R help - Sep 2016 - Run a fixed effect regression and a logit regression on a national survey that need to be "weighted"

I am a beginner user of R. I am using a national survey to test what
variables influence the partecipation in complementary pensions (the
partecipation in complementary pension is voluntary in my country).

Since the dependent variable is a dummy (1 if the person partecipate and 0
otherwise) I want to run a logit or probit regression; moreover I want to
run a fixed effect regression since I subset the survey in order to have
only the individuals interviewed more than one time.

The data frame is composed by several social and economical variables and
it also contain a variable "weight" which is the survey weight (they
are
weighting coefficients to adjust the results of the sample to the national
data).

 family pers sex income pension1     10    1   F  10000       12
20    1   F  20000       13     20    2   M  40000       04     30
1   M  25000       05     30    2   F  50000       06     40    1   M
60000       1

pers is the component of the family and pension takes 1 if the person
partecipate to complementary pension (it is a semplification of the
original survey, which contains more variables and observation (aroun 22k
observations)).

I know how to use the plm and glm functions for a fixed effect or logit
regressoin; in this case I don't know what to do since I need to take
account of the survey weights.

I used the svydesing function to "weight" the data frame:

df1 <- svydesign(ids=~1, data=df, weights=~dfweight)

I used ids=~1 because there isn't a "cluster" variable in the
survey (I
know that the towns are ramdomly selected and then individuals are ramdomly
selected, but there isn't a variable that indicate the stratification).

At this point I am lost: I don't know if it is right to use the survey
package and then what function use to run the regression, or there is a way
to use the plm or glm functions taking account of the weights.

I tried so hard to search a solution on the website but if you could give
me an answer I'd be glad.

	[[alternative HTML version deleted]]

If you want your records to be weighted by the survey weights during the
analysis, then use the weights= argument of the glm() function.

Jean

On Tue, Sep 20, 2016 at 5:04 AM, laura roncaglia <roncaglia.laura at
gmail.com>
wrote:
> I am a beginner user of R. I am using a national survey to test what
> variables influence the partecipation in complementary pensions (the
> partecipation in complementary pension is voluntary in my country).
>
> Since the dependent variable is a dummy (1 if the person partecipate and 0
> otherwise) I want to run a logit or probit regression; moreover I want to
> run a fixed effect regression since I subset the survey in order to have
> only the individuals interviewed more than one time.
>
> The data frame is composed by several social and economical variables and
> it also contain a variable "weight" which is the survey weight
(they are
> weighting coefficients to adjust the results of the sample to the national
> data).
>
>  family pers sex income pension1     10    1   F  10000       12
> 20    1   F  20000       13     20    2   M  40000       04     30
> 1   M  25000       05     30    2   F  50000       06     40    1   M
> 60000       1
>
> pers is the component of the family and pension takes 1 if the person
> partecipate to complementary pension (it is a semplification of the
> original survey, which contains more variables and observation (aroun 22k
> observations)).
>
> I know how to use the plm and glm functions for a fixed effect or logit
> regressoin; in this case I don't know what to do since I need to take
> account of the survey weights.
>
> I used the svydesing function to "weight" the data frame:
>
> df1 <- svydesign(ids=~1, data=df, weights=~dfweight)
>
> I used ids=~1 because there isn't a "cluster" variable in the
survey (I
> know that the towns are ramdomly selected and then individuals are ramdomly
> selected, but there isn't a variable that indicate the stratification).
>
> At this point I am lost: I don't know if it is right to use the survey
> package and then what function use to run the regression, or there is a way
> to use the plm or glm functions taking account of the weights.
>
> I tried so hard to search a solution on the website but if you could give
> me an answer I'd be glad.
>
>         [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/
> posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
>
	[[alternative HTML version deleted]]

Thank you for the answer but I had already tried that way; when I introduce
weights in the glm appears the error:

Warning: non-integer #successes in a binomial glm!

I tried to run the glm regression using the family quasibinomial:

eq <- glm(pip ~ men + age_pr + age_c + I(age_pr^2) + I(age_c^2),
weights = dfweights, data = df, family = quasibinomial(link "logit"))

Do you think it could be a right solution?

2016-09-20 18:23 GMT+02:00 Adams, Jean <jvadams at usgs.gov>:
> If you want your records to be weighted by the survey weights during the
> analysis, then use the weights= argument of the glm() function.
>
> Jean
>
> On Tue, Sep 20, 2016 at 5:04 AM, laura roncaglia <
> roncaglia.laura at gmail.com> wrote:
>
>> I am a beginner user of R. I am using a national survey to test what
>> variables influence the partecipation in complementary pensions (the
>> partecipation in complementary pension is voluntary in my country).
>>
>> Since the dependent variable is a dummy (1 if the person partecipate
and 0
>> otherwise) I want to run a logit or probit regression; moreover I want
to
>> run a fixed effect regression since I subset the survey in order to
have
>> only the individuals interviewed more than one time.
>>
>> The data frame is composed by several social and economical variables
and
>> it also contain a variable "weight" which is the survey
weight (they are
>> weighting coefficients to adjust the results of the sample to the
national
>> data).
>>
>>  family pers sex income pension1     10    1   F  10000       12
>> 20    1   F  20000       13     20    2   M  40000       04     30
>> 1   M  25000       05     30    2   F  50000       06     40    1   M
>> 60000       1
>>
>> pers is the component of the family and pension takes 1 if the person
>> partecipate to complementary pension (it is a semplification of the
>> original survey, which contains more variables and observation (aroun
22k
>> observations)).
>>
>> I know how to use the plm and glm functions for a fixed effect or logit
>> regressoin; in this case I don't know what to do since I need to
take
>> account of the survey weights.
>>
>> I used the svydesing function to "weight" the data frame:
>>
>> df1 <- svydesign(ids=~1, data=df, weights=~dfweight)
>>
>> I used ids=~1 because there isn't a "cluster" variable in
the survey (I
>> know that the towns are ramdomly selected and then individuals are
>> ramdomly
>> selected, but there isn't a variable that indicate the
stratification).
>>
>> At this point I am lost: I don't know if it is right to use the
survey
>> package and then what function use to run the regression, or there is a
>> way
>> to use the plm or glm functions taking account of the weights.
>>
>> I tried so hard to search a solution on the website but if you could
give
>> me an answer I'd be glad.
>>
>>         [[alternative HTML version deleted]]
>>
>> ______________________________________________
>> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
>> https://stat.ethz.ch/mailman/listinfo/r-help
>> PLEASE do read the posting guide http://www.R-project.org/posti
>> ng-guide.html
>> and provide commented, minimal, self-contained, reproducible code.
>>
>>
>
	[[alternative HTML version deleted]]