Maggie v5 adhoc

To summarize what we discussed, we are interested in knowing if the answers to questions 12 ("fellowship_yn"), 15 ("enfolded_postgrad_yn"), 16 ("private_academic"), 17 ("fellowship_years"), and 18 ("fellowship_field") differ based on year of training ("current_year"), debt ("debt"), gender ("gender"), race ("race"), age ("age"), marital status ("marital_status"), and family planning ("children").

Went from 265 to 257 rows because 8 cases from the original csv were removed due to having 50% or fewer of the questions answered.

read in and format data

df <- read.csv("maggie2.csv")
df <- df[!is.na(df$fellowship_yn),]
df2 <- df[c(2,7,20,22:23,27,31:33,35,37:39)]
df2$CAST_sub <- df$CAST_subspecialty
df2$CAST_fellow <- df$CAST_fellowship
df2 <- df2 %>%
  filter(is.na(gender) | gender == 1 | gender == 2 | gender == 7)

df2$pgy_cat <- ifelse(df2$current_year==1|df2$current_year==2, 'junior', ifelse(df2$current_year==7|df2$current_year==6, "senior", "midlevel"))
df2$fellow_cat <- ifelse(df2$fellowship_yn==1|df2$fellowship_yn==2, 'Probably or Definitely Yes', ifelse(df2$fellowship_yn==4|df2$fellowship_yn==5, "Probably or Definitely No", "Undecided"))

df2$age_cat <- ifelse(df2$age==2, '22-25 y/o', ifelse(df2$age==3, "26-30 y/o", ifelse(df2$age==4, "31-35 y/o", "36-45 y/o")))
df2$race_cat <- ifelse(df2$race==1, 'Native American or Alaska Native', ifelse(df2$race==2, "Asian", ifelse(df2$race==3, "Black or African American", ifelse(df2$race==4, "Native Hawaiian or other Pacific Islander", ifelse(df2$race==5, "White", "Other/No Response")))))

df2$gender_cat <- ifelse(df2$gender==1, 'Cis Woman', ifelse(df2$gender==2, "Cis Man", ifelse(df2$gender==3, "NB", ifelse(df2$gender==4, "Trans Woman", ifelse(df2$gender==7, "No Response", "Other")))))
{
df2$debt[df2$debt == 6] <- NA
df2$race[df2$race == 6] <- NA
df2$race[df2$race == 7] <- NA
df2$marital_status[df2$marital_status == 6] <- NA
df2$marital_status[df2$marital_status == 7] <- NA
df2$children[df2$children == 5] <- NA
}

Table 11. Characteristics of Residents Based on Q35. Did CAST accreditation affect FELLOWSHIP PROGRAMS APPLIED TO? [CAST_apply]

#makes cat for cast_apply
df3 <- df2 %>%
  mutate(CAST_cat = ifelse(df2$CAST_apply==1|df2$CAST_apply==2, 'Groups 1 and 2', ifelse(df2$CAST_apply==4|df2$CAST_apply==5, "Groups 4 and 5", NA))) 

year of training

df4 <- na.omit(df3[,c(7,19)])

table(df4$current_year)

 1  2  3  4  5  6  7 
15 33 65 44 17 21 20 

{
a <- filter(df4, current_year == 1 | current_year == 2)
b <- filter(df4, current_year == 1 | current_year == 3)
c <- filter(df4, current_year == 1 | current_year == 4)
d <- filter(df4, current_year == 1 | current_year == 5)
e <- filter(df4, current_year == 1 | current_year == 6)
f <- filter(df4, current_year == 1 | current_year == 7)
g <- filter(df4, current_year == 2 | current_year == 3)
h <- filter(df4, current_year == 2 | current_year == 4)
i <- filter(df4, current_year == 2 | current_year == 5)
j <- filter(df4, current_year == 2 | current_year == 6)
k <- filter(df4, current_year == 2 | current_year == 7)
l <- filter(df4, current_year == 3 | current_year == 4)
m <- filter(df4, current_year == 3 | current_year == 5)
n <- filter(df4, current_year == 3 | current_year == 6)
o <- filter(df4, current_year == 3 | current_year == 7)
p <- filter(df4, current_year == 4 | current_year == 5)
q <- filter(df4, current_year == 4 | current_year == 6)
r <- filter(df4, current_year == 4 | current_year == 7)
s <- filter(df4, current_year == 5 | current_year == 6)
t <- filter(df4, current_year == 5 | current_year == 7)
u <- filter(df4, current_year == 6 | current_year == 7)

mylist = list(a=a,b=b,c=c,d=d,e=e,f=f, g=g, h=h,i=i,j=j,k=k,l=l,m=m,n=n,o=o,p=p,q=q,r=r,s=s,t=t,u=u)
}

