Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, is already up and running.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Re: Polychoric PCA error message

From   Yashin <>
Subject   Re: st: Re: Polychoric PCA error message
Date   Sun, 24 Feb 2013 20:25:13 -0500

Thanks for the response. There are no longer zero cells--I was simply
not certain of how to double check that I can now use the 1st
principal component as asset index, given error messages.

Would it be possible to clarify what was meant by non polychoric correlations?


Yashin Lin

From	  "JVerkuilen (Gmail)" <>
Subject	  Re: st: Re: Polychoric PCA error message
Date	  Sat, 23 Feb 2013 00:36:06 -0500

I would recommend looking at the original correlations (non
polychoric) and one and two-way marginal tables. If there is an excess
of zero cells or other pathological patterns, polychoric won't
converge. Sometimes you can fix this up by judicious assumptions such
as adding one to all cells in the table, but this needs to be handled
with serious care. Search the archives, this was discussed recently.

On Fri, Feb 22, 2013 at 6:50 PM, Yashin <> wrote:
> Dear Statalisters,
> While executing polychoric PCA to produce an asset/wealth index, three
> iterations of the following message appeared:
>   numerical derivatives are approximate
>   nearby values are missing
> I understand that the first principal component should be the wealth
> index; it contains negative values, with proportion of explained
> variance = ~25%.
> Principal component analysis
>  k  |  Eigenvalues  |  Proportion explained  |  Cum. explained
> ----+---------------+------------------------+------------------
>   1 |    7.955020   |    0.248594            |   0.248594
> Question: Are there any methods to double check that the procedure
> performed reasonably well and that I can use this 1st PC as an asset
> index? 25% explained variance and persistence of error messages
> suggest that I should be cautious.
> In case it helps, I have copied below a previous issue I have had with
> the same dataset,\ which led me to remove five variables, resulting in
> no zeros in correlation matrix.
> Thank you for any comments or suggestions!
> Yashin

*   For searches and help try:

© Copyright 1996–2016 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index