Publications by ucfagls
Why I love open source!
Today I had a great reminder of why I love open source software and why I spend a bit of my time contributing R code to several packages. In the vegan, I had included some code to do an analysis of multivariate dispersions. Bone-headedness on my part meant that if you tried to plot the ordination results behind the model/test for any axes other ...
1116 sym 16 img
Embedding a time series with time delay in R
I’ve recently been looking at Martin Trauth‘s book MATLAB® Recipes for Earth Sciences to try to understand what some of my palaeoceanography colleagues are doing with their data analyses (lots of frequency domain time series techniques and a preponderance of filters). Whilst browsing, the recurrence plot section caught my eye as something t...
3102 sym R (958 sym/3 pcs) 16 img
New version of vegan released to CRAN (1.17-9)
Yesterday Jari packaged up the latest release in the current stable branch of the vegan package. Version 1.17-9 of vegan is now on CRAN as a source tarball with binaries for MS Windows and MacOS X to follow soon. New releases in the current, stable branch of the package tend to be for bug fixes but we sometimes include new functionality considere...
2486 sym R (1793 sym/1 pcs) 16 img
Minor update to Vegan (1.17-10)
I overlooked blogging about this at the time, but Jari released a minor update to our Vegan package to fix a few issues following release of R 2.13-0. As far as the user is concerned, this mainly affects capscale(). metaMDSrotate(), a helper function for rotating nMDS solutions from function metaMDS() can now handle missing values via argument na...
842 sym R (450 sym/1 pcs) 16 img
New version of analogue (0.7-0)
Last week I pushed an update of my analogue package to CRAN. The last release (0.6-23) was on CRAN sometime in Mar 2010 so an update was well overdue. This (0.7-0) is a major update to analogue containing lots of new functionality. The main changes are: chooseTaxa() is a new utility function for choosing which taxa to select from a species train...
4067 sym Python (5353 sym/1 pcs) 16 img
Stratigraphic diagrams using analogue
One of the routine tasks palaeoecologists do is plot data on species composition or geochemical proxies say along a sediment core or stratigraphic sequence. These diagrams are the canonical way of displaying stratigraphic data in this field. An example of a stratigraphic diagram is shown below. Example of a stratigraphic diagram showing data from...
6088 sym R (579 sym/3 pcs) 22 img
Global warming since 1995 ‘now significant’
Yesterday (June 11, 2011) the BBC reported on comments by Prof. Phil Jones, of the Climatic Research Unit (CRU), University of East Anglia (UEA), that the warming experienced by the planet since 1995 was statistically significant. That the trend in the recent data was now significant when last year it was not, was attributed to the fact that one ...
9097 sym R (4000 sym/15 pcs) 26 img
Additive modelling and the HadCRUT3v global mean temperature series
Earlier, I looked at the HadCRUT3vgl data set using generalized least squares to investigate whether the trend in temperature since 1995 was statistically significant. Here I want to follow-up one of the points from the earlier posting; namely using a statistical technique that fits a local, and not global, model to the entire time series and see ...
10804 sym R (4220 sym/14 pcs) 38 img
No lake is an island: PhD Opportunity
NERC recently funded the formation of the UK Lake Ecological Observation Network (UKLEON) as part of the its Networks of Sensors programme. UKLEON is lead by Ian Jones at CEH Lancaster. A fully-funded PhD project is associated with the UKLEON project, with the aim of investigating high resolution coherence in lake dynamics. The successful student...
1395 sym 16 img
Embedding a time series with time delay in R — Part II
Some months ago, I posted a function that extended the base R function embed() to allow for time delay embedding. Today, David Gonzales alerted me to an inconsistency between embed() and Embed(). The example David used was R> (x <- seq(1,20,3)) [1] 1 4 7 10 13 16 19 R> embed(x, 4) [,1] [,2] [,3] [,4] [1,] 10 7 4 1 [2,] 13 1...
2284 sym R (1469 sym/5 pcs) 16 img