{
  n=0
  for(i in mylist){
    n<-n+1
    cat("test",n,"\n")
    print(t.test(table(i))$p.val*length(mylist))
    }
}

test 1 
[1] 1.51373
test 2 
[1] 3.731431
test 3 
[1] 1.619772
test 4 
[1] 0.2248684
test 5 
[1] 0.9181455
test 6 
[1] 0.3949907
test 7 
[1] 2.417262
test 8 
[1] 1.056247
test 9 
[1] 1.077962
test 10 
[1] 1.183971
test 11 
[1] 0.9768934
test 12 
[1] 1.931069
test 13 
[1] 3.359384
test 14 
[1] 3.163632
test 15 
[1] 3.160357
test 16 
[1] 1.279489
test 17 
[1] 1.276579
test 18 
[1] 1.158723
test 19 
[1] 0.4220411
test 20 
[1] 0.103661
test 21 
[1] 0.3079464

#nothing sig after corrections

debt

df4 <- na.omit(df3[,c(8,19)])

table(df4$debt)

 1  2  3  4  5 
54 73 31 16 48 

{
a <- filter(df4, debt == 1 | debt == 2)
b <- filter(df4, debt == 1 | debt == 3)
c <- filter(df4, debt == 1 | debt == 4)
d <- filter(df4, debt == 1 | debt == 5)
e <- filter(df4, debt == 2 | debt == 3)
f <- filter(df4, debt == 2 | debt == 4)
g <- filter(df4, debt == 2 | debt == 5)
h <- filter(df4, debt == 3 | debt == 4)
i <- filter(df4, debt == 3 | debt == 5)
j <- filter(df4, debt == 4 | debt == 5)

mylist = list(a=a,b=b,c=c,d=d,e=e,f=f, g=g, h=h,i=i,j=j)
}

{
  n=0
  for(i in mylist){
    n<-n+1
    cat("debt test",n,"\n")
    print(t.test(table(i))$p.val*length(mylist))
    }
}

debt test 1 
[1] 0.7543326
debt test 2 
[1] 0.1639306
debt test 3 
[1] 0.3891244
debt test 4 
[1] 0.1499835
debt test 5 
[1] 1.276186
debt test 6 
[1] 1.872269
debt test 7 
[1] 0.9111425
debt test 8 
[1] 0.3740217
debt test 9 
[1] 0.2164811
debt test 10 
[1] 0.5439639

#nothing sig after corrections

age

df4 <- na.omit(df3[,c(11,19)])

table(df4$age)

 2  3  4  5  6 
24 97 78 17  5 

{
a <- filter(df4, age == 1 | age == 2)
b <- filter(df4, age == 1 | age == 3)
c <- filter(df4, age == 1 | age == 4)
d <- filter(df4, age == 1 | age == 5)
e <- filter(df4, age == 2 | age == 3)
f <- filter(df4, age == 2 | age == 4)
g <- filter(df4, age == 2 | age == 5)
h <- filter(df4, age == 3 | age == 4)
i <- filter(df4, age == 3 | age == 5)
j <- filter(df4, age == 4 | age == 5)

mylist = list(a=a,b=b,c=c,d=d,e=e,f=f, g=g, h=h,i=i,j=j)
}

{
  n=0
  for(i in mylist){
    n<-n+1
    cat("age test",n,"\n")
    print(t.test(table(i))$p.val*length(mylist))
    }
}

age test 1 
[1] 1.93257
age test 2 
[1] 2.435653
age test 3 
[1] 1.419503
age test 4 
[1] 0.5385422
age test 5 
[1] 1.295021
age test 6 
[1] 0.5600675
age test 7 
[1] 0.3284896
age test 8 
[1] 0.5255765
age test 9 
[1] 1.49452
age test 10 
[1] 0.6720919

