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

# Re: st: Constructing a variable from standard deviations

 From Clive Nicholas To statalist@hsphsun2.harvard.edu Subject Re: st: Constructing a variable from standard deviations Date Mon, 22 Nov 2010 19:46:16 +0000

```Maarten Buis replied to Mathijs P.J. van Zaal:

Bit late to this party, but...

[...]

> *---------------------------- begin example -----------------------
> // define linear regression model with non-constant error variance
> program drop _all
> program define mynormal_lf
>        version 11
>        args lnfj mu ln_sigma
>        quietly replace `lnfj' = ///
>                ln(normalden(\$ML_y1, `mu', exp(`ln_sigma')))
> end
>
> // open data
> sysuse auto, clear
> recode rep78 1/2=3
>
> // estimate a regular regression, i.e. with constant residual variance
> reg mpg weight displacement foreign i.rep78
>
> // store parameters for starting values
> tempname b0 rmse
> matrix `b0' = e(b)           // effects in the mu equation
> scalar `rmse' = ln(e(rmse))  // constant of the ln_sigma equation
>
> // specify the model
> ml model lf mynormal_lf                            ///
>   (mu: mpg = weight displacement foreign i.rep78) ///
>   (ln_sigma: i.rep78)
>
> // specify the initial values
> ml init `b0'
> ml init ln_sigma:_cons = `= `rmse' '
>
> // maximize the likelihood
> ml maximize
>
> // predict the residual variances
> predict sigma, xb eq(ln_sigma)
> replace sigma = exp(sigma)
>
> // display the residual variances
> // the residual variance is constant within each category of rep78
> table rep78, c(mean sigma)
> *---------------------------- end example --------------------------

...on my Stata 9.2, this code choked at

. // estimate a regular regression, i.e. with constant residual variance
. reg mpg weight displacement foreign i.rep78
i:  operator invalid
r(198);

and at all other parts of the code which feature -i.rep78-

--
Clive Nicholas

[Please DO NOT mail me personally here, but at
<clivenicholas@hotmail.com>. Please respond to contributions I make in