

## Year.of.diagnosis 1.003

## Tumor.location2 1.062

## Tumor.location3 1.928

## Tumor.location4 1.256

## Tumor.location5 1.392

## Tumor.location6 1.749

## Tumor.location7 2.144

## Tumor.location8 2.858

## Tumor.location9 1.486

## Tumor.location10 1.579

## T2 1.634

## T3 2.617

## T4 2.442

## T5 1.428

## N2 1.942

## N3 3.101

## N4 11.241

## N5 1.338

## Grade 1.832

## Histology2 2.189

## Histology3 2.471

## Histology4 1.634

## Histology5 Inf

## Histology6 Inf

## Histology7 Inf

## Histology8 6.908

## Histology9 2.520

## Histology10 2.102

## Histology11 4.664

## Surgery2 0.862

## Surgery3 1.136

## Surgery4 0.948

## Surgery5 2.243

## Surgery6 1.276

## Surgery7 0.981

## Surgery8 1.488

## Concordance= 0.853 (se = 0.013 )

## Rsquare= 0.374 (max possible= 0.979 )

## Likelihood ratio test= 991 on 56 df, p=0

## Wald test = 555 on 56 df, p=0

## Score (logrank) test = 1158 on 56 df, p=0

# conclusion? don't get treated for salivary gland surgery in utah!

utah.patients = which(seer.data$Registry.ID == levels(seer.data$Registry.ID)[15])

seer.data = seer.data[-utah.patients, ]

seer.data$Registry.ID = factor(seer.data$Registry.ID, levels = levels(seer.data$Registry.ID)[1:14])

# now get the fitted values for IV

Adj.RT.IV = glm(form, data = seer.data, family = binomial)$fitted.values

seer.data$U.est = seer.data$Adj.RT - Adj.RT.IV

form.final = as.formula(paste("Surv(Survival.Time,as.numeric(Vital.status.recode)) ~ Adj.RT + U.est + ",

paste(covs, collapse = "+")))

final.ph = coxph(form.final, data = seer.data)

## Warning: Loglik converged before variable 30,31,32 ; beta may be infinite.

summary(final.ph)