#nothing sig after corrections

Marital Status

df4 <- na.omit(df3[,c(12,19)])

a <- filter(df4, marital_status == 1 | marital_status == 2)
b <- filter(df4, marital_status == 1 | marital_status == 3)
c <- filter(df4, marital_status == 1 | marital_status == 4)
d <- filter(df4, marital_status == 2 | marital_status == 3)
e <- filter(df4, marital_status == 2 | marital_status == 4)
f <- filter(df4, marital_status == 3 | marital_status == 4)
mylist = list(a=a,b=b,c=c,d=d,e=e,f=f)

{
  n=0
  for(i in mylist){
    n<-n+1
    cat("test",n,"\n")
    print(t.test(table(i))$p.val*length(mylist))
    }
}

test 1 
[1] 0.1943717
test 2 
[1] 0.5227947
test 3 
[1] 0.3955447
test 4 
[1] 0.7136844
test 5 
[1] 0.5484972
test 6 
[1] 1.105587

#not sig after corrections

Children

df4 <- na.omit(df3[,c(13,19)])

{
a <- filter(df4, children == 1 | children == 2)
b <- filter(df4, children == 1 | children == 3)
c <- filter(df4, children == 1 | children == 4)
d <- filter(df4, children == 2 | children == 3)
e <- filter(df4, children == 2 | children == 4)
f <- filter(df4, children == 3 | children == 4)
mylist = list(a=a,b=b,c=c,d=d,e=e,f=f)
}

{
  n=0
  for(i in mylist){
    n<-n+1
    cat("test",n,"\n")
    print(t.test(table(i))$p.val*length(mylist))
    }
}

test 1 
[1] 0.4568477
test 2 
[1] 0.7779609
test 3 
[1] 0.4059886
test 4 
[1] 0.8393993
test 5 
[1] 0.5796956
test 6 
[1] 0.1574991

#none are sig after corrections

Table 10. Characteristics of Residents Based on Q34. Did CAST accreditation affect SUBSPECIALTY CHOICE

#makes cat for cast_apply
df3 <- df2 %>%
  mutate(CAST_sub = ifelse(df2$CAST_sub==1|df2$CAST_sub==2, 'Groups 1 and 2', ifelse(df2$CAST_sub==4|df2$CAST_sub==5, "Groups 4 and 5", NA))) 

year of training

df4 <- na.omit(df3[,c(7,14)])

table(df4$current_year)

 1  2  3  4  5  6  7 
10 32 52 32  9 16 17 

{
a <- filter(df4, current_year == 1 | current_year == 2)
b <- filter(df4, current_year == 1 | current_year == 3)
c <- filter(df4, current_year == 1 | current_year == 4)
d <- filter(df4, current_year == 1 | current_year == 5)
e <- filter(df4, current_year == 1 | current_year == 6)
f <- filter(df4, current_year == 1 | current_year == 7)
g <- filter(df4, current_year == 2 | current_year == 3)
h <- filter(df4, current_year == 2 | current_year == 4)
i <- filter(df4, current_year == 2 | current_year == 5)
j <- filter(df4, current_year == 2 | current_year == 6)
k <- filter(df4, current_year == 2 | current_year == 7)
l <- filter(df4, current_year == 3 | current_year == 4)
m <- filter(df4, current_year == 3 | current_year == 5)
n <- filter(df4, current_year == 3 | current_year == 6)
o <- filter(df4, current_year == 3 | current_year == 7)
p <- filter(df4, current_year == 4 | current_year == 5)
q <- filter(df4, current_year == 4 | current_year == 6)
r <- filter(df4, current_year == 4 | current_year == 7)
s <- filter(df4, current_year == 5 | current_year == 6)
t <- filter(df4, current_year == 5 | current_year == 7)
u <- filter(df4, current_year == 6 | current_year == 7)

mylist = list(a=a,b=b,c=c,d=d,e=e,f=f, g=g, h=h,i=i,j=j,k=k,l=l,m=m,n=n,o=o,p=p,q=q,r=r,s=s,t=t,u=u)
}

{
  n=0
  for(i in mylist){
    n<-n+1
    cat("test",n,"\n")
    print(t.test(table(i))$p.val*length(mylist))
    }
}

test 1 
[1] 2.859129
test 2 
[1] 3.794592
test 3 
[1] 1.289794
test 4 
[1] 0.1671575
test 5 
[1] 0.8699079
test 6 
[1] 1.068202
test 7 
[1] 1.758363
test 8 
[1] 0.7511715
test 9 
[1] 3.117452
test 10 
[1] 1.98436
test 11 
[1] 1.902498
test 12 
[1] 1.348805
test 13 
[1] 3.987495
test 14 
[1] 2.929115
test 15 
[1] 2.81732
test 16 
[1] 1.506524
test 17 
[1] 0.7328367
test 18 
[1] 0.7003125
test 19 
[1] 1.118448
test 20 
[1] 1.330887
test 21 
[1] 0.9247949

