Statistics 36-462, Spring 2008

Syllabus

Readings marked with a star (*) are more advanced and/or otherwise more likely to be cut. Readings from Guttorp's book (which is optional) will be distributed as xeroxed handouts.

Details are subject to change without notice --- unless you come to class!

Lecture 1, January 15 (Tu): What is a dynamical system? What is chaos? What is a simulation?: slides; R for examples
Lecture 2, January 17 (Th): More chaos: Flake, ch. 10 and sec. 11.1; Guttorp, ch. 1; slides; R for examples; The Arnold Cat Map Movie (starring Marlowe the Cat, directed by Evelyn Sander)
Lecture 3, January 22 (Tu): Attractors: Flake, ch. 11; Miller and Page, ch. 1--3; slides; R for examples
Lecture 4, January 24 (Th): Attractor reconstruction and nonlinear prediction: handouts: Kantz and Schreiber, Nonlinear Time Series Analysis, chapters 3 and 4; (*) Smith, "Disentangling Uncertainty and Error: On the Predictability of Nonlinear Systems", in Mees (ed.), Nonlinear Dynamics and Statistics (2000) [PDF]; PDF of slides; see slides for R examples; Lorenz time-series generator, written in Perl (see comments at head of file for usage instructions). The parameter values sigma=10, rho=28, beta=8/3 were hard-coded.; the Lorenz time series used in the lecture: 4 comma-separated columns, giving t, x, y and z; t runs from 50 to 100 in steps of 0.001.; Note: Nonlinear prediction, nearest-neighbors, kernel methods
Assignment 1, due February 1
Lecture 5, January 29 (Tu): Symbolic dynamics; stochastics from dynamics: Daw, Finney and Tracy, "A review of symbolic analysis of experimental data", Review of Scientific Instruments 74 (2003): 916--930 [reprint]; (*) handout from Badii and Politi, Complexity: Hierarchical Structures and Scaling in Physics; slides; Note: More on the Topological Entropy Rate
Lecture 6, January 31 (Th): Inference for Markov chains and dynamical systems: Guttorp, 2.7--2.9 and 2.12 (I, II, III); (*) Smith, "The Maintenance of Uncertainty", pp. 177--246 of the Proceedings of the International School of Physics "Enrico Fermi", Course CXXXIII (1997) [PDF]; Foulkes, "A Class of Machines Which Determine the Statistical Structure of a Sequence of Characters", pp. 66--73, vol. 4 of Western Electronics Convention Record, 1959 [PDF]; slides; Note: Maximum Likelihood Estimation for Markov Chains
Lecture 7, February 5 (Tu): Information theory: Feldman, "Information Theory" [PDF]; M.C. Hawking, "Entropy", from Fear of a Black Hole [lyrics; mp3 (radio-safe Brief History of Rhyme version)]; Ray and Charles Eames, A Communications Primer; slides
Lecture 8, February 7 (Th): Randomness and determinism: Flake, ch. 14; Poincaré, "Chance", from Science and Method [PDF]; slides
Lecture 9, February 12 (Tu): Self-organization 1, some examples: Miller and Page, ch. 4; Office of Charles and Ray Eames, Powers of Ten, narration by Philip Morrison; slides
Lecture 10, February 14 (Th): Cellular automata 1: Flake, ch. 15; Miller and Page, ch. 8; slides
Lecture 11, February 19 (Tu): Cellular automata 2, excitable media: Fisch, Gravner and Griffeath, "Threshold-range scaling of excitable cellular automata", Statistics and Computing 1 (1991): 23--39 [PDF]; Fisch, Gravner and Griffeath, "Cyclic Cellular Automata in Two Dimensions", pp. 171--185 in Alexander and Wadkins (eds.), Spatial Stochastic Processes (1991) [zipped PostScript]; Griffeath, "Self-Organization of Random Cellular Automata: four snapshot", pp. 49--67 in Grimmett (ed.), Probability and Phase Transitions (1994) [zipped PostScript]; (*) ch. 4 of Guttorp; slides
Assignment 2, due ~~29 February~~ 6 March: full solutions, R
