Submission

Your homework submission should include the markdown file and the knitted document (your choice of html, pdf or Word).

Questions

  1. For this exercise we will use the data set ChickWeight. You need to load the data in R using data(ChickWeight). The ChickWeight data frame has 578 rows and 4 columns from an experiment on the effect of diet on early growth of chicks. Use ?ChickWeight to get more information on every one of the variables.
data("ChickWeight")
?ChickWeight
  1. Each chick should have twelve weight measurements. Use the dplyr package to identify how many chicks have a complete set of weight measurements and how many measurements there are in the incomplete cases. Extract a subset of the data for all chicks with complete information and name the data set complete. (Hint: you might want to use mutate to introduce a helper variable consisting of the number of observations)
complete <- ChickWeight %>% 
  group_by(Chick) %>%
  tally() %>%
  filter(n==12)
complete <- ChickWeight %>%
  filter(Chick%in%complete$Chick)
  1. In the complete data set introduce a new variable that measures the current weight difference compared to day 0. Name this variable weightgain.
complete <- complete %>% 
  group_by(Chick) %>%
  mutate(weightgain = weight - weight[Time == 0])
  1. Using the ggplot2 package create side-by-side boxplots of weightgain by Diet for day 21. Describe the relationship in 2-3 sentences. Change the order of the categories in the Diet variable such that the boxplots are ordered by median weightgain.
complete %>%
  filter(Time == 21) %>%
  ggplot(aes(x=weightgain, y=reorder(Diet, weightgain, fun=median))) + geom_boxplot()

  1. Using the ggplot2 package create a plot with Time along the x axis and weight in the y axis. Facet by Diet. Use a point layer and also draw one line for each Chick. Color by Diet. Include the legend on the bottom (check theme).
    Comment on something interesting about these data in 2-3 sentences.
ggplot(data=complete, aes(x=Time, y=weight))  + geom_point() +
  geom_line(aes(group=Chick, color=Diet)) +
  facet_wrap(~Diet) +
  theme_dark() + theme(legend.position="bottom")

# The median seem to be somewhat similar between diet 2 and 4 while 3 surpasses them all. It is interesting that Diet 2 gave the broadest results, but was one of the furthest from being the best diet.
  1. Select the Chick with the maximum weight at Time 21 for each of the diets. Redraw the previous plot with only these 4 chicks (and don’t facet).
    Compute average daily weights under each Diet and redraw the plot (using the same structure and aesthetics as before).
    Comment on the results and compare all the visualizations. In your opinion which visualization presented in exercise 1 best describe this data set?
complete%>%
  group_by(Diet) %>%
  filter(weight==max(weight), Time==21)
## # A tibble: 4 × 5
## # Groups:   Diet [4]
##   weight  Time Chick Diet  weightgain
##    <dbl> <dbl> <ord> <fct>      <dbl>
## 1    305    21 7     1            264
## 2    331    21 21    2            291
## 3    373    21 35    3            332
## 4    322    21 48    4            283
ChickWeight %>%
  filter(Chick==7|Chick==21|Chick==35|Chick==48) %>%
  ggplot(aes(x=Time, y=weight))  + geom_point() +
  geom_line(aes(group=Chick, color=Diet)) +
  facet_wrap(~Diet) +
  theme_dark() + theme(legend.position="bottom")

ChickWeight %>%
  group_by(Diet, Time) %>%
  summarise(output=mean(weight)) %>%
  ggplot(aes(x=Time, y=output))  + geom_point() +
  geom_line(aes(color=Diet)) +
  theme_dark() + theme(legend.position="bottom")
## `summarise()` has grouped output by 'Diet'. You can override using the
## `.groups` argument.

# The Diet vs Time because you can see how they all differ across the same plane. It further illustrates that diet 3 produced the best results and shows around what time the results started to really differ.
  1. Create an R function that fits a simple linear regression and plots residuals vs fitted values using ggplot2 and includes a horizontal line in zero. The arguments for this function should be x (explanatory variable), y (response variable) and col for the horizontal line color. The x label should be Fitted Value and the y label should be Residuals.

    Show how your function works with data(LifeCycleSavings), use x = sr y = ddpi and col = red.
data("LifeCycleSavings")
?LifeCycleSavings

residPlot <- function(pop15,sr,col){
  lmFit <- lm(pop15~sr) +
  ggplot(aes(x=pop15, y=sr)) 
  return(plt)}
# residPlot(x = LifeCycleSavings$sr,y = LifeCycleSavings$ddpi,col = "red") would not let me knit the document. R said the function was unrecognizable