cies_logo.jpg

 

LIKELIHOOD METHODS AND MODELS IN ECOLOGY

 

May 29 � June 2, 2017

Colorado State University, Fort Collins, CO

 

INSTRUCTORS:

Dr. Charles Canham, email: canhamc@caryinstitute.org

Dr. Patrick Martin, email: patrick.martin@colostate.edu

 

Day 1

8:309:30��� Lecture 1:An Introduction to Likelihood for Estimation and Inference���

9:30� 10:30�� Case Study 1:�� Distribution and Abundance of Tree Species Along Climate Gradients[Canham and Thomas 2010]

10:30 � 12:00Lab1:Calculating Likelihood, Likelihood Surfaces, and Likelihood Profiles��� [R Code � Section 1][R Code � Section 2]

12:00 �1:00�� Lunch

1:002:00��� Lecture 2:Parameter Estimation and Evaluation of Support

2:00�� 5:00�� Lab 2: Global Optimization using Simulated Annealing and Genetic Algorithms

[R code � anneal]�� [R code � genoud][R code � optim]

[BC Sapling Growth Data � Excel Version] [BC Sapling Growth Data.txt � (right click and �Save as��)]

[Wright et al. 1998]

 

Recommended Reading for Day 2:

G�mez-Aparicio, L. and C. D. Canham.2008.A neighborhood analysis of the allelopathic effects of the invasive tree Ailanthus altissima in temperate forests.Journal of Ecology 96:447-458

 

 

Day 2

8:30 � 9:30 ���� Lecture 3:Hypothesis Testing and Statistical Inference Using Likelihood: The Central Role of Models

9:30 � 10:30 �� Case Study 2: Neighborhood Models Of The Allelopathic Effects Of An Invasive Tree Species

10:30 � 12:00�� Lab3:Likelihood Functions for Continuous and Count Data: A Plethora of PDFs

����������������������������������� [McLaughin 1993 � Compendium of Common Probability Distributions]

����������������������������������� [Normal PDF with non-homogeneous variances]

����������������������������������� [Gamma and Lognormal PDFs][Exponential PDF]�� [Beta PDF]

����������������������������������� [Poisson, Negative Binomial, and Zero-Inflated PDFs]

12:00�� 1:00 Lunch

1:00�� � 2:00��� Lecture 4:Model Selection: AIC and Akaike Weights, Multi-model Inference

2:005:00��� Lab 4:Model Comparison and Hypothesis Testing in a Likelihood Framework

����������������������������������� [Lab 4 R Script]

 

Recommended Reading for Day 3:

Canham, C. D., M. Papaik, M. Uriarte, W. McWilliams, J. C. Jenkins, and M. Twery.2006. Neighborhood analyses of canopy tree competition along environmental gradients in New England forests.Ecological Applications 16:540-554.

 

Day 3

8:30�� � 9:30��� Lecture 5:Model Evaluation:How good is the best model?

9:30 � 10:30��� Case Study 3:Neighborhood Models of Tree Competition

10:30 � 12:00Lab 5:Model Evaluation�� [Sample R Code for Model Evaluation]

12:001:00Lunch

1:002:00���� Lecture 6:Analysis of Categorical and Ordinal Data:Binomial and Logistic Regression

2:005:00��� Lab 6: Developing your own binomial and logistic regression models in R

[R code � Logistic regression of windthrow data]�� [Damagedata.Rdata]��� [R code � binomial regression]

 

Recommended Reading for Day 4:

Canham et al. 2013.Regional variation in forest harvest regimes in the northeastern United States.Ecological Applications 23(3):515-522.

 

Day 4

8:30�� � 9:30��� Lecture 7:Avoiding and Dealing with Problems with Your Data and Models:Sampling Design, Lack of Independence, Spatial Autocorrelation, Collinearity, Parameter Tradeoffs,�

9:30 � 10:30��� Lab

10:30 � 12:00

12:001:00Lunch

1:00 ��� 5:00��� Lab Project:Analysis of variation in forest harvest regimes of the eastern US��

See the Course Materials page for datasets, R scripts, and documentation for the project

����������������������� [Course Materials Page]

�����������������������

Day 5

8:30 � 12:00��� Lab Projects, continued

 

COURSE HOMEPAGE