Future plans

[DominiqueMakowski]

Dear @tszanalytics, I am very interested in this great package (thanks 😃). However, I am wondering whether there were any plans to: 1) implement higher-level functions (e.g. bayesian_ttest()) similarly to the BayesFactor R package, that would ease the use of the procedures you developed (especially for new users) 2) support correlation tests? As correlation tests are currently not supported by Julia, implementing a Bayesian support could be a good alternative (and drag in new users)

Thank you for your work

[tszanalytics]

Hi Dominique,

Thanks for your comments and suggestions! I like both of your ideas. I have been planning to create a t-test function for a while, so your email prodded me to have a go at it. My initial version is in the attached code, along with an example of use. I would love to hear your feedback on how it should be modified, etc., if you get a chance to look at it. I"m planning to make the plot and the formatting of the output a bit nicer, and thinking about what else might need to reported.

I will look into creating a correlation test function also. I made a start, but I've been having problems getting Julia and Juno to behave and work properly since they released 0.7/1.0, so it may take me a little while to get that up and running. I will send you the code to have a look at if you are interested.

Best, Jeff

Jeffrey A. Mills Department of Economics, ML 0371 University of Cincinnati, OH 45221 jeffrey.mills@uc.edu

On Mon, Sep 10, 2018 at 2:26 AM Dominique Makowski notifications@github.com wrote:

Dear @tszanalytics https://github.com/tszanalytics, I am very interested in this great package (thanks 😃). However, I am wondering whether there were any plans to:

1. implement higher-level functions (e.g. bayesian_ttest()) similarly to the BayesFactor https://github.com/richarddmorey/BayesFactor R package, that would ease the use of the procedures you developed (especially for new users)
2. support correlation tests? As correlation tests are currently not supported https://github.com/JuliaStats/HypothesisTests.jl/issues/131 by Julia, implementing a Bayesian support could be a good alternative (and drag in new users)

Thank you for your work

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/tszanalytics/BayesTesting.jl/issues/1, or mute the thread https://github.com/notifications/unsubscribe-auth/Aa6vFVWJh6gLDMDT8xSsndLPnKlyFj9Gks5uZgYlgaJpZM4Wgx-r .

[tszanalytics]

Sorry, forgot to attach the code. Here it is.

On Thu, Sep 13, 2018 at 12:21 PM Jeff Mills tszanalytics@gmail.com wrote:

Hi Dominique,

Thanks for your comments and suggestions! I like both of your ideas. I have been planning to create a t-test function for a while, so your email prodded me to have a go at it. My initial version is in the attached code, along with an example of use. I would love to hear your feedback on how it should be modified, etc., if you get a chance to look at it. I"m planning to make the plot and the formatting of the output a bit nicer, and thinking about what else might need to reported.

I will look into creating a correlation test function also. I made a start, but I've been having problems getting Julia and Juno to behave and work properly since they released 0.7/1.0, so it may take me a little while to get that up and running. I will send you the code to have a look at if you are interested.

Best, Jeff

Jeffrey A. Mills Department of Economics, ML 0371 University of Cincinnati, OH 45221 jeffrey.mills@uc.edu

On Mon, Sep 10, 2018 at 2:26 AM Dominique Makowski < notifications@github.com> wrote:

Dear @tszanalytics https://github.com/tszanalytics, I am very interested in this great package (thanks 😃). However, I am wondering whether there were any plans to:

1. implement higher-level functions (e.g. bayesian_ttest()) similarly to the BayesFactor https://github.com/richarddmorey/BayesFactor R package, that would ease the use of the procedures you developed (especially for new users)
2. support correlation tests? As correlation tests are currently not supported https://github.com/JuliaStats/HypothesisTests.jl/issues/131 by Julia, implementing a Bayesian support could be a good alternative (and drag in new users)

Thank you for your work

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/tszanalytics/BayesTesting.jl/issues/1, or mute the thread https://github.com/notifications/unsubscribe-auth/Aa6vFVWJh6gLDMDT8xSsndLPnKlyFj9Gks5uZgYlgaJpZM4Wgx-r .

[DominiqueMakowski]

Dear @tszanalytics, I am afraid you didn't attach the code you mention :relaxed: You can send it to me via email (dom.makowski@gmail.com) if needed, I'll be glad to take a look

[DominiqueMakowski]

Closing this :)