

Hello all, can help clarify something?
According to R's lm() doc:
> NonNULL weights can be used to indicate that different observations
> have different variances (with the values in weights being inversely
> *proportional* to the variances); or equivalently, when the elements
> of weights are positive integers w_i, that each response y_i is the
> mean of w_i unitweight observations (including the case that there
> are w_i observations equal to y_i and the data have been summarized).
Since the idea here is *proportion*, not equality, shouldn't the vectors
of weights x, 2*x give the same result? And yet they don't, standard
errors differs:
> > summary(lm(c(1,2,3,1,2,3)~c(1,2.1,2.9,1.1,2,3),weight=rep(1,6)))$sigma
> [1] 0.07108323
> > summary(lm(c(1,2,3,1,2,3)~c(1,2.1,2.9,1.1,2,3),weight=rep(2,6)))$sigma
> [1] 0.1005269
So what if I know apriori, observation A has variance 2 times bigger
than observation B? Both weights=c(1,2) and weights=c(2,4) (and so on)
represent very well this knowledge, but we get different regression
(since sigma is different).
Also, if we do the same thing with a glm() model, than we get a lot of
other differences like in the deviance.
______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/rhelpPLEASE do read the posting guide http://www.Rproject.org/postingguide.htmland provide commented, minimal, selfcontained, reproducible code.


On 05/02/14 22:40, Marco Inacio wrote:
> Hello all, can help clarify something?
>
> According to R's lm() doc:
>
>> NonNULL weights can be used to indicate that different observations
>> have different variances (with the values in weights being inversely
>> *proportional* to the variances); or equivalently, when the elements
>> of weights are positive integers w_i, that each response y_i is the
>> mean of w_i unitweight observations (including the case that there
>> are w_i observations equal to y_i and the data have been summarized).
>
> Since the idea here is *proportion*, not equality, shouldn't the vectors
> of weights x, 2*x give the same result? And yet they don't, standard
> errors differs:
>
>>> summary(lm(c(1,2,3,1,2,3)~c(1,2.1,2.9,1.1,2,3),weight=rep(1,6)))$sigma
>> [1] 0.07108323
>>> summary(lm(c(1,2,3,1,2,3)~c(1,2.1,2.9,1.1,2,3),weight=rep(2,6)))$sigma
>> [1] 0.1005269
The weights are in fact case weights, i.e., a weight of 2 is the same as
including the corresponding item twice. I agree that the documentation
is no wonder of clarity in this respect.
Btw, note that, in your example, (0.1005269 / 0.07108323)^2 = 2, your
constant weight.
Göran Broström
>
>
> So what if I know apriori, observation A has variance 2 times bigger
> than observation B? Both weights=c(1,2) and weights=c(2,4) (and so on)
> represent very well this knowledge, but we get different regression
> (since sigma is different).
>
>
> Also, if we do the same thing with a glm() model, than we get a lot of
> other differences like in the deviance.
>
> ______________________________________________
> [hidden email] mailing list
> https://stat.ethz.ch/mailman/listinfo/rhelp> PLEASE do read the posting guide http://www.Rproject.org/postingguide.html> and provide commented, minimal, selfcontained, reproducible code.
>
______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/rhelpPLEASE do read the posting guide http://www.Rproject.org/postingguide.htmland provide commented, minimal, selfcontained, reproducible code.


Dear Marco and Goran,
Perhaps the documentation could be clearer, but it is after all a brief help page. Using weights of 2 to lm() is *not* equivalent to entering the observation twice. The weights are variance weights, not case weights.
You can see this by looking at the whole summary() output for the models, not just the residual standard errors:
 snip 
> summary(lm(c(1,2,3,1,2,3)~c(1,2.1,2.9,1.1,2,3),weight=rep(1,6)))
Call:
lm(formula = c(1, 2, 3, 1, 2, 3) ~ c(1, 2.1, 2.9, 1.1, 2, 3),
weights = rep(1, 6))
Residuals:
1 2 3 4 5 6
0.06477 0.08728 0.07487 0.03996 0.01746 0.02986
Coefficients:
Estimate Std. Error t value Pr(>t)
(Intercept) 0.11208 0.08066 1.39 0.237
c(1, 2.1, 2.9, 1.1, 2, 3) 1.04731 0.03732 28.07 9.59e06 ***