## Call:

## coxph(formula = form.final, data = seer.data)

## n= 2062, number of events= 560

## coef exp(coef) se(coef) z Pr(>|z|)

## Adj.RTTRUE 7.38e-01 2.09e+00 3.97e-01 1.86 0.06316 .

## U.est -1.03e+00 3.57e-01 4.19e-01 -2.46 0.01399 *

## Age.at.diagnosis 5.63e-02 1.06e+00 3.49e-03 16.14 < 2e-16 ***

## Sex2 3.01e-01 1.35e+00 9.18e-02 3.28 0.00103 **

## Race2 -4.71e-01 6.25e-01 2.08e-01 -2.26 0.02388 *

## Race3 -1.47e-01 8.63e-01 1.30e-01 -1.13 0.25821

## Race4 -1.55e+00 2.12e-01 1.01e+00 -1.53 0.12488

## Year.of.diagnosis -3.44e-02 9.66e-01 1.65e-02 -2.08 0.03782 *

## Tumor.location2 -2.76e-01 7.58e-01 1.99e-01 -1.39 0.16436

## Tumor.location3 -1.03e-01 9.02e-01 3.24e-01 -0.32 0.74975

## Tumor.location4 -3.98e-01 6.72e-01 2.63e-01 -1.51 0.13121

## Tumor.location5 -5.15e-02 9.50e-01 2.96e-01 -0.17 0.86208

## Tumor.location6 -1.74e-01 8.40e-01 3.14e-01 -0.55 0.57915

## Tumor.location7 2.36e-01 1.27e+00 2.17e-01 1.09 0.27524

## Tumor.location8 1.83e-01 1.20e+00 3.96e-01 0.46 0.64479

## Tumor.location9 -8.39e-02 9.19e-01 2.32e-01 -0.36 0.71762

## Tumor.location10 -4.49e-01 6.38e-01 3.56e-01 -1.26 0.20711

## T2 1.54e-01 1.17e+00 1.43e-01 1.08 0.28225

## T3 4.77e-01 1.61e+00 1.70e-01 2.80 0.00506 **

## T4 4.81e-01 1.62e+00 1.47e-01 3.28 0.00106 **

## T5 6.47e-02 1.07e+00 1.52e-01 0.42 0.67108

## N2 1.50e-01 1.16e+00 2.21e-01 0.68 0.49785

## N3 7.38e-01 2.09e+00 1.60e-01 4.63 3.7e-06 ***

## N4 1.69e+00 5.42e+00 3.93e-01 4.30 1.7e-05 ***

## N5 9.85e-02 1.10e+00 1.17e-01 0.84 0.39898

## Grade 4.21e-01 1.52e+00 6.83e-02 6.16 7.2e-10 ***

## Histology2 -1.63e-01 8.50e-01 6.07e-01 -0.27 0.78869

## Histology3 -2.42e-01 7.85e-01 6.07e-01 -0.40 0.69017

## Histology4 -4.08e-01 6.65e-01 6.11e-01 -0.67 0.50469

## Histology5 -1.44e+01 5.61e-07 1.13e+03 -0.01 0.98980

## Histology6 -1.45e+01 5.29e-07 2.97e+03 0.00 0.99612

## Histology7 -1.67e+01 5.86e-08 6.09e+03 0.00 0.99782

## Histology8 1.17e-01 1.12e+00 1.19e+00 0.10 0.92178

## Histology9 -1.84e-01 8.32e-01 6.57e-01 -0.28 0.77963

## Histology10 -5.69e-01 5.66e-01 8.44e-01 -0.67 0.50048

## Histology11 5.06e-01 1.66e+00 6.21e-01 0.82 0.41461

## Surgery2 -1.02e+00 3.62e-01 2.84e-01 -3.57 0.00035 ***

## Surgery3 -9.91e-01 3.71e-01 3.72e-01 -2.67 0.00765 **

## Surgery4 -9.54e-01 3.85e-01 2.85e-01 -3.35 0.00080 ***

## Surgery5 -2.45e-01 7.83e-01 3.57e-01 -0.69 0.49218

## Surgery6 -7.21e-01 4.86e-01 2.99e-01 -2.41 0.01599 *

## Surgery7 -1.01e+00 3.63e-01 2.94e-01 -3.45 0.00056 ***

## Surgery8 -1.71e+00 1.81e-01 7.78e-01 -2.20 0.02791 *

## ---

## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

## exp(coef) exp(-coef) lower .95 upper .95

## Adj.RTTRUE 2.09e+00 4.78e-01 0.9604 4.552

## U.est 3.57e-01 2.80e+00 0.1569 0.812

## Age.at.diagnosis 1.06e+00 9.45e-01 1.0507 1.065

## Sex2 1.35e+00 7.40e-01 1.1291 1.618

## Race2 6.25e-01 1.60e+00 0.4152 0.940

## Race3 8.63e-01 1.16e+00 0.6683 1.114

## Race4 2.12e-01 4.73e+00 0.0291 1.538

## Year.of.diagnosis 9.66e-01 1.03e+00 0.9354 0.998

## Tumor.location2 7.58e-01 1.32e+00 0.5137 1.120

## Tumor.location3 9.02e-01 1.11e+00 0.4775 1.703

## Tumor.location4 6.72e-01 1.49e+00 0.4009 1.126

## Tumor.location5 9.50e-01 1.05e+00 0.5314 1.698

## Tumor.location6 8.40e-01 1.19e+00 0.4536 1.556

## Tumor.location7 1.27e+00 7.89e-01 0.8284 1.937

## Tumor.location8 1.20e+00 8.33e-01 0.5521 2.611

## Tumor.location9 9.19e-01 1.09e+00 0.5834 1.449

## Tumor.location10 6.38e-01 1.57e+00 0.3178 1.282

## T2 1.17e+00 8.57e-01 0.8810 1.545

## T3 1.61e+00 6.21e-01 1.1542 2.248

## T4 1.62e+00 6.18e-01 1.2131 2.158

## T5 1.07e+00 9.37e-01 0.7913 1.438

## N2 1.16e+00 8.61e-01 0.7534 1.791

## N3 2.09e+00 4.78e-01 1.5302 2.860

## N4 5.42e+00 1.84e-01 2.5097 11.726

## N5 1.10e+00 9.06e-01 0.8778 1.387

## Grade 1.52e+00 6.57e-01 1.3322 1.741

## Histology2 8.50e-01 1.18e+00 0.2585 2.794

## Histology3 7.85e-01 1.27e+00 0.2391 2.579

## Histology4 6.65e-01 1.50e+00 0.2007 2.204

## Histology5 5.61e-07 1.78e+06 0.0000 Inf

## Histology6 5.29e-07 1.89e+06 0.0000 Inf

## Histology7 5.86e-08 1.71e+07 0.0000 Inf

## Histology8 1.12e+00 8.90e-01 0.1091 11.576

## Histology9 8.32e-01 1.20e+00 0.2297 3.015

## Histology10 5.66e-01 1.77e+00 0.1082 2.963

## Histology11 1.66e+00 6.03e-01 0.4916 5.600

## Surgery2 3.62e-01 2.76e+00 0.2077 0.632

## Surgery3 3.71e-01 2.69e+00 0.1793 0.769

## Surgery4 3.85e-01 2.60e+00 0.2205 0.673

## Surgery5 7.83e-01 1.28e+00 0.3889 1.575

## Surgery6 4.86e-01 2.06e+00 0.2706 0.874

## Surgery7 3.63e-01 2.75e+00 0.2041 0.646

## Surgery8 1.81e-01 5.53e+00 0.0393 0.831

## Concordance= 0.854 (se = 0.013 )

## Rsquare= 0.375 (max possible= 0.979 )

## Likelihood ratio test= 968 on 43 df, p=0

## Wald test = 550 on 43 df, p=0

## Score (logrank) test = 1127 on 43 df, p=0

# variance for beta_AdjRT should be the same ... testing

# boot.func.ART <- function(data,idx) { data.temp = data[idx,] final.ph =

# coxph(form.final,data=data.temp)

# return(c(final.ph$coef[1],final.ph$var[1,1])) }

# library(boot)

# final.ph.boot = boot(data=seer.data,statistic=boot.func.ART,R=1000)

# var.est = var(final.ph.boot$t[,1])

# z.boot = final.ph.boot$t[,1] / final.ph.boot$t[,2]

# p.val = sum(z.boot > 0) / 1000

# exp(coef(final.ph)[1] + c(-1,1) * 2 * sqrt(var.est)) [1] 0.8712999

# 5.0171531

阅读┊ 收藏 ┊ 喜欢 ▼ ┊打印┊举报/Report

前一篇：单边检测

后一篇：Count Data Using SAS, STATA

新浪BLOG意见反馈留言板　欢迎批评指正