2.2 The 6 types of objects in R are the following:
-vector: a collection of like elements without dimension
-matrix: a 2-D representation of a vector
-array: 3-D or more representation of a vector
-list: a collection of bins each containing any kind of R object
-dataframe: a list of tabular form where eah bin contains a data vector of the same length
-functions 2.3 3 main ways to index objects: by position, by name, by logical. Vectors can also be indexed by unique values and duplicated values.
2.4 Any R component(s) that can be indexed, can be replaced.
2.5 Code

smoking_y <- c(dead=139, alive=443)
smoking_n <- c(dead=230, alive=502)
cbind(smoking_y, smoking_n)
##       smoking_y smoking_n
## dead        139       230
## alive       443       502

2.6 Code

dat <- matrix(c(139, 443, 230, 502), 2, 2) #numbers ordered by row
dimnames(dat) <- list(c("Dead", "Alive"),
                      c("Yes", "No"))
cbind(dat)
##       Yes  No
## Dead  139 230
## Alive 443 502
rowtot <- apply(dat, 1, sum)
dat2 <- cbind(dat, rowtot)
coltot <- apply(dat2, 2, sum)
rbind(dat2, coltot)
##        Yes  No rowtot
## Dead   139 230    369
## Alive  443 502    945
## coltot 582 732   1314

2.7 Code

sweep(dat, 1, apply(dat, 1, sum), "/")            
##          Yes     No
## Dead  0.3767 0.6233
## Alive 0.4688 0.5312
sweep(dat, 2, apply(dat, 2, sum), "/")             
##          Yes     No
## Dead  0.2388 0.3142
## Alive 0.7612 0.6858

2.8 Code

coltot2 <- apply(dat, 2, sum)
risks <- dat["Dead", ]/coltot2
risk.ratio <- risks/risks[2]
odds <- risks/(1 - risks)
odds.ratio <- odds/odds[2]
dat # display results
##       Yes  No
## Dead  139 230
## Alive 443 502
rbind(risks, risk.ratio, odds, odds.ratio)
##               Yes     No
## risks      0.2388 0.3142
## risk.ratio 0.7601 1.0000
## odds       0.3138 0.4582
## odds.ratio 0.6848 1.0000

2.9 Risk calculations
Risk of death among non-smokers

         Age

Vital.Status 18-24 25-34 35-44 45-54 55-64 65-74 75+
Alive 0.98 0.97 0.94 0.85 0.67 0.22 0.00
Dead 0.02 0.03 0.06 0.15 0.33 0.78 1.00

Risk of death among smokers

         Age

Vital.Status 18-24 25-34 35-44 45-54 55-64 65-74 75+
Alive 0.96 0.98 0.87 0.79 0.56 0.19 0.00
Dead 0.04 0.02 0.13 0.21 0.44 0.81 1.00

Interpretation: The risk of death among smokers and non-smokers is about equivalent when comparing the age age groups between the two strata (smoking status). For both strata, risk of death increases with age.
2.10 Code

dat <- read.table("http://www.medepi.net/data/syphilis89c.txt", header = TRUE, sep = ",")
table(dat$Race, dat$Age, dat$Sex)    
## , ,  = Female
## 
##        
##         <=14  >55 15-19 20-24 25-29 30-34 35-44 45-54
##   Black  165   92  2257  4503  3590  2628  1505   392
##   Other   11   15   158   307   283   167   149    40
##   White   14   24   253   475   433   316   243    55
## 
## , ,  = Male
## 
##        
##         <=14  >55 15-19 20-24 25-29 30-34 35-44 45-54
##   Black   31  823  1412  4059  4121  4453  3858  1619
##   Other    7  108   210   654   633   520   492   202
##   White    2  216    88   407   550   564   654   323
attach(dat)     
table(Race, Age, Sex)      
## , , Sex = Female
## 
##        Age
## Race    <=14  >55 15-19 20-24 25-29 30-34 35-44 45-54
##   Black  165   92  2257  4503  3590  2628  1505   392
##   Other   11   15   158   307   283   167   149    40
##   White   14   24   253   475   433   316   243    55
## 
## , , Sex = Male
## 
##        Age
## Race    <=14  >55 15-19 20-24 25-29 30-34 35-44 45-54
##   Black   31  823  1412  4059  4121  4453  3858  1619
##   Other    7  108   210   654   633   520   492   202
##   White    2  216    88   407   550   564   654   323
xtabs(~ Race + Age + Sex)       
## , , Sex = Female
## 
##        Age
## Race    <=14  >55 15-19 20-24 25-29 30-34 35-44 45-54
##   Black  165   92  2257  4503  3590  2628  1505   392
##   Other   11   15   158   307   283   167   149    40
##   White   14   24   253   475   433   316   243    55
## 
## , , Sex = Male
## 
##        Age
## Race    <=14  >55 15-19 20-24 25-29 30-34 35-44 45-54
##   Black   31  823  1412  4059  4121  4453  3858  1619
##   Other    7  108   210   654   633   520   492   202
##   White    2  216    88   407   550   564   654   323

