Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.

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

 From William Buchanan <[email protected]> To "[email protected]" <[email protected]> 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 <[email protected]> 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: [email protected]
>> To: [email protected]
>>
>> On Tue, Jun 12, 2012 at 10:09 PM, tashi lama <[email protected]> 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/
```

• References: