Clinical and statistical significance

Important Message

Important Message by Patrick Denker Attribution-NonCommercial License

A statistically significant difference is a difference that we think is not just due to chance. I say “think”, because we are never completely certain. We express how certain we are by the p value. A p value of 0.05 indicates a 5% uncertainty, or a 95% probability.

Ok so we think there is a difference, but is it an important difference? Maybe, maybe not. Statistics don’t tell us the answer to this question. We have to think about the degree of difference and what that might mean. For example would that difference change how you would treat an animal? Would it change the treatment you recommend? Would it change when something happens by an important amount? This is what we mean by clinical significance.

Just because there is statistically significant difference, it does not necessarily follow that the difference is clinically significant.

Advertisements

One thought on “Clinical and statistical significance

  1. Pingback: Effect size | MVM learning

Leave a comment

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s