Reem's data

First Job

is to test whether some measures of eyetracking for Experimental and Control students are the same. First off, I renamed the variables so that they had Ex or Con at the beginning to make sure there was no confusion. The obvious test to use is a t-test, which is what I'll use below. First though, a barplot of the 8 columns to see the distribution:

Eyetrack <- read.csv("C:/Users/Stephen/Desktop/Reem/Eyetrack.csv")
boxplot(Eyetrack, col = "Wheat", main = "Experimental Total Scores")

plot of chunk unnamed-chunk-1

t.test(Eyetrack$Exfirst, Eyetrack$Confirst)

    Welch Two Sample t-test

data:  Eyetrack$Exfirst and Eyetrack$Confirst
t = 8.702, df = 833.7, p-value < 2.2e-16
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
  68.7 108.7
sample estimates:
mean of x mean of y 
    285.4     196.7 
t.test(Eyetrack$ExGaze, Eyetrack$ConGaze)

    Welch Two Sample t-test

data:  Eyetrack$ExGaze and Eyetrack$ConGaze
t = 15.83, df = 552.5, p-value < 2.2e-16
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 1564 2007
sample estimates:
mean of x mean of y 
   2049.6     263.8 
t.test(Eyetrack$ExRead, Eyetrack$Conread)

    Welch Two Sample t-test

data:  Eyetrack$ExRead and Eyetrack$Conread
t = 11.74, df = 547.3, p-value < 2.2e-16
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 1144 1604
sample estimates:
mean of x mean of y 
   1425.6      51.6 
t.test(Eyetrack$ExTotal, Eyetrack$ConTotal)

    Welch Two Sample t-test

data:  Eyetrack$ExTotal and Eyetrack$ConTotal
t = 31.25, df = 567.1, p-value < 2.2e-16
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 3222 3654
sample estimates:
mean of x mean of y 
   3753.4     315.4 

All the p values are well below 0.05. Therefore we have to conclude that the means of the variables are different.