Need feedback on extended example

[eric-pedersen]

Hi folks, @dill @gavinsimpson

I just pushed a commit with a new extended example for the second part of the day, focusing on non-linear time series data. The compiled script is "example-nonlinear-timeseries.html". It's partially based of the nonlinear trend analysis from Gavin's blog, and partially off the nonlinear analysis of the lynx data set, derived from Cosma Shalizi's blog. I still have to add a reference section to acknowledge both of those; that's on my todo list.

I was looking for feedback on it. Does this seem like a reasonable format for the extended examples? Does it need more explanatory text? Do the exercises make sense? Also, putting this together took a fair bit of time, so we may need to trim down the number of extended examples back a bit.

[gavinsimpson]

That's a nice example @eric-pedersen but probably a little long. What about splitting the content into two with one on modelling a time series deterministically (the gamm()) and the other on the stochastic trend?

The plots should use ggplot() not qplot() - even Hadley is downplaying qplot() now and it won't make the code that much longer.

The examples make sense and there is a good balance between explanation where required and practical stuff.

I'll drop some specific comment in line on the .Rmd file.

[gavinsimpson]

I've left some notes in-line on the commit: f5bf38320ab52702de302c2d8d09327a839507d6

[eric-pedersen]

Thanks for the feedback, Gavin. I've gone through and added a lot of it in.

I figure it'll be easiest to keep this as one example (so there's a shared glossary, etc.), but I made it explicit in the code that people can work through one of the two parts without having to do the other.

Good suggestion to move away from qplot as well. It's a bad habit of mine to use qplot as a shortcut, but it does just end up confusing R neophytes.