A4-LeslieIkemoto

From Visualization Sp06

I was interested in seeing if there were significant differences in response time due to the comparison type (A <-> B, A <-> B+C, A+B <-> C+D). First I separated the response times based on task, then computed the mean and standard deviation for each group:

Comparing A <-> B took less time on average than comparing A <-> B+C, which took less time on average than comparing A+B <-> C+D. I tested for significance by performing an single factor ANOVA. These results indicate that significant differences exist between the groups: F(2,4317) = 70.58, MSE = 2531351.10, p < 0.05. (I did this test using Excel's data analysis package, like in the example. I report the numbers in the same way; please see the example for explanation.)

After finding significant differeneces, I performed post-hoc pairwise T-tests between the response times for the tasks. I found all pairwise differences significant: A <-> B and A <-> B+C (t(1439) = -8.95, p < 0.05, two-tailed), A <-> B and A+B <-> C+D (t(1439) = -14.50, p < 0.05, two-tailed), and A <-> B+C and A+B <-> C+D (t(1439) = -2.99, p < 0.05, two-tailed). (I also did this test exactly like the example assignment. Please see the example for further explanation.)

---