Free Webinar Courses from USGS

Taxonomy upgrade extras: 

 The US Geological Survey is offering the following webinar courses, which are open to all who are interested without charge.  Please forward this announcement to those who may be interested.
* Modeling Patterns and Dynamics of Species Occurrence, August 23-27, 2010, by Drs. Darryl MacKenzie and Jim Nichols
* An Introduction to the Fundamentals of Linear Quantile Regression in R, August 31, 2010 by Dr. Brian Cade
* Learn the R Statistical Package by Example, Tuesdays and Thursdays, starting October 12, 2010, by Dr. Paul Geissler
* R for Monitoring Natural Resources, Mondays and Wednesdays, starting October 13, 2010, by Dr. Tom Philippi, NPS
Recognizing the need for in-service training for natural resource managers, who often do not have travel funds to attend in-person training, the USGS Status and Trends of Biological Resources Program offers a series on online courses, where the you can watch the presenter`s computer screen live over the web and listen using your computer speakers (VoIP) or by calling a phone bridge.  If you have a headset or are on the phone, you can ask questions orally.  If not, you can type in questions.  Audio/video recordings are available over the web, if you are unable to participate or want another look.  The courses open to all who are interested without cost. Certificates of participation are available, and DOI employees can receive credit through DOI Learn.
One participant commented “I was pessimistic about the format, but I found that it worked very well. I would gladly use this format again. I value personal interactions that come from real meetings, but given travel restrictions, costs, limited time for training (away from our daily tasks) I think this worked very well."  Another said “This was great! Thanks for making this opportunity available, and in these times of reduced funding, this method was the only way I would have been able to attend the class."
Modeling Patterns and Dynamics of Species Occurrence
by Dr. Darryl MacKenzie (Proteus Wildlife Research Consultants) and Jim Nichols (US Geological Survey, Patuxent Wildlife Research Center)
Monday through Friday, August 23-27, 2010 at 2:30-4:30 PM Eastern Time
Webpage:
http://www.fort.usgs.gov/brdscience/SpeciesOccurrence.htm
Register at
https://www1.gotomeeting.com/register/895225144
 The presence or absence of a species across a set of landscape units is a fundamental concept used widely in ecology (e.g., species range or distribution, epidemiology, habitat modeling, resource selection probability functions, as a monitoring metric, metapopulation studies, biodiversity and species co-occurrence). An important sampling issue, however, is that a species may not always be detected when present at a landscape unit. This will result in "false absences" causing parameter estimates to be biased if unaccounted for, possibly leading to misleading results and conclusions, even with moderate levels of imperfect detection.
 This introductory workshop will cover many of the latest methods for modeling patterns and dynamics of species occurrence in a landscape while accounting for the imperfect detection of the species. Participants will be introduced to the basic methods of analysis with worked examples and a strong emphasis on study design issues. Due to limited time there will be no software demonstrations or class exercises. While primarily aimed at the beginner and intermediate level, more experienced researchers will also benefit from attending.
 Darryl is also offering in-person workshops you may be interested in. See
http://www.proteus.co.nz/workshops.html
An Introduction to the Fundamentals of Linear Quantile Regression in R
by Dr. Brian Cade (US Geological Survey, Fort Collins Science Center)
Tuesday August 31,2010 at 11:30 AM – 2:30 PM Mountain Time
Register at
https://www1.gotomeeting.com/register/119623873
 Dr. Brian S. Cade (Fort Collins Science Center, USGS) will give a 3 hour presentation on the fundamentals of linear quantile regression and implementing the models in R at 11:30 am (Mountain Time) on Tuesday, 31 August 2010.  Quantile regression provides a comprehensive statistical approach for estimating relationships between a response variable and various predictor variables based on the inverse of the empirical cumulative distribution function, eliminating the need to make parametric error distribution assumptions.  It has been especially useful in ecological and biological applications where heterogeneity in responses are common because of missing information on some important processes, a concept that is often embodied in the notion of constraints associated with ecological limiting factors.  Quantile regression has many potential applications to modeling and predicting organism responses to their environment, density-dependent processes, allometric growth in biological organisms, changes in phenology, effects of contaminants on organisms, equivalence testing, and modeling of flow records in hydrology.  The course is designed to be most beneficial to individuals who already have some familiarity with linear modeling in R.  The course this year will also include an introduction to additive models based on smoothing splines for quantiles.  A primer on quantile regression; Cade and Noon.  2003.  A gentle introduction to quantile regression for ecologists.  Frontiers in Ecology and the Environment 1: 412-420; is recommended reading prior to the course and is available for download from
http://www.fort.usgs.gov/Products/Publications/pub_abstract.asp?PubID=21137
Learn the R Statistical Package by Example
by Dr. Paul Geissler (US Geological Survey,  Status and Trends of Biological Resources Program)
Tuesdays and Thursdays 12:00 – 2:00 PM, Mountain Time, starting October 12, 2010
Website:  
http://www.fort.usgs.gov/brdscience/learnRE.htm
Register at:
https://www1.gotomeeting.com/register/327005065
 R is a very powerful system for statistical computations and graphics, which runs on Windows, UNIX and Mac computers. You can think of it as a combination of a statistics package and a programming language. It can be downloaded for free from
http://www.r-project.org/
Advantages:
* With the increasing cost of commercial statistical package, a free package is very attractive. However, free does not imply second rate. R is a high quality package that is better than commercial package in many respects.