Signif. codes: 0 *** 0.001 ** 0.01 * 0.05 . 0.1 1
Residual standard error: 0.07108 on 4 degrees of freedom
Multiple Rsquared: 0.9949, Adjusted Rsquared: 0.9937
Fstatistic: 787.6 on 1 and 4 DF, pvalue: 9.59e06
> summary(lm(c(1,2,3,1,2,3)~c(1,2.1,2.9,1.1,2,3),weight=rep(2,6)))
Call:
lm(formula = c(1, 2, 3, 1, 2, 3) ~ c(1, 2.1, 2.9, 1.1, 2, 3),
weights = rep(2, 6))
Residuals:
1 2 3 4 5 6
0.09160 0.12343 0.10589 0.05652 0.02469 0.04223
Coefficients:
Estimate Std. Error t value Pr(>t)
(Intercept) 0.11208 0.08066 1.39 0.237
c(1, 2.1, 2.9, 1.1, 2, 3) 1.04731 0.03732 28.07 9.59e06 ***

Signif. codes: 0 *** 0.001 ** 0.01 * 0.05 . 0.1 1
Residual standard error: 0.1005 on 4 degrees of freedom
Multiple Rsquared: 0.9949, Adjusted Rsquared: 0.9937
Fstatistic: 787.6 on 1 and 4 DF, pvalue: 9.59e06
 snip 
Notice that while the residual standard errors differ, the coefficients and their standard errors are identical. There are compensating changes in the residual variance and the weighted sum of squares and products matrix for X.
In contrast, literally entering each observation twice reduces the coefficient standard errors by a factor of sqrt((6  2)/(12  2)), i.e., the square root of the relative residual df of the models:
 snip 
> summary(lm(rep(c(1,2,3,1,2,3),2)~rep(c(1,2.1,2.9,1.1,2,3),2)))
Call:
lm(formula = rep(c(1, 2, 3, 1, 2, 3), 2) ~ rep(c(1, 2.1, 2.9,
1.1, 2, 3), 2))
Residuals:
Min 1Q Median 3Q Max
0.087276 0.039963 0.006201 0.064768 0.074874
Coefficients:
Estimate Std. Error t value Pr(>t)
(Intercept) 0.11208 0.05101 2.197 0.0527
rep(c(1, 2.1, 2.9, 1.1, 2, 3), 2) 1.04731 0.02360 44.374 8.12e13
(Intercept) .
rep(c(1, 2.1, 2.9, 1.1, 2, 3), 2) ***

Signif. codes: 0 *** 0.001 ** 0.01 * 0.05 . 0.1 1
Residual standard error: 0.06358 on 10 degrees of freedom
Multiple Rsquared: 0.9949, Adjusted Rsquared: 0.9944
Fstatistic: 1969 on 1 and 10 DF, pvalue: 8.122e13
 snip 
I hope this helps,
John