Lecture 12, February 21 (Th): Self-organization 2: Shalizi, Klinkner and Haslinger, "Quantifying Self-Organization with Optimal Predictors", Physical Review Letters 93 (2004): 118701, arxiv:nlin.AO/0409024; Shalizi, Haslinger, Rouquier, Klinkner and Moore, "Automatic Filters for the Detection of Coherent Structure in Spatiotemporal Systems", Physical Review E 73 (2006): 036104, arxiv:nlin.CG/0508001; slides
Lecture 13, February 26 (Tu): Heavy-tailed distributions 1: what they are: Newman, "Power laws, Pareto distributions and Zipf's law", Contemporary Physics 46 (2005): 323--351, arxiv:cond-mat/0412004 (through section III); General R files for the next several lectures; slides; R
Lecture 14, February 28 (Th): Heavy-tailed distributions 2: how they arise: Newman, "Power laws", section IV; Mitzenmacher, "A Brief History of Generative Models for Power Law and Lognormal Distributions", Internet Mathematics 1 (2003): 226--251; Video of Mitzenmacher giving a talk on this material; Sornette, "Mechanism for Powerlaws without Self-Organization", International Journal of Modern Physics C 13 (2002): 133--136, arxiv:cond-mat/0110426; slides
Lecture 15, March 4 (Tu): Heavy-tailed distributions 3: Estimation: Clauset, Shalizi and Newman, "Power law distributions in empirical data", arxiv:0706.1062; (*) Markovitch and Krieger, "Nonparametric estimation of long-tailed density functions and its application to the analysis of World Wide Web traffic", Performance Evaluation 42 (2000): 205--222; slides
Lecture 16, March 6 (Th): Heavy-tailed distributions 4: Comparing models: Clauset et al. continued; Handcock and Morris, "Relative Distribution Methods", Sociological Methodology 28 (1998): 53--97 [JSTOR]; Freckleton and Sutherland, "Do power laws imply self-regulation?", Nature 412 (2001): 382; Freckleton and Sutherland, "Do in-hospital waiting lists show self-regulation?", Journal of the Royal Society of Medicine 95 (2002): 164; Edwards, Phillips, Watkins, Freeman, Murphy, Afanasyev, Buldyrev, da Luz, Raposo, Stanley and Viswanathan, "Revisiting Lévy flight search patterns of wandering albatrosses, bumblebees and deer", Nature 449 (2007): 1044--1048; (*) Vuong, "Likelihood Ratio Tests for Model Selection and Non-Nested Hypotheses", Econometrica 57 (1989): 307--333 [JSTOR]; slides and R
March 11 (Tu): Spring break; no lecture
March 13 (Th): Spring break; no lecture
Lecture 17, March 18 (Tu): Inference in general: error statistics and severe testing: Mayo and Cox, "Frequentist statistics as a theory of inductive inference", arxiv:math.ST/0610846; Mayo and Spanos, "Methodology in Practice: Statistical Misspecification Testing", Philosophy of Science 71 (2004): 1007--1025 [PDF]; Mayo and Spanos, "Severe Testing as a Basic Concept in a Neyman-Pearson Philosophy of Induction", The British Journal for the Philosophy of Science 57 (2006): 323--357; Spanos, "Curve-Fitting, the Reliability of Inductive Inference and the Error-Statistical Approach" [PDF]; slides
Lecture 18, March 20 (Th): ~~Inference from simulations 1~~: ch. 5 and appendix B of Miller and Page; Miller, "Active Nonlinear Tests (ANTs) of Complex Simulation Models", Management Science 44 (1998): 820--830 [JSTOR]; ~~Parker, "Computer Simulation through an Error-Statistical Lens" [PDF]~~; Special problem-solving session for homework 2; partial solutions, R
Lecture 19, March 25 (Tu): Inference from simulations 2: direct and indirect inference; A. A. Smith, "Indirect Inference" [PDF]; Gourieroux, Monfort and Renault, "Indirect Inference", Journal of Applied Econometrics 8 (1993): S85--S118 [JSTOR]; (*) Kendall, Ellner, McCauley, Wood, Briggs, Murdoch and Turchin, "Population Cycles in the Pine Looper Moth: Dynamical Tests of Mechanistic Hypotheses", Ecological Monographs 75 (2005): 259--276 [PDF reprint]; slides, R
