1 ## load the data
   2 load("data/studrecords.rdata")
   3 
   4 ## Test the null hypothesis that the population mean math score
   5 ## is 500 against a two-sided alternative. Would you accept or
   6 ## reject at a 0.05 significance level?
   7 
   8 t.test(stud.recs$sat.m, mu = 500)
   9 
  10 ## Test the null hypothesis that the mean math score is equal
  11 ## to the mean verbal (sat.v) score against a two sided hypothesis.
  12 t.test(stud.recs$sat.m, stud.recs$sat.v)
  13 
  14 
  15 ## Test the null hypothesis that the verbal and the math score
  16 ## is equal in each student.
  17 t.test(stud.recs$sat.m, stud.recs$sat.v, paired = T)
  18 
  19 
  20 ## Wilcoxon signed-rank test
  21 pre.test <- c(17,12,20,12,20,21,23,10,15,17,18,18)
  22 post.test <- c(19,25,18,18,26,19,27,14,20,22,16,18)
  23 
  24 wilcox.test(pre.test,post.test,paired = T)
  25 
  26 ## exercises
  27 ## load the data frame normtemp from the file temperature.rdata;
  28 ## it contains the body temperature of several individuals,
  29 ## the gender and the heart rate
  30 load("data/temperature.rdata")
  31 
  32 
  33 ## test if the temperature is different in male (coded as 1)
  34 ## and female (coded as 2), use the appropriate test.
  35 t.test(temperature ~ gender, data = normtemp)
  36 
  37 
  38 ## test again, compare the results of the t test and the wilcoxon.
  39 wilcox.test(temperature ~ gender, data = normtemp)
  40 
  41 
  42 require(ggplot2)
  43 ggplot(normtemp, aes(x = factor(gender), y = temperature)) +
  44     geom_boxplot()
  45 
  46 
  47 
  48 ## add another layer
  49 ggplot(normtemp, aes(x = factor(gender), y = temperature)) +
  50     geom_boxplot() +
  51     geom_point()
  52 
  53 ggsave("boxplotpoint.png")
  54 
  55 
  56 ggplot(normtemp, aes(x = factor(gender), y = temperature)) +
  57     geom_boxplot() +
  58     geom_jitter()
  59 
  60 
  61 ggsave("boxplotjitter.png")
  62 
  63 
  64 
  65 ggplot(normtemp, aes(x = factor(gender), y = temperature)) +
  66     geom_boxplot() +
  67     geom_jitter(position=position_jitter(width=0.1))
  68 
  69 
  70 ggsave("boxplotjitter2.png")
  71 
  72 ggplot(normtemp, aes(x = factor(gender), y = temperature)) +
  73     geom_boxplot() +
  74     geom_point(stat = "summary", fun.y = "mean")
  75 
  76 ggsave("boxplotmean.png")
  77 
  78 
  79 ggplot(normtemp, aes(x = factor(gender), y = temperature)) +
  80     geom_boxplot() +
  81     geom_point(stat = "summary", fun.y = "mean",
  82                size = 5, colour = "red")
  83 
  84 ggsave("boxplotmean2.png")
  85 
  86 
  87 
  88 
  89 ## Exercises
  90 
  91 ## load the data set GaltonFamilies from the package HistData 
  92 require(HistData)
  93 
  94 ## make a boxplot of childHeight dependent on gender
  95 ## add the means using geom_point()
  96 ggplot(GaltonFamilies, aes(x = gender, y = childHeight)) +
  97     geom_boxplot() +
  98     geom_point(stat = "summary", fun.y = "mean",
  99                size = 5, colour = "red") +
 100     geom_text(aes(label = round(..y..,1)), stat = "summary", fun.y = "mean",
 101                size = 5, colour = "red",vjust=-0.6)
 102 
 103 
 104 ## do the respective t-test: what is the (trivial) null hypothesis,
 105 ## what is appropriate test, what is the test result and what is
 106 ## the conclusion?
 107 t.test(childHeight ~ gender, data = GaltonFamilies)
 108 
 109 
 110 ## bivariate plots
 111 ggplot(GaltonFamilies, aes(x=mother,y=father)) +
 112     geom_point() 
 113 
 114 
 115 ggsave("scatter.png")
 116 
 117 ## adding a trend line
 118 ggplot(GaltonFamilies, aes(x=mother,y=father)) +
 119     geom_point() +
 120     geom_smooth()
 121 
 122 ggsave("scattertrend1.png")
 123 
 124 
 125 
 126 ## adding a trend line
 127 ggplot(GaltonFamilies, aes(x=mother,y=father)) +
 128     geom_point() +
 129     geom_smooth(method="lm")
 130 
 131 ggsave("scattertrend2.png")
 132 
 133 
 134 ## Exercises
 135 ## use again the GaltonFamilies data set; produce a scatter plot
 136 ## of childHeight vs midparentHeight
 137 
 138 ggplot(GaltonFamilies, aes(x=midparentHeight,y=childHeight)) +
 139     geom_point() 
 140 
 141 
 142 ##add a trend line by using geom\_smooth() without any
 143 ## arguments. Which method is used?
 144 ggplot(GaltonFamilies, aes(x=midparentHeight,y=childHeight)) +
 145     geom_point() +
 146     geom_smooth() 
 147 
 148 
 149 ## add a second trend line, this time a linear one!
 150 ggplot(GaltonFamilies, aes(x=midparentHeight,y=childHeight)) +
 151     geom_point() +
 152     geom_smooth() +
 153     geom_smooth(method="lm")
 154 
 155 
 156 ## now use the aesthetic colour in the first line of the plot
 157 ## definition. What happens?
 158 ggplot(GaltonFamilies, aes(x=midparentHeight,y=childHeight,colour=gender)) +
 159     geom_point() +
 160     geom_smooth() +
 161     geom_smooth(method="lm")
 162