John Fox, Professor
McMaster University
Hamilton, Ontario, Canada
http://socserv.mcmaster.ca/jfox/
On Thu, 6 Feb 2014 09:27:22 +0100
Göran Broström < [hidden email]> wrote:
> On 05/02/14 22:40, Marco Inacio wrote:
> > Hello all, can help clarify something?
> >
> > According to R's lm() doc:
> >
> >> NonNULL weights can be used to indicate that different observations
> >> have different variances (with the values in weights being inversely
> >> *proportional* to the variances); or equivalently, when the elements
> >> of weights are positive integers w_i, that each response y_i is the
> >> mean of w_i unitweight observations (including the case that there
> >> are w_i observations equal to y_i and the data have been summarized).
> >
> > Since the idea here is *proportion*, not equality, shouldn't the vectors
> > of weights x, 2*x give the same result? And yet they don't, standard
> > errors differs:
> >
> >>> summary(lm(c(1,2,3,1,2,3)~c(1,2.1,2.9,1.1,2,3),weight=rep(1,6)))$sigma
> >> [1] 0.07108323
> >>> summary(lm(c(1,2,3,1,2,3)~c(1,2.1,2.9,1.1,2,3),weight=rep(2,6)))$sigma
> >> [1] 0.1005269
>
> The weights are in fact case weights, i.e., a weight of 2 is the same as including the corresponding item twice. I agree that the documentation is no wonder of clarity in this respect.
>
> Btw, note that, in your example, (0.1005269 / 0.07108323)^2 = 2, your constant weight.
>
> Göran Broström
> >
> >
> > So what if I know apriori, observation A has variance 2 times bigger
> > than observation B? Both weights=c(1,2) and weights=c(2,4) (and so on)
> > represent very well this knowledge, but we get different regression
> > (since sigma is different).
> >
> >
> > Also, if we do the same thing with a glm() model, than we get a lot of
> > other differences like in the deviance.
> >
> > ______________________________________________
> > [hidden email] mailing list
> > https://stat.ethz.ch/mailman/listinfo/rhelp> > PLEASE do read the posting guide http://www.Rproject.org/postingguide.html> > and provide commented, minimal, selfcontained, reproducible code.
> >
>
> ______________________________________________
> [hidden email] mailing list
> https://stat.ethz.ch/mailman/listinfo/rhelp> PLEASE do read the posting guide http://www.Rproject.org/postingguide.html> and provide commented, minimal, selfcontained, reproducible code.
______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/rhelpPLEASE do read the posting guide http://www.Rproject.org/postingguide.htmland provide commented, minimal, selfcontained, reproducible code.


