R help - May 2019 - Generating nested models for order selection tests

Hello everyone,

I have created a parametric additive model for the median house price (as
the response) and with the number of tax forms (x1) and the number of
healthcare facilities (x2) as my covariates. I should mention that both of
the covariates have quadratic effects in my model.

Now I want to do a hypothesis testing. I am taking the mentioned parametric
model as my null state (hypothesis) and I want to use "order selection
test" to test it against a nonparametric alternative hypothesis. Based on
what I understood from few related articles I have read, I should create a
sequence of nested models. I am thinking about using polynomial or cosine
functions as my basis function. In either case, I have to create a series
of models (i.e. the sequence of nested models via series expansion) based
on the basis function to test the hypothesis.
Is there any way to do this automatically in R?

Kind regards,
readyToLearn

	[[alternative HTML version deleted]]

Purely statistical questions are generally off topic here, and your query
may fall under that rubric. But you should try searching at rseek.org and R
task views -- https://cran.r-project.org/web/views/  -- perhaps under the
SocialScience heading or others that may use the methodology to which you
refer.

Cheers,
Bert

On Fri, May 24, 2019 at 8:48 AM Ready Learner <readytolearn90 at
gmail.com>
wrote:
> Hello everyone,
>
> I have created a parametric additive model for the median house price (as
> the response) and with the number of tax forms (x1) and the number of
> healthcare facilities (x2) as my covariates. I should mention that both of
> the covariates have quadratic effects in my model.
>
> Now I want to do a hypothesis testing. I am taking the mentioned parametric
> model as my null state (hypothesis) and I want to use "order selection
> test" to test it against a nonparametric alternative hypothesis. Based
on
> what I understood from few related articles I have read, I should create a
> sequence of nested models. I am thinking about using polynomial or cosine
> functions as my basis function. In either case, I have to create a series
> of models (i.e. the sequence of nested models via series expansion) based
> on the basis function to test the hypothesis.
> Is there any way to do this automatically in R?
>
> Kind regards,
> readyToLearn
>
>         [[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]]

Dear Bert,

Thank you for your response. I apologize for getting back to you a little
late.
I do not think that my question is statistical. As a matter of fact, I do
know what I want to do in terms of statistics. The problem is that I do not
know how I can do it via R. To be more precise my question is: Is there a
way to create a sequence of nested models via series expansion (based on a
basis function) in R?

All the best,
RL

On Fri, May 24, 2019 at 6:49 PM Bert Gunter <bgunter.4567 at gmail.com>
wrote:
> Purely statistical questions are generally off topic here, and your query
> may fall under that rubric. But you should try searching at rseek.org and
> R task views -- https://cran.r-project.org/web/views/  -- perhaps under
> the SocialScience heading or others that may use the methodology to which
> you refer.
>
> Cheers,
> Bert
>
> On Fri, May 24, 2019 at 8:48 AM Ready Learner <readytolearn90 at
gmail.com>
> wrote:
>
>> Hello everyone,
>>
>> I have created a parametric additive model for the median house price
(as
>> the response) and with the number of tax forms (x1) and the number of
>> healthcare facilities (x2) as my covariates. I should mention that both
of
>> the covariates have quadratic effects in my model.
>>
>> Now I want to do a hypothesis testing. I am taking the mentioned
>> parametric
>> model as my null state (hypothesis) and I want to use "order
selection
>> test" to test it against a nonparametric alternative hypothesis.
Based on
>> what I understood from few related articles I have read, I should
create a
>> sequence of nested models. I am thinking about using polynomial or
cosine
>> functions as my basis function. In either case, I have to create a
series
>> of models (i.e. the sequence of nested models via series expansion)
based
>> on the basis function to test the hypothesis.
>> Is there any way to do this automatically in R?
>>
>> Kind regards,
>> readyToLearn
>>
>>         [[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]]