March 27 (Th): No regular lecture: I'll be at a conference
Lecture 20, April 1 (Tu): Complex networks 1: basics, network properties: Watts, "The 'New' Science of Networks", Annual Review of Sociology 30 (2004): 243--270; Newman, "The Structure and Function of Complex Networks", SIAM Review 45 (2003): 167--256, arxiv:cond-mat/0303516 (through sec. VI, but skipping or skimming IV B and V); slides
Lecture 21, April 3 (Th): Complex networks 2: growth models: Newman, "Structure and function", sec. VII; slides
Assignment 3, due 21 April 2008: blogs.dat for problem 1 (data courtesy of Henry Farrell and Dan Drezner)
Lecture 22, April 8 (Tu): Agent-based models 1: Miller and Page, chs. 6 and 7; Flake, ch. 12; slides
Lecture 23, April 10 (Th): Agents 2: collective phenomena and self-organization: Flake, ch. 16;; Miller and Page, ch. 9; slides
Lecture 24, April 15 (Tu): Complex networks 3: contagion on networks: Guttorp, sec. 2.11; Newman, "Structure and Function", sec. VIII; Bell, Maiden, Munoz-Solomando and Reddy, "'Mind control experiences' on the Internet: Implications for the psychiatric diagnosis of delusions", Psychopathology 39 (2006): 87--91 [PDF]; (*) Kenah and Robins, "Second look at the spread of epidemics on networks", Physical Review E 76 (2007): 036113, arxiv:q-bio.QM/0610057; slides
April 17 (Th): Spring carnival; no lecture
Lecture 25, April 22 (Tu): Complex networks 4: inference for network models: Clauset, Moore and Newman, "Structural Inference of Hierarchies in Networks", in Airoldi et al. (eds.) Statistical Network Analysis, arxiv:physics/0610051; Hanneke and Xing, "Discrete Temporal Models of Social Networks" in Airoldi et al. (eds.) Statistical Network Analysis [PDF]; Foster, Foster, Grassberger and Paczuski, "Link and subgraph likelihoods in random undirected networks with fixed and partially fixed degree sequence", arxiv:cond-mat/0610446; Handcock and Jones, "Likelihood-based inference for stochastic models of sexual network formation", Theoretical Population Biology 65 (2004): 413--422 [PDF]; Hunter, Goodreau and Handcock, "Goodness of Fit of Social Network Models" [PDF]; Middendorf, Ziv and Wiggins, "Inferring Network Mechanisms: The Drosophila melanogaster Protein Interaction Network", Proceedings of the National Academy of Sciences (USA) 102 (2005): 3192--3197, arxiv:q-bio/0408010; Newman, "Structure and Function", sections IV B and V; Newman, Strogatz and Watts, "Random graphs with arbitrary degree distributions and their applications", Physical Review E 64 (2001): 026118, arxiv:cond-mat/0007235; Wiuf, Brameier, Hagberg and Stumpf, "A likelihood approach to analysis of network data", Proceedings of the National Academy of Sciences (USA) 103 (2006): 7566--7570; slides
Lecture 26, April 24 (Th): Agents 3: social complexity: Flake, ch. 17; Miller and Page, chs. 10--11; Skyrms and Pemantle, "A Dynamic Model of Social Network Formation", Proceedings of the National Academy of Sciences (USA) 97 (2000): 9340--9346, arxiv:math.PR/0404101; slides
Lecture 27, April 29 (Tu): Agents 4: A real-world example of agents on networks: Hedstrom and Aberg, "Quantitative research, agent-based modelling and theories of the social", ch. 6 (pp. 114--144) in Hedstrom, Dissecting the Social [PDF]; (*) Guttorp, ch. 4
Lecture 28, May 1 (Th): Chaos, complexity and inference: Multi-author discussion of "Statistics, probability and chaos", Statistical Science 7:1 (1992): 49--122 [JSTOR]