Dear John,
thanks for the clarification! The lesson to be learned is that one
should be aware of the fact that weights may mean different things in
different functions, and sometimes different things in the same function
(glm)!
Göran
On 02/06/2014 02:17 PM, John Fox wrote:
> Dear Marco and Goran,
>
> Perhaps the documentation could be clearer, but it is after all a
> brief help page. Using weights of 2 to lm() is *not* equivalent to
> entering the observation twice. The weights are variance weights, not
> case weights.
>
> You can see this by looking at the whole summary() output for the
> models, not just the residual standard errors:
>
>  snip 
>
>> summary(lm(c(1,2,3,1,2,3)~c(1,2.1,2.9,1.1,2,3),weight=rep(1,6)))
>
> Call: lm(formula = c(1, 2, 3, 1, 2, 3) ~ c(1, 2.1, 2.9, 1.1, 2, 3),
> weights = rep(1, 6))
>
> Residuals: 1 2 3 4 5 6 0.06477
> 0.08728 0.07487 0.03996 0.01746 0.02986
>
> Coefficients: Estimate Std. Error t value Pr(>t) (Intercept)
> 0.11208 0.08066 1.39 0.237 c(1, 2.1, 2.9, 1.1, 2, 3)
> 1.04731 0.03732 28.07 9.59e06 ***  Signif. codes: 0 ‘***’
> 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
>
> Residual standard error: 0.07108 on 4 degrees of freedom Multiple
> Rsquared: 0.9949, Adjusted Rsquared: 0.9937 Fstatistic: 787.6 on
> 1 and 4 DF, pvalue: 9.59e06
>
>> summary(lm(c(1,2,3,1,2,3)~c(1,2.1,2.9,1.1,2,3),weight=rep(2,6)))
>
> Call: lm(formula = c(1, 2, 3, 1, 2, 3) ~ c(1, 2.1, 2.9, 1.1, 2, 3),
> weights = rep(2, 6))
>
> Residuals: 1 2 3 4 5 6 0.09160
> 0.12343 0.10589 0.05652 0.02469 0.04223
>
> Coefficients: Estimate Std. Error t value Pr(>t) (Intercept)
> 0.11208 0.08066 1.39 0.237 c(1, 2.1, 2.9, 1.1, 2, 3)
> 1.04731 0.03732 28.07 9.59e06 ***  Signif. codes: 0 ‘***’
> 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
>
> Residual standard error: 0.1005 on 4 degrees of freedom Multiple
> Rsquared: 0.9949, Adjusted Rsquared: 0.9937 Fstatistic: 787.6 on
> 1 and 4 DF, pvalue: 9.59e06
>
>  snip 
>
> Notice that while the residual standard errors differ, the
> coefficients and their standard errors are identical. There are
> compensating changes in the residual variance and the weighted sum of
> squares and products matrix for X.
>
> In contrast, literally entering each observation twice reduces the
> coefficient standard errors by a factor of sqrt((6  2)/(12  2)),
> i.e., the square root of the relative residual df of the models:
>
>  snip 
>
>> summary(lm(rep(c(1,2,3,1,2,3),2)~rep(c(1,2.1,2.9,1.1,2,3),2)))
>
> Call: lm(formula = rep(c(1, 2, 3, 1, 2, 3), 2) ~ rep(c(1, 2.1, 2.9,
> 1.1, 2, 3), 2))
>
> Residuals: Min 1Q Median 3Q Max 0.087276
> 0.039963 0.006201 0.064768 0.074874
>
> Coefficients: Estimate Std. Error t value Pr(>t) (Intercept)
> 0.11208 0.05101 2.197 0.0527 rep(c(1, 2.1, 2.9, 1.1, 2, 3),
> 2) 1.04731 0.02360 44.374 8.12e13
>
> (Intercept) . rep(c(1, 2.1, 2.9, 1.1, 2, 3), 2)
> ***  Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’
> 1
>
> Residual standard error: 0.06358 on 10 degrees of freedom Multiple
> Rsquared: 0.9949, Adjusted Rsquared: 0.9944 Fstatistic: 1969 on
> 1 and 10 DF, pvalue: 8.122e13
>
>  snip 
>
> I hope this helps,
>
> John
>
>  John Fox, Professor
> McMaster University Hamilton, Ontario, Canada
> http://socserv.mcmaster.ca/jfox/ On Thu, 6 Feb 2014 09:27:22 +0100
> Göran Broström < [hidden email]> wrote:
>> On 05/02/14 22:40, Marco Inacio wrote:
>>> Hello all, can help clarify something?
>>>
>>> According to R's lm() doc:
>>>
>>>> NonNULL weights can be used to indicate that different
>>>> observations have different variances (with the values in
>>>> weights being inversely *proportional* to the variances); or
>>>> equivalently, when the elements of weights are positive
>>>> integers w_i, that each response y_i is the mean of w_i
>>>> unitweight observations (including the case that there are w_i
>>>> observations equal to y_i and the data have been summarized).
>>>
>>> Since the idea here is *proportion*, not equality, shouldn't the
>>> vectors of weights x, 2*x give the same result? And yet they
>>> don't, standard errors differs:
>>>
>>>>> summary(lm(c(1,2,3,1,2,3)~c(1,2.1,2.9,1.1,2,3),weight=rep(1,6)))$sigma
>>>>
>>>>>
[1] 0.07108323
>>>>> summary(lm(c(1,2,3,1,2,3)~c(1,2.1,2.9,1.1,2,3),weight=rep(2,6)))$sigma
>>>>
>>>>>
[1] 0.1005269
>>
>> The weights are in fact case weights, i.e., a weight of 2 is the
>> same as including the corresponding item twice. I agree that the
>> documentation is no wonder of clarity in this respect.
>>
>> Btw, note that, in your example, (0.1005269 / 0.07108323)^2 = 2,
>> your constant weight.
>>
>> Göran Broström
>>>
>>>
>>> So what if I know apriori, observation A has variance 2 times
>>> bigger than observation B? Both weights=c(1,2) and weights=c(2,4)
>>> (and so on) represent very well this knowledge, but we get
>>> different regression (since sigma is different).
>>>
>>>
>>> Also, if we do the same thing with a glm() model, than we get a
>>> lot of other differences like in the deviance.
>>>
>>> ______________________________________________
>>> [hidden email] mailing list
>>> https://stat.ethz.ch/mailman/listinfo/rhelp PLEASE do read the
>>> posting guide http://www.Rproject.org/postingguide.html and
>>> provide commented, minimal, selfcontained, reproducible code.
>>>
>>
>> ______________________________________________ [hidden email]
>> mailing list https://stat.ethz.ch/mailman/listinfo/rhelp PLEASE do
>> read the posting guide http://www.Rproject.org/postingguide.html>> and provide commented, minimal, selfcontained, reproducible code.
>
>
>
______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/rhelpPLEASE do read the posting guide http://www.Rproject.org/postingguide.htmland provide commented, minimal, selfcontained, reproducible code.