2.11 Marginal totals code

sdat <- xtabs(~ Race + Age + Sex)
apply(sdat, c(1,2,3), sum) #race is dim1(rows), age is dim2(columns), sex is dim3(strata)
## , , Sex = Female
## 
##        Age
## Race    <=14 >55 15-19 20-24 25-29 30-34 35-44 45-54
##   Black  165  92  2257  4503  3590  2628  1505   392
##   Other   11  15   158   307   283   167   149    40
##   White   14  24   253   475   433   316   243    55
## 
## , , Sex = Male
## 
##        Age
## Race    <=14 >55 15-19 20-24 25-29 30-34 35-44 45-54
##   Black   31 823  1412  4059  4121  4453  3858  1619
##   Other    7 108   210   654   633   520   492   202
##   White    2 216    88   407   550   564   654   323
#2-d
tab.ar <- apply(sdat, c(1, 2), sum); tab.ar
##        Age
## Race    <=14 >55 15-19 20-24 25-29 30-34 35-44 45-54
##   Black  196 915  3669  8562  7711  7081  5363  2011
##   Other   18 123   368   961   916   687   641   242
##   White   16 240   341   882   983   880   897   378
tab.as <- apply(sdat, c(1, 3), sum); tab.as
##        Sex
## Race    Female  Male
##   Black  15132 20376
##   Other   1130  2826
##   White   1813  2804
tab.rs <- apply(sdat, c(2, 3), sum); tab.rs
##        Sex
## Age     Female Male
##   <=14     190   40
##   >55      131 1147
##   15-19   2668 1710
##   20-24   5285 5120
##   25-29   4306 5304
##   30-34   3111 5537
##   35-44   1897 5004
##   45-54    487 2144
#1-d
tab.a <- apply(sdat, 1, sum); tab.a
## Black Other White 
## 35508  3956  4617
tab.r <- apply(sdat, 2, sum); tab.r
##  <=14   >55 15-19 20-24 25-29 30-34 35-44 45-54 
##   230  1278  4378 10405  9610  8648  6901  2631
tab.s <- apply(sdat, 3, sum); tab.s      
## Female   Male 
##  18075  26006

