In my mind, significance is an either/or situation. EIther you have it, or you don't. "Marginally significant", to me, would indicate something in the .048 range (assuming alpha=.05, it has to first be significant in order to be "marginally" so.)

As for the question of it "approaching" significance. It could just as easily be running away from significance as it is "approaching" it. We don't know. Again, to me, this is an attempt by authors to make a bigger deal out of their findings than is really warranted based on the data.... my bias perhaps. Of course, another option would be to set alpha at .1 instead of .05 and suddenly both are statistically significant... the joys of alpha being fairly arbitrary, though most reviewers would question the high alpha level.

However, this might be a good way to start bringing up other issues with the student such as effect size and power. It's possible that the results indicate that there was an effect, but the study did not have enough power to detect it (perhaps caused by a small sample size?)

Just my two cents this morning as I get ready to discuss writing the results section with my methods class...
- Marc


At 07:39 AM 11/11/2002 -0500, you wrote:
One of my students doing her senior thesis ran her stats and got results of
.056 and .08 for two different ANOVAs. In the past I have seen published
studies indicating that these are "marginally significant." How do you deal
with results of this nature? More importantly, do you have any citations
(journals or books) that discuss the value of including/discussing results
that seem to "approach significance"?

Thanks,

Rob Flint

===========================
G. Marc Turner
Southwest Texas State University


---
You are currently subscribed to tips as: [EMAIL PROTECTED]
To unsubscribe send a blank email to [EMAIL PROTECTED]

Reply via email to