Thanks for the answers.
> Dear Marco and Goran,
>
> Perhaps the documentation could be clearer, but it is after all a brief help page. Using weights of 2 to lm() is *not* equivalent to entering the observation twice. The weights are variance weights, not case weights.
>
According to your post here:
http://tolstoy.newcastle.edu.au/R/e2/help/07/05/16311.html there are 3 possible kinds of weights.
The person in this one:
http://tolstoy.newcastle.edu.au/R/e2/help/07/06/18743.html includes 2 others making a distinction between weights inverse
proportional to variance and weight equal to inverse variance.
(looking at other posts in the thread shows that other people also make
confusions on this matter)
So R's lm(), glm(), etc weights **are** the inverse of the variance of
the observations, right?
They'are not **proportional** to the inverse of variance because if this
were true, then weight and 2*weight would archive the same results, right?
I needed a method to use proportional weights on observations as I know
their proportion of variance among each other.
And it doesn't need to be a R function, just an explanation on how
construct the likehood would be fine. If anybody know an article on the
subject, would be of great help to.
______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/rhelpPLEASE do read the posting guide http://www.Rproject.org/postingguide.htmland provide commented, minimal, selfcontained, reproducible code.


Dear Marco,
What I said in the 2007 rhelp posting to which you refer is, "The weights
used by lm() are (inverse)'variance weights,' reflecting the variances of
the errors, with observations that have lowvariance errors therefore being
accorded greater weight in the resulting WLS regression." ?lm says,
"NonNULL weights can be used to indicate that different observations have
different variances (with the values in weights being inversely proportional
to the variances)."
If I understand your situation correctly, you know the error variances up to
a constant of proportionality, in which case you can set the weights
argument to lm() to the inverses of these values. As I showed you in the
example I just posted, weight and 2*weight *do* produce the same coefficient
estimates and standard errors, with the difference between the two absorbed
by the residual standard error, which is the squareroot of the estimated
constant of proportionality.
If this is insufficiently clear, I'm afraid that I'll have to defer to
someone with greater powers of explanation.
Best,
John
> Original Message
> From: [hidden email] [mailto:rhelpbounces@r
> project.org] On Behalf Of Marco Inacio
> Sent: Thursday, February 06, 2014 9:06 AM
> To: [hidden email]
> Subject: Re: [R] proportional weights
>
> Thanks for the answers.
>
> > Dear Marco and Goran,
> >
> > Perhaps the documentation could be clearer, but it is after all a
> brief help page. Using weights of 2 to lm() is *not* equivalent to
> entering the observation twice. The weights are variance weights, not
> case weights.
> >
> According to your post here:
> http://tolstoy.newcastle.edu.au/R/e2/help/07/05/16311.html> there are 3 possible kinds of weights.
>
> The person in this one:
> http://tolstoy.newcastle.edu.au/R/e2/help/07/06/18743.html> includes 2 others making a distinction between weights inverse
> proportional to variance and weight equal to inverse variance.
>
> (looking at other posts in the thread shows that other people also make
> confusions on this matter)
>
> So R's lm(), glm(), etc weights **are** the inverse of the variance of
> the observations, right?
> They'are not **proportional** to the inverse of variance because if
> this
> were true, then weight and 2*weight would archive the same results,
> right?
>
>
> I needed a method to use proportional weights on observations as I know
> their proportion of variance among each other.
> And it doesn't need to be a R function, just an explanation on how
> construct the likehood would be fine. If anybody know an article on the
> subject, would be of great help to.
>
> ______________________________________________
> [hidden email] mailing list
> https://stat.ethz.ch/mailman/listinfo/rhelp> PLEASE do read the posting guide http://www.Rproject.org/posting> guide.html
> and provide commented, minimal, selfcontained, reproducible code.
______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/rhelpPLEASE do read the posting guide http://www.Rproject.org/postingguide.htmland provide commented, minimal, selfcontained, reproducible code.


