Using R for multilevel modeling; R programming topics; Calling C from R

Program:

1. Using R for multilevel modeling of salmon habitat, by Yasmin Lucero

2. R programming topics for further meetings, by Szilard Pafka

3. Calling C from R, by Rob Zinkov

Details:

1. Using R for multilevel modeling of salmon habitat

by Yasmin Lucero

Abstract:

Many salmon populations are threatened by a shortage of good quality freshwater rearing habitat. Identifying the precise freshwater habitat features that improve juvenile survival is a very important problem in fisheries ecology and management. I will present data describing the habitat and population density of an endangered species, Oregon's coastal coho salmon. I use multilevel models to address spatial and temporal correlation structure in the data. I present a model that is able to identify which specific habitat features distinguish good quality habitat from poor quality habitat.
This talk will be structured as a case study in R. I will emphasize the strategies employed to manipulate and analyze the data. Topics will include: managing complex metadata, data visualization, the melt and cast functions from the reshape package, using the lmer and glmer functions from the lme4 package, and using sweave and xtable.

Bio:

Yasmin Lucero is a statistician specializing in natural resource management with an emphasis on fish population dynamics. She received her PhD in 2007 from the department of Ocean Sciences at UC Santa Cruz. From 2007-2011, she was a postdoctoral research fellow with NWFSC-NOAA research lab where she worked on salmon freshwater ecology. She has recently transitioned to independent statistical consulting.

2. R programming topics for further meetings

by Szilard Pafka

Discuss/select programming topics for future meetings, find speakers. Possible topics:

• how to create an R package
• Roxygen
• unit testing
• debugging
• profiling (performance)
• OOP: S3, S4, R5...
• R traps and pitfalls
  etc.

3. Calling C from R

by Rob Zinkov

Short introduction to how to speed up your R code with C/C++.

Please RSVP as places are limited.

Venue and starting time as usual: UCLA Boelter Hall Room 9413 (the lab), 6:30pm

Important message for first comers: Please consult the detailed venue information given at the first meeting as many people had difficulties finding the place the first time: https://www.meetup.com/LAarea-R-usergroup/events/10154603/