Re: st: Predicting sdres in stata

[Richard Goldstein <richgold@ix.netcom.com>]

no

Rich

On 7/20/11 10:01 AM, Lars Folkestad wrote:
> Thank you both of you.
> Last question: The robust option, does This render the test of residual normality unnessesery?
> 
> Mvh
> Lars Folkestad
> 
> 
> Den 20/07/2011 kl. 15.34 skrev "Nick Cox" <njcoxstata@gmail.com>:
> 
>> Note that -predict- without options gives you predicted values, What
>> you call the variable makes no difference to that.
>>
>> Nick
>>
>> On Wed, Jul 20, 2011 at 7:40 AM, Richard Goldstein
>> <richgold@ix.netcom.com> wrote:
>>> I think regression is the best way; I am not familiar with how either of
>>> the two concepts are measured; for general guidance on this kind of
>>> adjustment, I suggest the following two articles (which have different
>>> but related points):
>>>
>>> Rosenbaum, PR and Rubin, DB (1984), "Difficulties with regression
>>> analyses of age-adjusted rates," _Biometrics_ 40: 437-443
>>>
>>> Kronmal, RA (1993), "Spurious correlation and the fallacy of the ratio
>>> standard revisited," _Journal of the Royal Statistical Society, Series
>>> A_, 156(3): 379-392; comments and reply in the same journal (1995),
>>> 158(3): 619-625
>>>
>>> Rich
>>>
>>> On 7/20/11 8:28 AM, Lars Folkestad wrote:
>>>> Thank You For the swift answare.
>>>> I was indeed trying to predict the residuals for the regression model.
>>>>
>>>> What i am trying to do is to adjust a Bone Density Value for the
>>>> participants Body surface area. Is there a better way to do this than
>>>> regression?
>>>>
>>>> Will figure wich option fits best.
>>>>
>>>> Lars
>>>>
>>>> Den 20/07/11 14.19 skrev "Richard Goldstein" <richgold@ix.netcom.com>
>>>> følgende:
>>>>
>>>>> without knowing what depenVar1 and depenVar2 are, it is not possible to
>>>>> fully answer the question
>>>>>
>>>>> however, note that what you are asking for are the predicted values from
>>>>> the equation and this depends solely on the value of the constant and
>>>>> the value of the coefficient for BSA; apparently, these are "very
>>>>> similar" in the two regressions; do you mean to ask for the predicted
>>>>> values or are you trying to predict some kind of residual? if you want
>>>>> some kind of residual, you will need to add an option; see -h regress
>>>>> postestimation- and click on "predict"
>>>>>
>>>>> Rich
>>>>>
>>>>> On 7/20/11 8:05 AM, Lars Folkestad wrote:
>>>>>> Hi Stata Listers
>>>>>>
>>>>>> This is probably a simple question for you all. I just cannot see my way
>>>>>> through it.
>>>>>>
>>>>>> I am doing liniar regression for different variables as a way to adjust for
>>>>>> Body Surface Area. I do the following
>>>>>>
>>>>>> . regress depenVar1 BSA, vce(robust)
>>>>>> . predict sdres
>>>>>> . qnorm sdres
>>>>>> . swilk sdres
>>>>>> . predict adjdepenVar1
>>>>>> . drop sdres
>>>>>>
>>>>>> . regress depenVar2 BSA, vce(robust)
>>>>>> . predict sdres
>>>>>> . qnorm sdres
>>>>>> . swilk sdres
>>>>>>
>>>>>> The two swilks tests give the exact same p-value and the qnorm graf is
>>>>>> identical.
>>>>>>
>>>>>> I cannot understand how. For your information i am new to stata and
>>>>>> regression and my statistically knowledge is low.
>>>>>>
>>>>>> Why is the two swilks tests and qnorms the same?
*
*   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/