I think we can blame Tim Hesterberg for the confusion:
He writes
"
I'll add:
* inversevariance weights, where var(y for observation) = 1/weight (as opposed to just being inversely proportional to the weight) *
"
And, although I'm not a native English speaker, I think there's a spurious comma in there. The intention was clearly to have this as a 4th type of weight which is a special case of inversevariance weights, not as an elaboration on the definition of inv.var. weights.
I.e., it is the difference between
Motorists who are reckless drivers...
and
Motorists, who are reckless drivers...
pd
On 06 Feb 2014, at 16:04 , John Fox < [hidden email]> wrote:
> Dear Marco,
>
> What I said in the 2007 rhelp posting to which you refer is, "The weights
> used by lm() are (inverse)'variance weights,' reflecting the variances of
> the errors, with observations that have lowvariance errors therefore being
> accorded greater weight in the resulting WLS regression." ?lm says,
> "NonNULL weights can be used to indicate that different observations have
> different variances (with the values in weights being inversely proportional
> to the variances)."
>
> If I understand your situation correctly, you know the error variances up to
> a constant of proportionality, in which case you can set the weights
> argument to lm() to the inverses of these values. As I showed you in the
> example I just posted, weight and 2*weight *do* produce the same coefficient
> estimates and standard errors, with the difference between the two absorbed
> by the residual standard error, which is the squareroot of the estimated
> constant of proportionality.
>
> If this is insufficiently clear, I'm afraid that I'll have to defer to
> someone with greater powers of explanation.
>
> Best,
> John
>
>> Original Message
>> From: [hidden email] [mailto:rhelpbounces@r
>> project.org] On Behalf Of Marco Inacio
>> Sent: Thursday, February 06, 2014 9:06 AM
>> To: [hidden email]
>> Subject: Re: [R] proportional weights
>>
>> Thanks for the answers.
>>
>>> Dear Marco and Goran,
>>>
>>> Perhaps the documentation could be clearer, but it is after all a
>> brief help page. Using weights of 2 to lm() is *not* equivalent to
>> entering the observation twice. The weights are variance weights, not
>> case weights.
>>>
>> According to your post here:
>> http://tolstoy.newcastle.edu.au/R/e2/help/07/05/16311.html>> there are 3 possible kinds of weights.
>>
>> The person in this one:
>> http://tolstoy.newcastle.edu.au/R/e2/help/07/06/18743.html>> includes 2 others making a distinction between weights inverse
>> proportional to variance and weight equal to inverse variance.
>>
>> (looking at other posts in the thread shows that other people also make
>> confusions on this matter)
>>
>> So R's lm(), glm(), etc weights **are** the inverse of the variance of
>> the observations, right?
>> They'are not **proportional** to the inverse of variance because if
>> this
>> were true, then weight and 2*weight would archive the same results,
>> right?
>>
>>
>> I needed a method to use proportional weights on observations as I know
>> their proportion of variance among each other.
>> And it doesn't need to be a R function, just an explanation on how
>> construct the likehood would be fine. If anybody know an article on the
>> subject, would be of great help to.
>>
>> ______________________________________________
>> [hidden email] mailing list
>> https://stat.ethz.ch/mailman/listinfo/rhelp>> PLEASE do read the posting guide http://www.Rproject.org/posting>> guide.html
>> and provide commented, minimal, selfcontained, reproducible code.
>
> ______________________________________________
> [hidden email] mailing list
> https://stat.ethz.ch/mailman/listinfo/rhelp> PLEASE do read the posting guide http://www.Rproject.org/postingguide.html> and provide commented, minimal, selfcontained, reproducible code.

Peter Dalgaard, Professor
Center for Statistics, Copenhagen Business School
Solbjerg Plads 3, 2000 Frederiksberg, Denmark
Phone: (+45)38153501
Email: [hidden email] Priv: [hidden email]
______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/rhelpPLEASE do read the posting guide http://www.Rproject.org/postingguide.htmland provide commented, minimal, selfcontained, reproducible code.


