# Thread: Which statistical test?

1. ## Which statistical test?

Hi everyone,

It's been a couple of years since I've taken a statistics class and I'm struggling to remember which test I should use. Essentially, what I'm trying to analyze is if new technology has decreased a trend of accidents and severity.

Thanks!

2. ## Re: Which statistical test?

A chi-square test would be appropriate.

3. ## Re: Which statistical test?

Originally Posted by cruiselife
Hi everyone,

It's been a couple of years since I've taken a statistics class and I'm struggling to remember which test I should use. Essentially, what I'm trying to analyze is if new technology has decreased a trend of accidents and severity.

Thanks!
Chi-square, but since the count in one of the cells is less than 5, Fisher Exact would be an appropriate one.

Thanks!

4. ## Re: Which statistical test?

Originally Posted by bburugap
Chi-square, but since the count in one of the cells is less than 5, Fisher Exact would be an appropriate one.

Thanks!
It's a small point, but typically, the observed cell count is not the focus. The assumption is with respect to the expected cell count being at least 5. The smallest expected count in this table is around 4.80, so strictly following the rule, a FET probably wouldn't hurt too much. OP should be careful, though, as the FET is frequently less powerful than the chi-square (if I recall, it's ameliorated by larger a larger sample size), and these differences don't appear to be too large. Looking at both a FET and chi-square would probably be useful. If they agree, you don't have to think as hard about it as in the case of the tests disagreeing (personally, I'd probably be more conservative and stick with FET if they disagree). If this is for a research project or something in the real world, the OP should definitely decide beforehand how disagreement between the tests will be handled.

 Tweet

#### Posting Permissions

• You may not post new threads
• You may not post replies
• You may not post attachments
• You may not edit your posts