---

Date	Lecture topics	Lab topics	Homework
8 January	Course overview Properties of time series Data transformations Time series decomposition	Matrices & matrix algebra (review on your own)	Review of matrix math Optional
10 January	Covariance & correlation Autocorrelation & Partial autocorrelation Cross correlation White noise Random walks Differencing	Writing models in matrix form (through section 2.5) Basic time series functions Autocorrelation	linear regression in matrix form Due 5pm next Tues; email to instructor(s) for lab
15 January	Autoregressive (AR) models Moving average (MA) models Stationary AR models Invertible MA models Using ACF & PACF for model ID
17 January	Box-Jenkins method Fitting ARIMA models with R Forecasting with ARIMA models Seasonal ARIMA models	Simulating ARMA models Fitting ARIMA models Forecasting with ARIMA models Box-Jenkins Methods	ARIMA models Due 5pm Tues 1/22; email to instructor(s) for lab
22 January	Univariate state-space models Diagnostics for state-space models
24 January	Introduction to multivariate state-space models	Fitting univariate and mulitvariate state-space models	State-space models Due midnight THURS 1/31; email to instructor(s) for lab
29 January	Multi-model inference and selection Information criteria Cross-validation & LOOIC
31 January	Dynamic factor analysis (DFA)	Fitting DFA models	Dynamic Factor Analysis Due midnight next Thurs 2/7; email to Mark
5 February	Regression with autocorrelated errors Dynamic linear models (DLMs)
7 February	Bayesian estimation of time-series and state-space models Stan	Fitting DLMs	Dynamic Linear Models Due midnight next Thurs 2/14; email to instructor(s) for lab
12 February	Writing our own Bayesian models in Stan
14 February	Hidden Markov models	Bayesian estimation STAN	No homework work on projects
19 February	Exponential smoothing models crossvalidation tests
21 February	Including covariates (predictors) in models Seasonal effects Missing covariates Colinearity MARSSX and ARMAX	Forecasting with ETS models, Model comparison, Covariates in MARSS models	Covariates in MARSS models Due 5pm next Thurs 2/28; email to instructor(s) for lab
26 February	Semi- and non-parametric models
28 February	Frequency domain Fourier transforms Spectral analysis Wavelet analysis	Frequency domain methods wavelet analysis Stochastic volatility	No homework work on projects
5 March	Estimating interaction strengths Gompertz models Stability metrics
7 March	Spatial and spatio-temporal models	Perturbation detection	No homework work on projects
12 March	Zero-inflated data Perturbation analysis outliers standardized residuals
14 March	Warlick-Pinniped stranding data Lowe-Bull trout life history trends McGill-Coastal productivity trends Feddern-Coastal stream flow patterns Sorel-Juvenile chinook timing	Student presentations	No homework work on projects