Michael's GitHub Space
I'm Michael, and I do all manner of things within the realm of data science. Here you'll find source code for modeling, packages, general programming, and various other things.
Covers the basics of mixed models, mostly using @lme4
Home Page: https://m-clark.github.io/mixed-models-with-R/
In keeping with glmmTMB and brms notation, and following Bolker's demo. Probably best for appendix.
Your deck is truly an excellent introduction to mixed models. I wish it had existed 3 years ago!
One thing I think is missing is a note on how to do hypothesis testing using LME.
I ended up using something like this
#adding groups fixed effect
model.test <-lmer(metric~experiment_treat+
(1|user_id)+(1|days_in),data=experiment_session_df,REML=F)
# create a test
anova(model.null,model.test) %>%
data.frame() %>%
display(.)
#display the model
model.test %>%
display(.)
Where experiment_treat is the independent variable I really care about, but I want to extract the effect of user and time, while seeing the effect of time (days_in).
It would be good to have something about doing these kinds of hypothesis tests in your guide.
Cheers,
James
Hi Clark,
first of all thank you for this precious guides. I just want to ask you if there is the possibility to publish the related R snippets code (eg all the plots codes). Thanks in advance
In Issues/Convergence, add link to post
Great book! Just finished it up. In the appendix you mentioned that Python and Julia offer a subset of modeling options that R does. You also mentioned that you've been able to build some models in R with over a million records. Do you know if Julia (or Python) can process larger amounts of data than R for running these types of models or any run time advantages? I would like to think Julia could but I'm not sure what the bottleneck is in the training of these models or to what extent there are multi-threading opportunities... Again, great book!
in first nested example use the default ward identifier (i.e. 'ward'), making for more comparison to nesting vs. crossed section later.
use gganimate or at least add another level of transparency to clean up the spaghetti plots
currently is a folder within the older version of the folder
Thank you for such a nice Package.
The initial part where using of merTools came off as confusing to most.
If possible try to provide format that might be more print friendly. Currently epub will break with html based images (won't print any subsequent text), but perhaps it will be more viable in the future. PDF at present seems incompatible with the current approach.
A current solution is to minimize the menu, which is more print friendly than retaining.
https://m-clark.github.io/sem/latent-growth-curves.html
in issues.Rmd is not working
Discuss issues/difficulty, demo no more than two ways.
Perhaps make a separate chapter given the utility/importance
In the issues section, add link for mgcv, lme4, glmmTMB comparisons
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.