* There are over 2,400 contributed packages (extensions) available for R to perform a great variety of statistical and graphical procedures.
* An easy to use menu system is available for common procedures.
* R includes a powerful programming language for selecting, manipulating and transforming data.
* R is interactive and supports data analysis, which should be interactive and exploratory.
* New statistical methods often are available first in R. For example, GRTS analyses are only available in R at this time to my knowledge.
* R can easily import and export data to and from Microsoft Access and Excel as well as text files.
 This course introduces R by working through a series of practical examples, showing how to use R analyses for common problems. It provides an overview, organized by problem situation, without going into all the options available with each procedure. We will use Brian S. Everitt and Torsten Hothorn, 2010, A Handbook of Statistical Analyses Using R, Second Edition, CRC Press, 355 pages, list price $54.95, but available at discount for $37.08. R Commander (a graphical user interface to R) will be used to provide menu access to R, supplemented with commands when necessary. The course will cover the R procedures, not the statistics, which can be learned from the text book.
R for Monitoring Natural Resources
by Dr. Tom Philippi ( US National Park Service, Inventory and Monitoring Program)
Mondays and Wednesdays, 1:30-3:00 PM Mountain Time, starting October 13, 2010
Website:
http://science.nature.nps.gov/im/monitor/stats/R/R_course2010.cfm
To register, contact  Tom_Philippi@nps.gov
 This course will cover the same topics as the above By Example course, using commands instead of menus.  One of the major advantages of R being open source is that experts in many fields not only use R, but also provide their field-specific coding as freely available packages.  In fact, the vast majority of R consists of these packages rather than the core or base.  As of early August, 2010, there are 2433 packages available on CRAN, with well over 100 on topics related to natural resources, ranging from handling climate data, to non-detects in water quality and toxicology, to mark-recapture, distance sampling, and double sampling approaches to population estimation, to GRTS spatially-balanced sampling (and analysis of data from GRTS samples), to analysis of bird or frog calls, to ordination and powerful extensions of analysis of dissimilarity, and to several approaches to habitat analysis. These packages allow R users to leverage both the topical expertise and the programming of the experts in those fields, but usually require writing simple R code to call the functions.   By writing R code and modifying examples, Tom`s version of the R course will provide an entry to using these packages.  The course will cover reading data from files, databases, and remote services, common data manipulations such as reshaping monitoring (revisit) data between long and wide formats, simple and customized graphics, and statistical tests relevant to natural resource science and management.  The same Everitt and Hothorn (2010) handbook as in Paul`s course will be used.
 Tom expects that folks who opt for the non-menu version will have a bit more background and familiarity with some form of computer coding, which would allow examples with participant data as well as the clean textbook examples. This may be overoptimistic.  The NPS coding version has a limit of 100 participants, but we anticipate that most participants will opt for Paul`s GUI-based version.  If that limit is reached, priority will be given to NPS participants, other DOI participants, Federal, State, Local, Tribal agency participants (including Canadian and Mexican), non-profit conservation organizations, students and academics, and finally for-profit consulting and other businesses. Students and academics receive low priority only because most universities provide courses and workshops on using R, or statistics and data analysis courses that use R for their exercises.