e: Multiple loadings for a variable in Factor analysis

[Laurie Moseley]

I do not see the problem. A variable can load on several factors and, if it is sensible to do so, one can treat more than one of them as meaningful. "Attractiveness" can be loaded high on, say, both "Intelligence" and "Personality". The two may or may not be related to each other, but they can both form part of what goes to make up attractiveness. Or is there some subtle (or even obvious) point that I have missed during my rapid reading of the exchanges on this topic? That is a genuine question.

Best wishes

Laurie
23 August 2007

Topic: Multiple loadings for a variable in Factor analysis
To: [hidden email]

Naru wrote:

> Hi
>
> I am carrying out factor analysis for my research data using SPSS. I have
> about 200 cases.
>
> Some of the variables have multiple loadings to different factors in the
> rotated component matrix results.
> I have given a cut off of 0.3 for "Coefficient display format - Suppress
> absolute values less than" option in SPSS.
>
> There is one variable where the loading is 0.3 against Factor 1 and 0.61
> against Factor-3.
>
> I would want to classify this variable under Factor-1 rather than Factor-3.
> I have read materials about factor analysis. None of them talk about moving
> a variable from one factor to another factor based on valid arguments.
>
> Is that an acceptable practice ?
> --
> View this message in context: http://www.nabble.com/Multiple-loadings-for-a-variable-in-Factor-analysis-tf4291887.html#a12218125
> Sent from the SPSSX Discussion mailing list archive at Nabble.com.
>
>
>

[Art Kendall-2]

If I factor a set of items related to "attractiveness" and
"intelligence" and "personality" items group on two factors, then I
would represent attractiveness in further modeling as two variables.  If
I include an item on more than one score, I lose divergent validity.
That is one reason one takes care to avoid or eliminate items that are
"double barreled".

That some items might be splitters and be dropped is a reason that
typically one started with many more candidate items than one finally
retains.

Art Kendall


Laurie Moseley wrote:

> I do not see the problem. A variable can load on several factors and, if it is sensible to do so, one can treat more than one of them as meaningful. "Attractiveness" can be loaded high on, say, both "Intelligence" and "Personality". The two may or may not be related to each other, but they can both form part of what goes to make up attractiveness. Or is there some subtle (or even obvious) point that I have missed during my rapid reading of the exchanges on this topic? That is a genuine question.
>
> Best wishes
>
> Laurie
> 23 August 2007
>
> Topic: Multiple loadings for a variable in Factor analysis
> To: [hidden email]
>
> Naru wrote:
>
>> Hi
>>
>> I am carrying out factor analysis for my research data using SPSS. I have
>> about 200 cases.
>>
>> Some of the variables have multiple loadings to different factors in the
>> rotated component matrix results.
>> I have given a cut off of 0.3 for "Coefficient display format - Suppress
>> absolute values less than" option in SPSS.
>>
>> There is one variable where the loading is 0.3 against Factor 1 and 0.61
>> against Factor-3.
>>
>> I would want to classify this variable under Factor-1 rather than Factor-3.
>> I have read materials about factor analysis. None of them talk about moving
>> a variable from one factor to another factor based on valid arguments.
>>
>> Is that an acceptable practice ?
>> --
>> View this message in context: http://www.nabble.com/Multiple-loadings-for-a-variable-in-Factor-analysis-tf4291887.html#a12218125
>> Sent from the SPSSX Discussion mailing list archive at Nabble.com.
>>
>>
>>
>>
>
>
>