Data set: Games2
Assume that in the computer game study researchers were also interested in testing whether college students could play the game more quickly with their right or left hand. The data set Games2 shows a column Type2 with four types of games, based on distracter and which hand was used.
a. Graph the data and compare the center and spread of the completion times for each of the four groups listed under Type2. Does any group have outliers or skewed data?
b. Conduct an ANOVA with one explanatory variable that has the four levels listed under Type2. Notice that this data set has I = 4 groups instead of 2 groups. However, the model and calculations are identical except that now i = 1, 2, 3, 4 instead of i = 1, 2 and now each group has a sample size of ni = 10. The null hypothesis is H0: µ1 = µ2 = µ3 = µ4 versus the alternative Ha: at least one mean is different from another. Does the ANOVA show that a significant difference exists between group means?
c. Create residual plots. Are the model assumptions satisfied?
d. Are there any extraneous variables that might bias the results?
e. Assuming that the data for this game were collected in the same way as the Game1 data, state your conclusions. Be sure to address random sampling and random allocation.
We could consider modeling the completion times as a function of two explanatory variables: the hand used (right or left) and the game type (standard or with color distracter). This would require a two-way ANOVA analysis (discussed in later chapters).