Nearing significance?

[futureapppsy2]

Advertisement - Members don't see this ad

thanks!

 

[erg923]

Yes, its done/written all the time, but many researchers have also written about the fallacies and implications of such statments.

 

[Ollie123]

What on earth kind of literature is this Co-I reading?

I see < .1 described as a "trend towards significance" or "Approaching significance" when its very close to .05 ALL-the-freakin-time. This is not unusual in the slightest, even in top-tier journals.

I don't think there's anything wrong with reporting it, provided you are upfront about it and the limitations. "Approaching significance" is not the same as significant. Its important to acknowledge that. Though since your study may have been underpowered and depending on how you analyzed it, the unbalanced groups could also reduce your power even further, I think its fine to report it and I certainly would (and have). It isn't ideal, but like I said, as long as you are honest about it I don't see anyone having a problem with it. The only reason .05 is the standard anyways is tradition. There's nothing magical about it.

 

[futureapppsy2]

Thanks guys!