2.12 Code

tab.ars <- xtabs(~ Age + Race + Sex, data = sdat)
rowt <- apply(tab.ars, c(1, 3), sum) # row distrib
rowd <- sweep(tab.ars, c(1, 3), rowt, "/"); rowd
## , , Sex = Female
## 
##        Race
## Age      Black  Other  White
##   <=14  0.3333 0.3333 0.3333
##   >55   0.3333 0.3333 0.3333
##   15-19 0.3333 0.3333 0.3333
##   20-24 0.3333 0.3333 0.3333
##   25-29 0.3333 0.3333 0.3333
##   30-34 0.3333 0.3333 0.3333
##   35-44 0.3333 0.3333 0.3333
##   45-54 0.3333 0.3333 0.3333
## 
## , , Sex = Male
## 
##        Race
## Age      Black  Other  White
##   <=14  0.3333 0.3333 0.3333
##   >55   0.3333 0.3333 0.3333
##   15-19 0.3333 0.3333 0.3333
##   20-24 0.3333 0.3333 0.3333
##   25-29 0.3333 0.3333 0.3333
##   30-34 0.3333 0.3333 0.3333
##   35-44 0.3333 0.3333 0.3333
##   45-54 0.3333 0.3333 0.3333
apply(rowd, c(1, 3), sum) # confirm
##        Sex
## Age     Female Male
##   <=14       1    1
##   >55        1    1
##   15-19      1    1
##   20-24      1    1
##   25-29      1    1
##   30-34      1    1
##   35-44      1    1
##   45-54      1    1
colt <- apply(tab.ars, c(2, 3), sum) # col distrib
cold <- sweep(tab.ars, c(2, 3), colt, "/"); cold
## , , Sex = Female
## 
##        Race
## Age     Black Other White
##   <=14  0.125 0.125 0.125
##   >55   0.125 0.125 0.125
##   15-19 0.125 0.125 0.125
##   20-24 0.125 0.125 0.125
##   25-29 0.125 0.125 0.125
##   30-34 0.125 0.125 0.125
##   35-44 0.125 0.125 0.125
##   45-54 0.125 0.125 0.125
## 
## , , Sex = Male
## 
##        Race
## Age     Black Other White
##   <=14  0.125 0.125 0.125
##   >55   0.125 0.125 0.125
##   15-19 0.125 0.125 0.125
##   20-24 0.125 0.125 0.125
##   25-29 0.125 0.125 0.125
##   30-34 0.125 0.125 0.125
##   35-44 0.125 0.125 0.125
##   45-54 0.125 0.125 0.125
apply(cold, c(2, 3), sum) # confirm
##        Sex
## Race    Female Male
##   Black      1    1
##   Other      1    1
##   White      1    1
jtt <- apply(tab.ars, 3, sum) # joint distrib
jtd <- sweep(tab.ars, 3, jtt, "/"); jtd
## , , Sex = Female
## 
##        Race
## Age       Black   Other   White
##   <=14  0.04167 0.04167 0.04167
##   >55   0.04167 0.04167 0.04167
##   15-19 0.04167 0.04167 0.04167
##   20-24 0.04167 0.04167 0.04167
##   25-29 0.04167 0.04167 0.04167
##   30-34 0.04167 0.04167 0.04167
##   35-44 0.04167 0.04167 0.04167
##   45-54 0.04167 0.04167 0.04167
## 
## , , Sex = Male
## 
##        Race
## Age       Black   Other   White
##   <=14  0.04167 0.04167 0.04167
##   >55   0.04167 0.04167 0.04167
##   15-19 0.04167 0.04167 0.04167
##   20-24 0.04167 0.04167 0.04167
##   25-29 0.04167 0.04167 0.04167
##   30-34 0.04167 0.04167 0.04167
##   35-44 0.04167 0.04167 0.04167
##   45-54 0.04167 0.04167 0.04167
apply(jtd, 3, sum) # confirm
## Female   Male 
##      1      1
distr <- list(rowd, cold, jtd); distr
## [[1]]
## , , Sex = Female
## 
##        Race
## Age      Black  Other  White
##   <=14  0.3333 0.3333 0.3333
##   >55   0.3333 0.3333 0.3333
##   15-19 0.3333 0.3333 0.3333
##   20-24 0.3333 0.3333 0.3333
##   25-29 0.3333 0.3333 0.3333
##   30-34 0.3333 0.3333 0.3333
##   35-44 0.3333 0.3333 0.3333
##   45-54 0.3333 0.3333 0.3333
## 
## , , Sex = Male
## 
##        Race
## Age      Black  Other  White
##   <=14  0.3333 0.3333 0.3333
##   >55   0.3333 0.3333 0.3333
##   15-19 0.3333 0.3333 0.3333
##   20-24 0.3333 0.3333 0.3333
##   25-29 0.3333 0.3333 0.3333
##   30-34 0.3333 0.3333 0.3333
##   35-44 0.3333 0.3333 0.3333
##   45-54 0.3333 0.3333 0.3333
## 
## 
## [[2]]
## , , Sex = Female
## 
##        Race
## Age     Black Other White
##   <=14  0.125 0.125 0.125
##   >55   0.125 0.125 0.125
##   15-19 0.125 0.125 0.125
##   20-24 0.125 0.125 0.125
##   25-29 0.125 0.125 0.125
##   30-34 0.125 0.125 0.125
##   35-44 0.125 0.125 0.125
##   45-54 0.125 0.125 0.125
## 
## , , Sex = Male
## 
##        Race
## Age     Black Other White
##   <=14  0.125 0.125 0.125
##   >55   0.125 0.125 0.125
##   15-19 0.125 0.125 0.125
##   20-24 0.125 0.125 0.125
##   25-29 0.125 0.125 0.125
##   30-34 0.125 0.125 0.125
##   35-44 0.125 0.125 0.125
##   45-54 0.125 0.125 0.125
## 
## 
## [[3]]
## , , Sex = Female
## 
##        Race
## Age       Black   Other   White
##   <=14  0.04167 0.04167 0.04167
##   >55   0.04167 0.04167 0.04167
##   15-19 0.04167 0.04167 0.04167
##   20-24 0.04167 0.04167 0.04167
##   25-29 0.04167 0.04167 0.04167
##   30-34 0.04167 0.04167 0.04167
##   35-44 0.04167 0.04167 0.04167
##   45-54 0.04167 0.04167 0.04167
## 
## , , Sex = Male
## 
##        Race
## Age       Black   Other   White
##   <=14  0.04167 0.04167 0.04167
##   >55   0.04167 0.04167 0.04167
##   15-19 0.04167 0.04167 0.04167
##   20-24 0.04167 0.04167 0.04167
##   25-29 0.04167 0.04167 0.04167
##   30-34 0.04167 0.04167 0.04167
##   35-44 0.04167 0.04167 0.04167
##   45-54 0.04167 0.04167 0.04167

2.13 Code

std <- read.table("http://www.medepi.net/data/syphilis89b.txt",                       header = TRUE, sep = ",")
sex <- rep(std$Sex, std$Freq)
race <- rep(std$Race, std$Freq)
age <- rep(std$Age, std$Freq)
std.df <- data.frame(sex, race, age)

2.14
Read county names: scan indicates how many unique values are within the field.
Ready county pop estimates: read.csv reads text into the data frame as data without displaying output.
Replace county number with name: the for-loop will repeat for the number of unique county numbers within the dataset