Publications by Robert
Dataviz of the week, 12/4/17
This week, a chart with some Bayesian polemic behind it. Alexander Etz put this on Twitter: He is working on an R package to provide easy Bayesian adjustments for reporting bias with a method by Guan & Vandekerchhove. Imagine a study reporting three p-values, all just under the threshold of significance, and with small-ish sample sizes. Sound s...
1702 sym 8 img
SVG from stats software: the good, the bad and the ugly
What and why If there could only be one file format to save your charts in, it should be SVG. It stands for So Very Good (not really). But there’s good SVG and not so good SVG, and I want to explore that a little here, while also hopefully winning over some new SVG fans. I’m going to use scatterplots throughout of Ronald Fisher’s classic ir...
10846 sym 26 img
Using Stata and R together
I’m running a one day course with Timberlake, Stata’s UK distributors on this topic. We’ll run it next Friday the 9th of March and again later in the year (10 Aug, 6 Dec), each time at Cass Business School in the City of London. If you use one of these, and have at least had a quick look at the other, then this course is for you. I won’t ...
1565 sym
A one-day course in using Stata and R together: running twice in 2018
I am going to be giving this course on 10 August and 6 December this year. It is organised by Timberlake Consultants, the distributors of Stata for UK and Ireland, and will take place at Cass Business School’s excellent facilities in the City of London. I am excited to offer this new course because I think there is a real gap in the market here...
2860 sym 2 img
A webinar and online workshop for learning Bayesian analysis
I am running a couple of online events through BayesCamp next month that might interest you if you want to learn more about Bayesian analysis. Firstly, the Bayesian Taster webinar. This lasts for one hour and costs only ten of those British pounds (currently, 13 USD or 11 EUR). There’s no maths and no coding; this is for complete beginners and ...
2160 sym
Data visualization with statistical reasoning: seeing uncertainty with the bootstrap
This blog post is one of a series highlighting specific images from my book Data Visualization: charts, maps and interactive graphics. This is from Chapter 8, “Visualizing Uncertainty”. Why? One of the most common concerns that I hear from dataviz people is that they need to visualise not just a best estimate about the behaviour of their data...
7235 sym 4 img
Randomisation tests comparing dependent correlations
This is about some academic work I did that never got published. But, I think it should be out there as you might find it useful. Here’s the motivation. You measure three variables, A, B, and Z. You are interested in whether the correlation between A and Z is different to that between B and Z. Of course, they are not independent sampling distri...
5375 sym
Machine Learning explained for statistics folk
I’m running a one-day workshop called “From Statistics To Machine Learning” in central London on 28 October, for anyone who learnt some statistics and wants to find out about machine learning methods. I guess you might feel frustrated. There’s a lot of interest and investment in machine learning, but it’s hard to know where to start lea...
3458 sym
Books for sale!
I’m clearing out some books. You can buy them! They are all good ones, it’s just that I don’t need to have hard copies filling up my (already bulging) shelves. They are all cheaper than Amazon, although shipping beyond the EU is more expensive as I don’t have my own logistics empire. Logistic regression yes, logistics empire no. Here’s ...
3713 sym 2 img
Introductory course on Bayesian data analysis for beginners with Rasmus Bååth
On 25 November 2019, BayesCamp will be hosting a one-day course called Get up and running with Bayesian data analysis, in central London. I am delighted that this will be taught by Rasmus Bååth from Lund University and King Entertainment. That makes him the statistician behind Candy Crush. His YouTube videos introducing Bayes are very popular, ...
2059 sym