Instructions

# Run this code chunk WITHOUT editing it!
source("https://uoepsy.github.io/data/get_data_lt1_dapr1_2122.R")

For example, if we were to ask you to compute 2 to the power of 3, store it to an object x, and then print the value, your code chunk should look like this:

x <- 2^3

# The next line prints the result
x
## [1] 8

The data

In your R environment you should see a data set called water. This contains data for 100 individuals taking part in a survey. They were asked to report their age group (non-adult/adult) and which type of water they usually drink.

Tasks

Question 1

Create a new object called tbl which contains the two-way contingency table of counts for each combination of age group and preferred type of water.

Answer below:

tbl <- water %>%
  table()

# The next line prints the result
tbl
##            UsuallyDrink
## AgeGroup    Bottled Filtered Tap
##   Non-adult      14        8   5
##   Adult          27       18  28

Question 2

Using ggplot, create an object called plot_tbl that displays the different water preferences faceted by age group.

Answer below:

plot_tbl <- ggplot(data = water, aes(x = UsuallyDrink)) +
  geom_histogram(stat="count") +
  facet_wrap("AgeGroup")
## Warning: Ignoring unknown parameters: binwidth, bins, pad
# The next line prints the result
plot_tbl

Question 3

Create an object called p_age containing 2 numbers: the first is the probability of being a non-adult, and the second the probability of being an adult.

Answer below:

p_age <- c((27/100), (73/100))
   
# The next line prints the result
p_age
## [1] 0.27 0.73

Question 4

Create an object called p_cond, containing the probability that, given the preference is filtered water, the participant is not an adult. The object p_cond should only be one number.

Answer below:

p_cond <- 8/26
   
# The next line prints the result
p_cond
## [1] 0.3076923

Question 5

Create an object called p_adult_water, containing two probabilities: the first is the probability that an adult prefers bottled water, and the second the probability that an adult prefers filtered or tap water.

Answer below:

p_adult_water <- c(27/73, (18+28)/73)
   
# The next line prints the result
p_adult_water
## [1] 0.369863 0.630137