2 Independent Sample t-test

1 Continuous Dependent Variable with normal distribution

1 (2 level) Categorical Independent Variable

The t-test assesses whether the means of two groups statistically differ from each other. The 2 independent sample t-test is used when testing 2 independent groups. The groups are considered independent if a member of one group cannot possibly be in the other group.  For example, the 2 independent sample t-test is appropriate when testing behavioral differences between males and females (assuming ‘male’ and ‘female’ are the independent variables) because a person cannot be in both groups.

In a study conducted in 2000, Maglio and Campbell [7] test distraction level of 2 different peripheral displays. In the experiment, test subjects perform a complex editing task. Subjects also periodically monitor a peripheral display containing miscellaneous news headlines. They are told their performance will be measured by the number of correct edits they complete and the number of news headlines they remember. The peripheral interfaces the experimenters evaluate include (1) a display that continuously scrolls news headlines across the screen, and (2) a display that scrolls news headlines across the screen at discrete intervals.

The research team demonstrates a valid application of the 2 sample independent t-test when comparing distraction level of display 1 verses display 2. The two peripheral displays serve as the independent variables, and performance on the editing task serves as the dependent variable. 29 subjects participated in the experiment, so the team was marginally safe in assuming the dependent variable followed a normal distribution (the central limit theorem proves distribution is normal with a sample size of 30 or more). The independent variables were mutually exclusive: the peripheral displays had different scrolling characteristics, so in the context of the experiment, they could not have been grouped together. The team found subjects in the discrete scrolling condition were better editors than subjects in the continuous scrolling condition.

Values to report:

· Mean value of each test group

· T-value

· degrees of freedom

· p value