R - Comparing BIC Results Between Expectation-Maximization (EM) and Linear Regression (LR) Algorithm

classic Classic list List threaded Threaded
2 messages Options
Reply | Threaded
Open this post in threaded view
|

R - Comparing BIC Results Between Expectation-Maximization (EM) and Linear Regression (LR) Algorithm

andikapa
Hi there,

I am trying to compare result of BIC (Bayesian Information Criterion)
between Expectation-Maximization (EM) and Linear Regression (LR) Algorithm
on "Hotel Occupancy" data using R, for my college task.

The data contains data occupancy percentage from January to December 2017,
based on islands in Indonesia.

The result I got :
- for EM : -2687.035
- for LR : 225.0898

*notes :
- For EM, I use mclust packages, then I type mclustBIC(variable name)
- For LR, I type BIC(MonthA~MonthB) etc (every 2 month), then I count the
average as the BIC result.

I don't know how to compare it, which BIC result is better (EM or LR)?

Can you explain the reason please?
Thanks in advance!

Regards,
Andika.

        [[alternative HTML version deleted]]

______________________________________________
[hidden email] 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.
Reply | Threaded
Open this post in threaded view
|

Re: R - Comparing BIC Results Between Expectation-Maximization (EM) and Linear Regression (LR) Algorithm

Sarah Goslee
Hi Andika,

We don't do homework on this list, and your question is a statistics
question rather than an R question anyway.

That said, googling "interpreting BIC" should get you going, if
talking to your professor and reading your textbook haven't helped.

Sarah

On Wed, Nov 28, 2018 at 11:30 AM Andika Putra Agustian
<[hidden email]> wrote:

>
> Hi there,
>
> I am trying to compare result of BIC (Bayesian Information Criterion)
> between Expectation-Maximization (EM) and Linear Regression (LR) Algorithm
> on "Hotel Occupancy" data using R, for my college task.
>
> The data contains data occupancy percentage from January to December 2017,
> based on islands in Indonesia.
>
> The result I got :
> - for EM : -2687.035
> - for LR : 225.0898
>
> *notes :
> - For EM, I use mclust packages, then I type mclustBIC(variable name)
> - For LR, I type BIC(MonthA~MonthB) etc (every 2 month), then I count the
> average as the BIC result.
>
> I don't know how to compare it, which BIC result is better (EM or LR)?
>
> Can you explain the reason please?
> Thanks in advance!
>
> Regards,
> Andika.
>
>         [[alternative HTML version deleted]]
>
> ______________________________________________
> [hidden email] 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.



--
Sarah Goslee (she/her)
http://www.numberwright.com

______________________________________________
[hidden email] 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.