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 at the end of May, and its replacement, statalist.org is already up and running.


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

Re: st: documentation on iteration for a non linear regression


From   William Buchanan <william@williambuchanan.net>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   Re: st: documentation on iteration for a non linear regression
Date   Tue, 12 Jun 2012 15:21:02 -0700

Hi Tashi,

In addition to the requirement that you read the FAQ and try searching for answers in the manuals, your response indicates that you didn't bother to look "in" the stored matrix but instead just looked "at" it.  As well as reading the documentation that Nick recommended, I would also suggest reading the documentation regarding how to use matrices in Stata.  What you were commenting about is correct, you saw the dimensions of the matrix that you are interested in.  Had you entered: 

mat li e(b) 

You would have displayed the information in the matrix rather than the dimension of the matrix.  

- Billy

Sent from my iPhone

On Jun 12, 2012, at 14:40, tashi lama <ltashi32@hotmail.com> wrote:

> ereturn list will will provide e(b) under matrices like 
> 
> ereturn list 
> 
> scalars:
> 
> macros:
> 
> matrice: 
> 
>      e(b): 1*2
> 
> 
> 
> that doesn't tell much, does it. Looks like a size of a matrix. I was looking for the the values of parameters b0 and b1 in the table saved as macro or scalar. 
> 
> 
> 
> Source |       SS       df       MS
> -------------+------------------------------         Number of obs =       312
>       Model |  49079.3588     2  24539.6794         R-squared     =    0.9785
>    Residual |  1077.64118   310  3.47626187         Adj R-squared =    0.9784
> -------------+------------------------------         Root MSE      =  1.864474
>       Total |       50157   312  160.759615         Res. dev.     =   1272.15
> 
> ------------------------------------------------------------------------------
>        hits |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
> -------------+----------------------------------------------------------------
>         /b0 |   632.7244   16.97061    37.28   0.000     599.3323    666.1166
>         /b1 |   .3304635   .0074969    44.08   0.000     .3157122    .3452148
> ------------------------------------------------------------------------------
> 
> 
> 
> 
> 
> 
> 
> Thanx
> 
> 
> 
> 
>> Subject: Re: st: documentation on iteration for a non linear regression
>> From: njcoxstata@gmail.com
>> To: statalist@hsphsun2.harvard.edu
>> 
>> On Tue, Jun 12, 2012 at 10:09 PM, tashi lama <ltashi32@hotmail.com> wrote:
>> 
>> Is there a documentation in Stata which tells how iteration for a non
>> linear regression is done? I am having trouble with initializing the
>> parameters. I am hoping I will have a better idea to initialize the
>> parameters if I understand the iteration process.
>> 
>>>>> See the help and the manual entry as usual. The iteration is faster if you have even a rough idea of what the correct values should be.
>> 
>> Also, when I run a non linear regression model, the values of the
>> estimated parameters aren't returned. Isn't it a choke?
>> 
>>>>> I don't know what "choke" means here, but this is utterly incorrect. Look in e(b).
>> *
>> * For searches and help try:
>> * http://www.stata.com/help.cgi?search
>> * http://www.stata.com/support/statalist/faq
>> * http://www.ats.ucla.edu/stat/stata/                         
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index