COMP 3008 Chapter Notes - Chapter 14: Null Hypothesis, Dependent And Independent Variables
Document Summary
Independent variable what the investigator manipulates (i. e. selects: dependent variable a measure of the user performance, ex. if hypothesis is context menus are easier to select options compared with cascading menus. Important to ensure that the order in which participants perform tasks for this set up does not bias the results. Ex. if there are two tasks, a and b, half the participants should do task a followed by task b and the other half should do task b followed by task a. Each pair is then randomly allocated to each experimental condition: disadvantage: can never be sure that subjects are matched across variables that might affect performance t-tests test the probability of a result occurring by chance. Compare the differences between the conditions, to reveal if they are significant.