> I think we can blame Tim Hesterberg for the confusion:
>
> He writes
>
> "
> I'll add:
> * inversevariance weights, where var(y for observation) = 1/weight (as opposed to just being inversely proportional to the weight) *
> "
>
> And, although I'm not a native English speaker, I think there's a spurious comma in there. The intention was clearly to have this as a 4th type of weight which is a special case of inversevariance weights, not as an elaboration on the definition of inv.var. weights.
>
> I.e., it is the difference between
>
> Motorists who are reckless drivers...
>
> and
>
> Motorists, who are reckless drivers...
>
> pd
In fact, that wasn't what caused the confusion as I have understood what
he meant despite the problem with the comma.
But I got the idea now, R uses weighted least squares and:
"Var[\epsilon  X] = \Omega" (equal, not proportion)
( https://en.wikipedia.org/wiki/Generalized_least_squares) (since WLS is
just a special case of GLS)
"The weights should, ideally, be equal to the reciprocal of the variance
of the measurement."
( https://en.wikipedia.org/wiki/Linear_least_squares_(mathematics)#Weighted_linear_least_squares)
I guess I need to find another strategy to use proportional weights
(weights know up to a constant, as John says).
So, thank you much to you all, and sorry the inconvenience I caused.
______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/rhelpPLEASE do read the posting guide http://www.Rproject.org/postingguide.htmland provide commented, minimal, selfcontained, reproducible code.


Dear Marco,
> Original Message
> From: [hidden email] [mailto:rhelpbounces@r
> project.org] On Behalf Of Marco Inacio
> Sent: Thursday, February 06, 2014 12:41 PM
> To: R help
> Subject: Re: [R] proportional weights
>
>
> > I think we can blame Tim Hesterberg for the confusion:
> >
> > He writes
> >
> > "
> > I'll add:
> > * inversevariance weights, where var(y for observation) = 1/weight
> (as opposed to just being inversely proportional to the weight) *
> > "
> >
> > And, although I'm not a native English speaker, I think there's a
> spurious comma in there. The intention was clearly to have this as a
> 4th type of weight which is a special case of inversevariance weights,
> not as an elaboration on the definition of inv.var. weights.
> >
> > I.e., it is the difference between
> >
> > Motorists who are reckless drivers...
> >
> > and
> >
> > Motorists, who are reckless drivers...
> >
> > pd
> In fact, that wasn't what caused the confusion as I have understood
> what
> he meant despite the problem with the comma.
>
> But I got the idea now, R uses weighted least squares and:
>
> "Var[\epsilon  X] = \Omega" (equal, not proportion)
> ( https://en.wikipedia.org/wiki/Generalized_least_squares) (since WLS is
> just a special case of GLS)
>
> "The weights should, ideally, be equal to the reciprocal of the
> variance
> of the measurement."
> ( https://en.wikipedia.org/wiki/Linear_least_squares_(mathematics)#Weigh> ted_linear_least_squares)
>
> I guess I need to find another strategy to use proportional weights
> (weights know up to a constant, as John says).
No, you are perfectly fine using WLS. The constant of proportionality is the
estimated error variance, i.e., the square of the residual standard error
(as I think I said earlier).
John
>
> So, thank you much to you all, and sorry the inconvenience I caused.
>
> ______________________________________________
> [hidden email] mailing list
> https://stat.ethz.ch/mailman/listinfo/rhelp> PLEASE do read the posting guide http://www.Rproject.org/posting> guide.html
> and provide commented, minimal, selfcontained, reproducible code.
______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/rhelpPLEASE do read the posting guide http://www.Rproject.org/postingguide.htmland provide commented, minimal, selfcontained, reproducible code.


> No, you are perfectly fine using WLS. The constant of proportionality is the
> estimated error variance, i.e., the square of the residual standard error
> (as I think I said earlier).
>
> John
You're right. That was a little hard for me to grasp. Thanks for the
patience.
______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/rhelpPLEASE do read the posting guide http://www.Rproject.org/postingguide.htmland provide commented, minimal, selfcontained, reproducible code.

