Ok, thanks for the suggestions. I will look into that. And you are absolutely
right that I should have been more clear about what type of weighting I want.
So to clarify: I run time series regressions of returns of company i on two
different sets of explanatory variables. Then I extract the resp
On 21 Nov 2014, at 19:18, David Winsemius wrote:
>
> On Nov 21, 2014, at 6:52 AM, ivan wrote:
>
>> I am aware of the fact that bootstrapping produces different CIs with every
>> run. I still believe that there is a difference between both types of
>> procedures. My understanding is that sett
On Nov 21, 2014, at 6:52 AM, ivan wrote:
> I am aware of the fact that bootstrapping produces different CIs with every
> run. I still believe that there is a difference between both types of
> procedures. My understanding is that setting "w" in the boot() function
> influences the "importance"
I am aware of the fact that bootstrapping produces different CIs with every
run. I still believe that there is a difference between both types of
procedures. My understanding is that setting "w" in the boot() function
influences the "importance" of observations or how the bootstrap selects
the obse
On Nov 20, 2014, at 2:23 AM, i.petzev wrote:
> Hi David,
>
> sorry, I was not clear.
Right. You never were clear about what you wanted and your examples was so
statistically symmetric that it is still hard to see what is needed. The
examples below show CI's that are arguably equivalent. I can
Hi David,
sorry, I was not clear. The difference comes from defining or not defining �w�
in the boot() function. The results with your function and your approach are
thus:
set.seed()
x <- rnorm(50)
y <- rnorm(50)
weights <- runif(50)
weights <- weights / sum(weights)
dataset <- cbind(x,y,we
On Nov 19, 2014, at 6:08 AM, i.petzev wrote:
> Hi David,
>
> thanks a lot for the response. I see that this works. I am not sure, however,
> what the appropriate way to do this is. It also works if you do not define
> weights in the boot() function (weighted bootstrap) but rather in the
> vw_
Hi David,
thanks a lot for the response. I see that this works. I am not sure, however,
what the appropriate way to do this is. It also works if you do not define
weights in the boot() function (weighted bootstrap) but rather in the vw_m_diff
function (ordinary bootstrap), i.e.,
vw_m_diff <-
On Nov 14, 2014, at 3:18 PM, David Winsemius wrote:
>
> On Nov 14, 2014, at 12:15 PM, ivan wrote:
>
>> Hi,
>>
>> I am trying to compute bootstrap confidence intervals for weighted means of
>> paired differences with the boot package. Unfortunately, the weighted mean
>> estimate lies out of the
On Nov 14, 2014, at 12:15 PM, ivan wrote:
> Hi,
>
> I am trying to compute bootstrap confidence intervals for weighted means of
> paired differences with the boot package. Unfortunately, the weighted mean
> estimate lies out of the confidence bounds and hence I am obviously doing
> something wro
Hi,
I am trying to compute bootstrap confidence intervals for weighted means of
paired differences with the boot package. Unfortunately, the weighted mean
estimate lies out of the confidence bounds and hence I am obviously doing
something wrong.
Appreciate any help. Thanks. Here is a reproducible
11 matches
Mail list logo