#nothing sig after corrections

debt

df4 <- na.omit(df3[,c(8,14)])

table(df4$debt)

 1  2  3  4  5 
35 70 21  9 32 

{
a <- filter(df4, debt == 1 | debt == 2)
b <- filter(df4, debt == 1 | debt == 3)
c <- filter(df4, debt == 1 | debt == 4)
d <- filter(df4, debt == 1 | debt == 5)
e <- filter(df4, debt == 2 | debt == 3)
f <- filter(df4, debt == 2 | debt == 4)
g <- filter(df4, debt == 2 | debt == 5)
h <- filter(df4, debt == 3 | debt == 4)
i <- filter(df4, debt == 3 | debt == 5)
j <- filter(df4, debt == 4 | debt == 5)

mylist = list(a=a,b=b,c=c,d=d,e=e,f=f, g=g, h=h,i=i,j=j)
}

{
  n=0
  for(i in mylist){
    n<-n+1
    cat("debt test",n,"\n")
    print(t.test(table(i))$p.val*length(mylist))
    }
}

debt test 1 
[1] 1.473104
debt test 2 
[1] 0.2775927
debt test 3 
[1] 1.015563
debt test 4 
[1] 0.09444612
debt test 5 
[1] 2.06963
debt test 6 
[1] 2.825597
debt test 7 
[1] 1.541306
debt test 8 
[1] 0.448362
debt test 9 
[1] 0.07581739
debt test 10 
[1] 0.6389743

#nothing sig after corrections

age

df4 <- na.omit(df3[,c(11,14)])

table(df4$age)

 2  3  4  5  6 
19 72 64  7  4 

{
a <- filter(df4, age == 1 | age == 2)
b <- filter(df4, age == 1 | age == 3)
c <- filter(df4, age == 1 | age == 4)
d <- filter(df4, age == 1 | age == 5)
e <- filter(df4, age == 2 | age == 3)
f <- filter(df4, age == 2 | age == 4)
g <- filter(df4, age == 2 | age == 5)
h <- filter(df4, age == 3 | age == 4) 
i <- filter(df4, age == 3 | age == 5)
j <- filter(df4, age == 4 | age == 5)

mylist = list(a=a,b=b,c=c,d=d,e=e,f=f, g=g, h=h,i=i,j=j)
}

{
  n=0
  for(i in mylist){
    n<-n+1
    cat("age test",n,"\n")
    print(t.test(table(i))$p.val*length(mylist))
    }
}

age test 1 
[1] 4.254463
age test 2 
[1] 3.361826
age test 3 
[1] 1.559583
age test 4 
[1] 0.9033447
age test 5 
[1] 1.516461
age test 6 
[1] 0.7829851
age test 7 
[1] 1.622876
age test 8 
[1] 0.3482941
age test 9 
[1] 2.180582
age test 10 
[1] 1.386915

#nothing

Marital Status

df4 <- na.omit(df3[,c(12,14)])

table(df4)

              CAST_sub
marital_status Groups 1 and 2 Groups 4 and 5
             1             20             20
             2             25              6
             3             60             27
             4              0              5

a <- filter(df4, marital_status == 1 | marital_status == 2)
b <- filter(df4, marital_status == 1 | marital_status == 3)
c <- filter(df4, marital_status == 1 | marital_status == 4)
d <- filter(df4, marital_status == 2 | marital_status == 3)
e <- filter(df4, marital_status == 2 | marital_status == 4)
f <- filter(df4, marital_status == 3 | marital_status == 4)
mylist = list(a=a,b=b,c=c,d=d,e=e,f=f)

{
  n=0
  for(i in mylist){
    n<-n+1
    cat("test",n,"\n")
    print(t.test(table(i))$p.val*length(mylist))
    }
}

test 1 
[1] 0.1354815
test 2 
[1] 0.2701048
test 3 
[1] 0.7022342
test 4 
[1] 0.4696764
test 5 
[1] 1.198921
test 6 
[1] 1.144412

#not sig after corrections