Last week I re-blogged a post introducing Approximate Bayesian Computation. I thought some of the content was a little foreign, so I wanted to give an intro to the intro. ABC core concept Say we have a process that is controlled by a parameter - say the slope in $latex y = m\cdot x+b$, or… Continue reading Introduction to an Introduction to Approximate Bayesian Computation (ABC)
In this post I talk about my motivation to complete a degree in statistics during my PhD, and all the failures that went into that decision.
It's been quite a while since I updated this tutorial series- better late than never? Introduction First, we determine the distribution our data comes from, or the likelihood, and any prior information is described using the prior distribution. Then we use Markov chain Monte Carlo to explore this posterior. Then we determine if we need… Continue reading Bayesian statistics part 4 – R tutorial
I made a poster format in latex for my presentation last year at the Society for Mathematical Biology annual meeting. This paper was just accepted for publication! 😀 Check out the source files here. This poster is 3'x4'. Some of the formatting is a bit creative, but in general I used the tcolorbox package to… Continue reading Latex poster format – Cool tones
Spoonflower offers custom digitally printed fabric for only 22$. Choose "performance knit" as your fabric, and the yard size is a generous 54". You can print any size poster by centering the image and trimming later on. Check out how nice the text looks in this shot - take into consideration my potato camera! https://www.instagram.com/p/Bgwb1SqARnj/?taken-by=ultimate_algorithm_cyborg… Continue reading How to make a 20$ fabric poster
Last week was the Plantae Seminar "Computational Plant Science - Science at the Interface of Math, Computer Science, and Plant Biology with Alexander Bucksch": Dr. Bucksch mentions using two clustering techniques - B splines and K-means clustering. I've discussed K-means clustering in a previous post to analyze predictors of success in Settlers of Catan. B splines… Continue reading Computational Plant Science – Clustering in R Tutorial
Ask me anything anonymously (or non-anonymously) using this Google form: https://goo.gl/forms/JIAIGvvLYATAuEjv2 You can also ask questions on the blog or on the Plantae BDCI network!
The two most popular Markov chain Monte Carlo sampling algorithms are Gibbs sampling and Metropolis Hastings. These algorithms produce Markov chains. Numbers inside a Markov chain are dependent on only the previous number. In the context of sampling, we check the probability of the proposed value based on only the probability of the current value,… Continue reading Introduction to Bayesian Statistics, Part 3
As mentioned in Part 1, in Bayesian statistics you summarize a priori knowledge in the prior, and your data in the likelihood. The prior distribution is often chosen based on analytical convenience, while the likelihood is chosen based on the underlying sampling distribution (read about some appropriate distributions here). Multiplying these together produces the posterior distribution. Probability… Continue reading Introduction to Bayesian statistics, Part 2
Many people are aware of the normal distribution or "bell curve". What are some other probability distributions and when are they useful? You can think of a probability distribution as a collection of the number of times something happened. For example, how many students get which grade (70%, 73%, 94%, etc). We can visualize this… Continue reading Probability distributions that aren’t Normal