 |
StatXact Example 2
Does Type of Reward Influence Reaction to Task Disruption?
Pearson Chi-Squared Test Says NO! But Exact Test Says YES!
Researchers provided four types of rewards for successful completion of a block building task. The rewards may be categorized as achievement oriented, financial, socially reinforcing, and neural. Five subjects were assigned at random to each reward category. The subjects were instructed in advance about their respective reward structures, and then assigned to the block building task. Each subject was interrupted in a standard way while carrying out the task. The object of the experiment was to determine if the type of reward was related to the subject's reaction to task disruption. The data are displayed below:
| |
Reaction To Task Disruption |
Totals |
|
Type Of Reward |
Start Over |
Abandon Task |
Modify Task |
(N = 20) |
| Achievement Oriented |
5 |
0 |
0 |
5 |
| Financial |
2 |
1 |
2 |
5 |
| Socially Reinforcing |
2 |
0 |
3 |
5 |
| Neutral |
0 |
1 |
4 |
5 |
| TOTALS |
9 |
2 |
9 |
20 |
The output from StatXact for Pearson's X2 test is displayed below:

Notice that the Pearson X2 = 11.56, which, when referred to a chi squared distribution with 6 degrees of freedom, yields an asymptotic p-value of 0.0727. But with data this sparse can you really trust the asymptotic p-value? Fortunately you don't need to. The exact p-value of the Pearson test is computed by StatXact to be 0.0398. You can feel secure that your experiment did indeed yield a statistically significant outcome, despite the small sample size. The type of reward does indeed affect one's reaction to task disruption.
|
 |
 |
 |
| |
Example Submissions
Over the years, most of the examples have come from in-house statisticians, but we would like our examples to better reflect the actual uses customers have for our products.
Therefore, we would like to ask for data from our customers for use as examples. Any data we use would be properly cited, and with your permission, could be used for examples in our manuals, in marketing material, or even for one of our live webcasts.
This is a chance to have your hard work published and made known to many other statisticians in your field and in other disciplines.
Get Acrobat Reader
|
|