Comments (7)
Yes -- the last column is used as the baseline / reference. The choice here is arbitrary, and the back transformed proportions will be identical, no matter which column is set to 0
from zoid.
Ok great, closing this issue -- thanks!
from zoid.
Ok, so I do not know if it is the best, but from your function fit_zoid, I commented on those lines (because parse_re_formula will already generate the matrix, and extract random effect factor? L16)
#model_frame <- model.frame(formula, design_matrix)
#model_matrix <- model.matrix(formula, model_frame)
res <- parse_re_formula(formula, design_matrix)
from zoid.
Great questions and thanks for the help in catching issues. On the parameters:
The betas represent the mean estimates of the parameters in logit space, before being back-transformed. Maybe a clearer example would be to use a case of 3 observations (rows) and 4 groups:
y <- matrix(c(3.77, 6.63, 2.60, 0.9, 1.44, 0.66, 2.10, 3.57, 1.33, 3.4, 1.4, 5),
nrow = 3, byrow = TRUE
)
fit <- fit_zoid(data_matrix = y)
p_hat <- get_pars(fit)
Now, p_hat$betas
contains the estimated intercepts in logit space (the last is set to 0 for identifiability)
And then the back-transformed estimates of proportions are given by p_hat$p
Note that the intercepts are not varying across observations -- so they're the same for all groups. More complicated models with fixed / random effects could make them vary
from zoid.
For the question about the error and random effects, I'm not sure there's anything wrong here? I was able to run the example just fine (I realize there was the warning message, and just have pushed a commit to suppress that message)
set.seed(123)
y <- matrix(runif(99,1,4), ncol=3)
design <- data.frame("fac" = sample(letters[1:5], size=nrow(y), replace=TRUE))
design$fac <- as.factor(design$fac)
fit<-fit_zoid(formula=~(1|fac),design_matrix=design,data_matrix=y,chains=1,iter=100)
What's the results of sessionInfo()?
Here's mine:
from zoid.
Thanks for the fast answer! :) but in your example, how is the variable defined at 0 (the group you use by default)? In your first screenshot we can see that m = 4, the coefficient is at 0. Does this mean that you are using the 4th column from Y as a reference? Or is it the first column? If I am asking, it's because by default in brms::, when you are fitting a dirichlet model, it will use the first column as "reference category"
from zoid.
OK, I found the issue,...!
I used in my code
options(na.action = "na.fail")
And because this function was loaded at the beginning of the code, I did not pay enough attention to it. Thanks a lot for your answers and your help!
from zoid.
Related Issues (6)
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from zoid.