Biostatistic 2 Exam Preparations NAIMUR RAHMAN 24316007

Load required packages and dataset

library(gtsummary)
library(dplyr)
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
data("trial")

#Generate a univariate summary for age, grade, and trt

trial %>% 
  tbl_summary()
Characteristic N = 2001
Chemotherapy Treatment
    Drug A 98 (49%)
    Drug B 102 (51%)
Age 47 (38, 57)
    Unknown 11
Marker Level (ng/mL) 0.64 (0.22, 1.41)
    Unknown 10
T Stage
    T1 53 (27%)
    T2 54 (27%)
    T3 43 (22%)
    T4 50 (25%)
Grade
    I 68 (34%)
    II 68 (34%)
    III 64 (32%)
Tumor Response 61 (32%)
    Unknown 7
Patient Died 112 (56%)
Months to Death/Censor 22.4 (15.9, 24.0)
1 n (%); Median (Q1, Q3) 
trial1 <-  trial %>% 
  select(trt, age, grade)
trial1

#Select variables

trial2 <- trial %>% 
select(trt, age, grade)

#Descriptive table

trial2 %>% 
tbl_summary()
Characteristic N = 2001
Chemotherapy Treatment
    Drug A 98 (49%)
    Drug B 102 (51%)
Age 47 (38, 57)
    Unknown 11
Grade
    I 68 (34%)
    II 68 (34%)
    III 64 (32%)
1 n (%); Median (Q1, Q3)

#Cross Table Summary

trial %>%
  tbl_summary(
    by = trt)
Characteristic Drug A
N = 981		 Drug B
N = 1021
Age 46 (37, 60) 48 (39, 56)
    Unknown 7 4
Marker Level (ng/mL) 0.84 (0.23, 1.60) 0.52 (0.18, 1.21)
    Unknown 6 4
T Stage

    T1 28 (29%) 25 (25%)
    T2 25 (26%) 29 (28%)
    T3 22 (22%) 21 (21%)
    T4 23 (23%) 27 (26%)
Grade

    I 35 (36%) 33 (32%)
    II 32 (33%) 36 (35%)
    III 31 (32%) 33 (32%)
Tumor Response 28 (29%) 33 (34%)
    Unknown 3 4
Patient Died 52 (53%) 60 (59%)
Months to Death/Censor 23.5 (17.4, 24.0) 21.2 (14.5, 24.0)
1 Median (Q1, Q3); n (%)

#Bi variate Analysis (Add P Value)

trial %>%
   tbl_summary(by = trt) %>%
   add_p() %>%
   add_overall() %>%
   add_n()
Characteristic N Overall
N = 2001		 Drug A
N = 981		 Drug B
N = 1021		 p-value2
Age 189 47 (38, 57) 46 (37, 60) 48 (39, 56) 0.7
    Unknown
11 7 4
Marker Level (ng/mL) 190 0.64 (0.22, 1.41) 0.84 (0.23, 1.60) 0.52 (0.18, 1.21) 0.085
    Unknown
10 6 4
T Stage 200


0.9
    T1
53 (27%) 28 (29%) 25 (25%)
    T2
54 (27%) 25 (26%) 29 (28%)
    T3
43 (22%) 22 (22%) 21 (21%)
    T4
50 (25%) 23 (23%) 27 (26%)
Grade 200


0.9
    I
68 (34%) 35 (36%) 33 (32%)
    II
68 (34%) 32 (33%) 36 (35%)
    III
64 (32%) 31 (32%) 33 (32%)
Tumor Response 193 61 (32%) 28 (29%) 33 (34%) 0.5
    Unknown
7 3 4
Patient Died 200 112 (56%) 52 (53%) 60 (59%) 0.4
Months to Death/Censor 200 22.4 (15.9, 24.0) 23.5 (17.4, 24.0) 21.2 (14.5, 24.0) 0.14
1 Median (Q1, Q3); n (%)
2 Wilcoxon rank sum test; Pearson’s Chi-squared test

#logistic regression model

model <- lm(response ~  trt+age, data = trial)
 # Create a summary table
 tbl_regression(model)
Characteristic Beta 95% CI p-value
Chemotherapy Treatment


    Drug A — —
    Drug B 0.03 -0.11, 0.16 0.7
Age 0.00 0.00, 0.01 0.095
Abbreviation: CI = Confidence Interval

#egression output using tbl_regression

 model <- glm(death ~ trt + age, data = trial, family = "binomial")
 # Create a summary table
 tbl_regression(model)
Characteristic log(OR) 95% CI p-value
Chemotherapy Treatment


    Drug A — —
    Drug B 0.30 -0.27, 0.88 0.3
Age 0.01 -0.01, 0.03 0.3
Abbreviations: CI = Confidence Interval, OR = Odds Ratio

#odds ratio with confidence intervals

exp(cbind(OR = coef(model), confint(model)))
## Waiting for profiling to be done...
##                    OR     2.5 %   97.5 %
## (Intercept) 0.6221615 0.2173766 1.748544
## trtDrug B   1.3559218 0.7628798 2.419382
## age         1.0106203 0.9904519 1.031601