Re: asymptotic standard error of lambda

[Ben Pfaff]

On Mon, May 05, 2014 at 10:24:07PM +0200, John Darrington wrote:
> On Mon, May 05, 2014 at 11:27:40AM -0700, Ben Pfaff wrote:
>      On Mon, May 5, 2014 at 10:51 AM, John Darrington
>      <address@hidden> wrote:
>      > On Mon, May 05, 2014 at 08:09:16AM -0700, Ben Pfaff wrote:
>      >      I'm sure there is an error in our implementation.  NaN is coming 
> from
>      >      the square root of a negative number, as you said.
>      >
>      >      I made another mistake below.  PSPP actually calculates ASE0 
> correctly
>      >      for asymmetric lambda (lambda divided by ASE0 is what's displayed 
> as
>      >      "Approx. T", which matches that calculated by SPSS for asymmetric
>      >      lambda).  It's ASE1, displayed as "Asymp. Std. Error", that PSPP 
> gets
>      >      wrong.
>      >
>      > Ahh. I was calculating ASE0.
>      >
>      > ASE1 like you say seems wierd and results in an imaginary number.  I 
> can only imagine
>      > that this is a mistake in the SPSS documentation.  Unfortunately I 
> haven't been able
>      > to find any other references on how to calculate this value.
>      >
>      > Another issue: if we have T, we should be able to calculate the 
> significance.  We just
>      > need to know the degrees of freedom.  I wonder how these are 
> calculated?
>      >
>      > Unfortunately the litereature on these values seems to be scarce.
>      
>      https://v8doc.sas.com/sashtml/stat/chap28/sect20.htm has a different 
> formula,
>      but I don't understand how to interpret r_i|l_i = l.
> 
> The text below it says:
>  Also, let li be the unique value of j such that ri=nij, and let l be the 
> unique value of j such that r = n??j.
> 
> I interpret this to mean that r_i is summed for all i where the condition l_i 
> == l is true.

I can't seem to get anything sensible out of that formula either.

For now, I removed the calculation entirely, so that PSPP displays
nothing instead of a wrong answer.