Blog Archives

Animating neural networks from the nnet package

March 19, 2013
By
Animating neural networks from the nnet package

My research has allowed me to implement techniques for visualizing multivariate models in R and I wanted to share some additional techniques I’ve developed, in addition to my previous post. For example, I think a primary obstacle towards developing a useful neural network model is an under-appreciation of the effects model parameters have on model

Read more »

Visualizing neural networks from the nnet package

March 4, 2013
By
Visualizing neural networks from the nnet package

Neural networks have received a lot of attention for their abilities to ‘learn’ relationships among variables. They represent an innovative technique for model fitting that doesn’t rely on conventional assumptions necessary for standard models and they can also quite effectively handle multivariate response data. A neural network model is very similar to a non-linear regression

Read more »

Data fishing: R and XML part 3

February 18, 2013
By
Data fishing: R and XML part 3

I’ve recently posted two blogs about gathering data from web pages using functions in R. Both examples showed how we can create our own custom functions to gather data about Minnesota lakes from the Lakefinder website. The first post was an example showing the use of R to create our own custom functions to get

Read more »

Collinearity and stepwise VIF selection

February 5, 2013
By
Collinearity and stepwise VIF selection

Collinearity, or excessive correlation among explanatory variables, can complicate or prevent the identification of an optimal set of explanatory variables for a statistical model. For example, forward or backward selection of variables could produce inconsistent results, variance partitioning analyses may be unable to identify unique sources of variation, or parameter estimates may include substantial amounts

Read more »

Data fishing: R and XML part 2

January 21, 2013
By
Data fishing: R and XML part 2

I’m constantly amazed at what can be done using free software, such as R, and more importantly, what can be done with data that are available on the internet. In an earlier post, I confessed to my sedentary lifestyle immersed in code, so my opinion regarding the utility of open-source software is perhaps biased. None

Read more »

Breaking the rules with spatial correlation

January 7, 2013
By
Breaking the rules with spatial correlation

Students in any basic statistics class are taught linear regression, which is one of the simplest forms of a statistical model. The basic idea is that a ‘response’ variable can be mathematically related to one or any number of ‘explanatory’ variables through a linear equation and a normally distributed error term. With any statistical tool,

Read more »

Stealing from the internet: Part 1

December 20, 2012
By
Stealing from the internet: Part 1

Well, not stealing but rather some handy tools for data mining… About a year ago I came across the package XML as I was struggling to get some data from various web pages. The purpose of this blog is to describe how this package can be used to quickly gather data from the internet. I’ll

Read more »