Assess Variable Importance In GRNN
Technically speaking, there is no need to evaluate the variable importance and to perform the variable selection in the training of a GRNN. It’s also been a consensus that the...continue reading.
Category: Statistics
Hyper-Parameter Optimization of General Regression Neural Networks
A major advantage of General Regression Neural Networks (GRNN) over other types of neural networks is that there is only a single hyper-parameter, namely the sigma. In the previous post...continue reading.
JRSS: Series B read paper and comparison with other unbiased estimators
Hi all, The paper “unbiased Markov chain Monte Carlo with couplings” co-written with John O’Leary and Yves Atchadé has been accepted as a read paper in JRSS: Series B, to...continue reading.
BayesBag, and how to approximate it
Hi all, This post describes how unbiased MCMC can help in approximating expectations with respect to “BayesBag”, an alternative to standard posterior distributions mentioned in Peter Bühlmann‘s discussion of Big...continue reading.
Five levels of analytical automation
I have been thinking more about how programming that requires minimal human input is a virtue in computer science, and … Morecontinue reading.
Coding algorithms in R for models written in Stan
Hi all, On top of recommending the excellent autobiography of Stanislaw Ulam, this post is about using the software Stan, but not directly to perform inference, instead to obtain R...continue reading.
Debuting in a VFL/AFL Grand Final is rare
When Marlion Pickett runs onto the M.C.G for Richmond in the AFL Grand Final this Saturday, he’ll be only the sixth player in 124 finals to debut on the big...continue reading.
Multiple imputation support in Finalfit
We are using multiple imputation more frequently to “fill in” missing data in clinical datasets. Multiple datasets are created, models run, and results pooled so conclusions can be drawn. We’ve...continue reading.
She was like omg, and I was like no way
Why are there zombie stats (they’re not true, and nobody really believes them anyway, yet they refuse to die)? I … Morecontinue reading.
poor statistics
I came over the weekend across this graph and the associated news that the county of Saint-Nazaire, on the southern border of Brittany, had a significantly higher rate of cancers...continue reading.
Le Monde puzzle [#1111]
Another low-key arithmetic problem as Le Monde current mathematical puzzle: Notice that there are 10 numbers less than, and prime with 11, 100 less than and prime with 101, 1000...continue reading.
Develop Performance Benchmark with GRNN
It has been mentioned in https://github.com/statcompute/GRnnet that GRNN is an ideal approach employed to develop performance benchmarks for a variety of risk models. People might wonder what the purpose of...continue reading.
Survival analysis with strata, clusters, frailties and competing risks in in Finalfit
Background In healthcare, we deal with a lot of binary outcomes. Death yes/no, disease recurrence yes/no, for instance. These outcomes are often easily analysed using binary logistic regression via finalfit(). When...continue reading.
R puzzle
Can you guess the meaning of the following R code “?”=`u\164f8ToI\x6Et`;’!’=prod;!{ y<-xtabs(~?readLines())}%in%{ z<-y[1]}&z>T##&[]>~48bEfILpu If not (!), the explanation is provided in Robin’s answer to a codegolf …continue reading.
Extracting Sydney transport data from Twitter
The @sydstats Twitter account uses this code base, and data from the Transport for NSW Open Data API to publish insights into delays on the Sydney Trains network. Each tweet...continue reading.
Dummy Is As Dummy Does
In the 1975 edition of “Applied multiple regression/correlation analysis for the behavioral sciences” by Jacob Cohen, an interesting approach of handling missing values in numeric variables was proposed with the...continue reading.
Learn Python Statistics and Machine Learning with My New Book: Training Systems using Python Statistical Modeling
Packt Publishing has turned another one of my video courses, Training Your Systems with Python Statistical Modeling, into a book! This book is now available for purchase. It is a...continue reading.
R wins COPSS Award!
Hadley Wickham from RStudio has won the 2019 COPSS Award, which expresses a rather radical switch from the traditional recipient of this award in that this recognises his many contributions...continue reading.
Gibbs sampling with incompatible conditionals
An interesting question (with no clear motivation) on X validated wondering why a Gibbs sampler produces NAs… Interesting because multi-layered: The attached R code indeed produces NAs because it calls...continue reading.
Improve GRNN by Weighting
In the post (https://statcompute.wordpress.com/2019/07/14/yet-another-r-package-for-general-regression-neural-network), several advantages of General Regression Neural Network (GRNN) have been discussed. However, as pointed out by Specht, a major weakness of GRNN is the high computational...continue reading.
