Hi Stephen-

I don't have the original post in front of me but my memory was that the
scores were being categorized as something like "low-medium-high". To me
this idicates ordinal data & that is why I suggested Spearman's Rho.
Probably doesn't matter much which you use unless you have a highly
non-monotonic distribution in which case the Pearson values would be
artifically low.

Have a great weekend.

-Don.

Steven Specht said:
> But the scores themselves are not being ranked (that is, subjects are
> not ranked), they are being categorized.
>
> Don Allen wrote:
>
>> Wouldn't it be more appropriate to use a Spearman Rho if you are
>> asuming ordinality in your data?
>>
>> -Don.
>>
>> --
>>
>> ---
>> You are currently subscribed to tips as: [EMAIL PROTECTED]
>> To unsubscribe send a blank email to
>> [EMAIL PROTECTED]
>
> --
> ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
>
> Steven M. Specht, Ph.D.
> Associate Professor of Psychology
> Department of Psychology
> Utica College
> Utica, NY 13502
> (315) 792-3171
>
> "unanswered questions are less dangerous than unquestioned answers"
>
>
>
> ---
> You are currently subscribed to tips as: [EMAIL PROTECTED]
> To unsubscribe send a blank email to
> [EMAIL PROTECTED]


-- 




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

Reply via email to