Re: st: How to find the best transformation for each variable in 120 periods

[Xixi Lin <winnielxx@gmail.com>]

Hi JVerkuilen,

You are right that the key assumption is Gaussian errors, but my data
does not have Gaussian errors, and I wanna use t statistics, so I
wanna to fix the non-normal residuals by transforming the variables (I
don't know what else to do to fix the Gaussian errors). Is there any
better way to deal with it? Or Is there any papers that I can read
about it?

Thanks,
Xixi Lin

On Fri, Feb 22, 2013 at 10:27 AM, JVerkuilen (Gmail)
<jvverkuilen@gmail.com> wrote:
> On Fri, Feb 22, 2013 at 9:44 AM, Xixi Lin <winnielxx@gmail.com> wrote:
>> Hi,
>>
>> I am trying to find the best transformation for each variable in 120
>> periods. I know that command ladder gives the following result:
>
> Transforming the dependent variable before you have a notion of what
> the regression model will be and the deviations from it is generally a
> useless endeavor. A good bit of the non-Gaussian structure in data can
> be due to the regressors and once you regress on them the data may be
> much better behaved. The key assumption is Gaussian errors, not
> Gaussian dependent variables unconditionally. (And even that
> assumption isn't *that* important, just so long as it's not violated
> too badly.)
>
> If you're planning on using transformations, I highly recommend
> getting a copy of A. C. Atkinson's book Plots, Transformations and
> Regression: An Introduction to Graphical Methods of Diagnostic
> Regression Analysis (1986, Oxford University Press).
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/faqs/resources/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/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/