Environmental Studies 562—Lecture Outlines

Lecture 1 (Wednesday, January 10): Statistical experiments versus observational studies; statistical difficulties that arise with environmental data

Lecture 2 (lab) (Friday, January 12): Introduction to R

Lecture 3 (Wednesday, January 17): Discrete probability distributions—Bernoulli, binomial, multinomial

Lecture 4 (lab) (Friday, January 19): Fitting and plotting univariate probability distributions in R

Lecture 5 (Monday, January 22): Discrete probability distributions—Poisson and negative binomial

Lecture 6 (Wednesday, January 24): Continuous probability distributions—normal, lognormal, gamma, and beta

Lecture 7 (lab) (Friday, January 26): Mean-variance relations as guidelines for choosing probability models

Lecture 8 (Monday, January 29): Statistical issues in environmental sampling

Lecture 9 (Wednesday, January 31): Stratified, cluster, and systematic random samples

Lecture 10 (lab) (Friday, February 2): Analyzing survey samples with R's survey package

Lecture 11 (Monday, February 5): Simple linear regression and probability generating models

Lecture 12 (Wednesday, February 7): Output from regression models; regression with categorical variables

Lecture 13 (lab) (Friday, February 9): Using residuals to assess regression model assumptions; analysis of covariance

Lecture 14 (Monday, February 12): Maximum likelihood estimation

Lecture 15 (Wednesday, February 14): Maximum likelihood estimation (continued)

Lecture 16 (lab) (Friday, February 16): Maximum likelihood estimation in R

Lecture 17 (Monday, February 19): Information and the likelihood ratio test. Generalized linear models

Lecture 18 (Wednesday, February 21): Generalized linear models (continued)

Lecture 19 (lab) (Friday, February 23): Generalized linear models in R

Lecture 20 (Monday, February 26): Information-theoretic methods for model selection. Introduction to AIC

Lecture 21 (Wednesday, February 28): Using AIC to select models--the Burnham & Anderson protocol

Lecture 22 (lab) (Friday, March 2): Using AIC to screen models using the Burnham & Anderson protocol. AIC for transformed response models

Lecture 23 (Monday, March 5): Temporal and spatial autocorrelation

Lecture 24 (Wednesday, March 7): Proper inference in ANOVA models with interaction terms

Lecture 25 (lab) (Friday, March 9): Goodness of fit for continuous probability models; assessing temporal correlation

Lecture 26 (Monday, March 19): Design-based inference

Lecture 27 (Wednesday, March 21): The bootstrap

Lecture 28 (lab) (Friday, March 23): The nonparametric bootstrap and bootstrap confidence intervals

Lecture 29 (Monday, March 26): Introduction to randomization tests

Lecture 30 (Wednesday, March 28): The basic strategy of randomization tests

Lecture 31 (lab) (Friday, March 30): The parametric bootstrap and randomization tests

Lecture 32 (Monday, April 2): The multiple comparison problem

Lecture 33 (Wednesday, April 4): "Solutions" to the multiple comparison problem

Lecture 34 (Monday, April 9): An example of adjusting for multiple tests. The analysis of structured data

Lecture 35 (Wednesday, April 11): The multilevel model

Lecture 36 (lab) (Friday, April 13): Fitting multilevel models in R

Lecture 37 (Monday, April 16): Introduction to Bayesian inference

Lecture 38 (Wednesday, April 18): Markov chain Monte Carlo, the Gibbs sampler, and BUGS

Lecture 39 (lab) (Friday, April 20): Bayesian modeling using WinBUGS

Lecture 40 (Monday, April 23): Introduction to the analysis of spatial data

Lecture 41 (Wednesday, April 25): The semivariogram, Moran's I, and Ripley's K function

Lecture 42 (lab) (Friday, April 27): Accounting for spatial correlation in regression models

Course Home Page