In emeyers/SDS100: Tools for the class Introductory Statistics

knitr::opts_chunk$set(echo = TRUE)

$\$

Quantiles on the Bechdel data

70% of movies made less than how much money?

library(fivethirtyeight)


# get the 70th percentile of the Bechdel data

quantile(bechdel$domgross_2013, .7, na.rm = TRUE)

$\$

Boxplots on the Bechdel data

# get pass fail data separately

bechdel_pass_df <- subset(bechdel, binary == "PASS")
bechdel_fail_df <- subset(bechdel, binary == "FAIL")

domgross_pass <- bechdel_pass_df$domgross_2013 
domgross_fail <- bechdel_fail_df$domgross_2013 



# boxplot

boxplot(domgross_pass, 
        domgross_fail, 
        names = c("pass", "fail"))



# log 10 of the data boxplot

boxplot(log10(domgross_pass), 
        log10(domgross_fail), 
        names = c("pass", "fail"))

$\$

Scatterplots and Correlation

Do movies that have larger budgets make more profit?

# original data

budget <- bechdel$budget_2013
profit <- bechdel$domgross_2013

# create scatter plot
plot(budget, profit)

# add identity line
abline(a = 0, b = 1, col = "red")


# calculate the correlation
cor(budget, profit, use = "complete.obs")




# look at log10 of the data scatter plot

budget_log10 <- log10(budget)
profit_log10 <- log10(profit)


# create scatter plot
plot(budget_log10, profit_log10)

# add identity line
abline(a = 0, b = 1, col = "red")


# calculate the correlation
cor(budget_log10, profit_log10, use = "complete.obs")

$\$

Does playing football affect brain size?

library(Lock5Data)

# get the data from the data frame
years_played <- FootballBrain$Years
hippocampus_vol <- FootballBrain$Hipp
group <- FootballBrain$Group



# create scatterplot and calculate the correlation
plot(years_played, hippocampus_vol)
cor(years_played, hippocampus_vol)



# create side-by-side boxplots for the different groups
boxplot(hippocampus_vol ~ group)