My approach to problems like this is to write down the proposed model mathematically first, in extreme detail. I find hierarchical form to be the easiest way to break it down piece by piece. Once I have the maths then I turn it into a Stan model. Last step is to use the Stan output to answer the research questions. Source: 11 months ago
For instance my first choice in these cases is always a Bayesian inference tool like Stan. In my experience as someone who’s more of a programmer than mathematician/statistician, Bayesian tools like this make it much easier to not accidentally fool yourself with assumptions, and they can be pretty good at catching statistical mistakes. Source: 12 months ago
I tend to be most impressed by tools and libraries. The stuff that has most impressed me in my time in ML is stuff like pytorch and Stan, tools that allow expression of a wide variety of statistical (and ML, DL models, if you believe there's a distinction) models and inference from those models. These are the things that have had the largest effect in my own work, not in the sense of just using these tools, but... Source: 12 months ago
Oh its certainly used in practice. You should look into frameworks like Stan[1] and pyro[2]. I think bayesian models are seen as more explainable so they will be used in industries that value that sort of thing [1] https://mc-stan.org/. - Source: Hacker News / about 1 year ago
At this point the only people using such things are the programmers. Think e.g. STAN. https://mc-stan.org/ the rest of us: R, SAS, Excel. Source: about 1 year ago
Before machine learning I’d strongly recommend using Bayesian modeling like with stan. There’s a variety of Bayesian modeling tools but I’ve used that one the most. Source: over 1 year ago
Well it sounds a lot like you are listening to developers talk about coding languages they like for high performance compute. This is not what you want to be spending all your time doing afaik. The more appropriate languages to get into would be the classic Python and R. Julia if you dont give a shit about productionizing your code and https://mc-stan.org/ Stan if you are really locked into bayesian inference and... Source: over 1 year ago
I'd say take a look at Stan (https://mc-stan.org/). Source: over 1 year ago
Even if RStudio & the Tidyverse have mostly been promoting a functional programming style in R, it has full support for OOP (see R6 or R7 for more modern implementations of it). Let's not even mention the excellent Stan ecosystem for Probabilistic programming / Bayesian modeling, or Bioconductor, the biggest repository of bioinformatics packages & tools of any language. Source: over 1 year ago
This sounds like a case for a nonlinear random effects model (without any AR component). I like to fit such models using Stan, via rstan, although it has quite the learning curve. Source: over 1 year ago
After this I plan to do a series on regression in R, with a focus on Bayesian models using stan. Source: over 1 year ago
I guess you could go that route, but I don't think there's much you could do with that other than simulate the draws. That doesn't have nearly the level of structure as something like a STAN model, for instance. Source: over 1 year ago
However, I am not very familiar with Bayesian statistics or the software used. I looked into OpenBUGS and Stan, which both can be used with R in Linux. However, the syntax seem very complex in comparison to any SEM software I've encountered before. Furthermore, searching for any literature on the subject (articles, examples, documentation, etc.), I can find some on SEM with ordinal data and some on multilevel SEM,... Source: almost 2 years ago
I think there’s an interface to Stan via MATLAB, but if you can, better to use either R or Python as the help/community for stats is better for those Languages. Source: about 2 years ago
Okay so first off, I recommend that you read [this](https://link.springer.com/article/10.3758/s13423-016-1221-4) article about "The Bayesian New Statistics", which highlights estimation rather than hypothesis testing from a Bayesian perspective (see Fig. 1, second row, second column). Instead of a t-test, then, we can *estimate the difference* between two groups/variables. If you want to go deeper than JASP etc, I... Source: about 2 years ago
As others have said, R for academia, Python for industry. However, I'd also throw Stan into the mix, along with other PPL frameworks like Tensorflow Probability and Pyro. The latter two will require you to learn Python first, though. Source: about 2 years ago
How does pomp compare to mc-stan? I thought that was the preferred tool these days. https://mc-stan.org/. - Source: Hacker News / about 2 years ago
> I wonder if the tricky part is in choosing random vectors? Sampling vectors from multidimensional random distributions is a well studied problem. For example the open source project https://mc-stan.org implemented several (at the time) state of the art methods like Hamiltonian Monte Carlo with the help of Automatic Differentiation. - Source: Hacker News / over 2 years ago
Probabilistic programming uses computer science techniques to do automated statistical modeling. For example, imagine I have a coin, and I want to discover if it is biased, i.e. If it lands on heads more often than tails. In a probabilistic programming framework, I can express my model as a simple Bernoulli model, `x ~ Bernoulli(p)`, and then automatically estimate the bias parameter `p` given some data (do... - Source: Hacker News / over 2 years ago
Not a language, but Stan is worth looking into if you are interested in Bayesian modeling. Source: over 2 years ago
This tutorial explains what is probabilistic programming & provides a review of 5 frameworks (PPLs) using an example taken from Chapter 4 of Statistical Rethinking by Dr. Richard McElreath. Frameworks (PPLs) reviewed are - Stan (https://mc-stan.org/) PyMC3 (https://docs.pymc.io/) Tensorflow Probability (https://www.tensorflow.org/probability) Pyro/NumPyro (https://pyro.ai/) Turing.jl... Source: over 2 years ago
Do you know an article comparing MC Stan to other products?
Suggest a link to a post with product alternatives.
This is an informative page about MC Stan. You can review and discuss the product here. The primary details have not been verified within the last quarter, and they might be outdated. If you think we are missing something, please use the means on this page to comment or suggest changes. All reviews and comments are highly encouranged and appreciated as they help everyone in the community to make an informed choice. Please always be kind and objective when evaluating a product and sharing your opinion.