Quantitative Reasoning 2: Uncertainty and Inference

Spring 2017, INFO-1301, University of Colorado Boulder


Instructor: Prof. Michael Paul (Office hour: Friday, 10:15am–11:45am, ENVD 207)

Time/Place: MW 9:30am–10:45am
ENVD 201

Contact: mpaul@colorado.edu

Textbook: Downey (2014) Think Stats: Exploratory Data Analysis in Python, 2nd Edition.


Introduces intermediate-level methods for quantitative data analysis, focusing on foundational concepts in probability and statistical inference along with complementary computational skills and tools. The course will cover basic probability concepts, common probability distributions and methods for estimating their parameters, multivariate regression with applications to forecasting and classification and a variety of methods of statistical significance testing. data, probability, statistics
Prerequisites:
  • INFO 1301: Quantitative Reasoning 1 (or equivalent)
  • INFO 1201: Computational Reasoning 1 (or equivalent)
Schedule
Policies
Resources
Student Login
Lecture Materials Readings
Wednesday, January 18, 2017
Introduction
Course introduction and overview. 		[slides-1]
Monday, January 23, 2017
Probability foundations
Definitions and terminology. Distributions and joint probability. 		[slides-2]
Wednesday, January 25, 2017
Probability foundations
Marginalization and independence. Expected value. 		[slides-2]
  • Diez et al: 2.1, 2.4.1, 2.5
Monday, January 30, 2017
Probability foundations
Practice problems. 		[practice]
  • Grinstead & Snell: 1, 2.1
Wednesday, February 2, 2017
Probability foundations
Computational randomness.
Monday, February 6, 2017
Conditional probability
Introduction to conditional probability. 		[slides-3]
  • Diez et al: 2.2, 2.3
Wednesday, February 8, 2017
Conditional probability
Practice problems.
Monday, February 13, 2017
Class cancelled
Wednesday, February 15, 2017
Discrete distributions
Representing distributions with functions. Survey of discrete distributions. 		[slides-4]
  • Diez et al: 3.3.1, 3.4.1
Monday, February 20, 2017
Discrete distributions
Sampling from distributions in Python.
Wednesday, February 22, 2017
Discrete distributions
Language modeling. 		[slides-4b]
Monday, February 27, 2017
Discrete classification
Naive Bayes classification. 		[slides-4c]
Wednesday, March 1, 2017
Continuous distributions
Density functions. Normal distribution. 		[slides-5]
  • Diez et al: 2.5, 3.1
  • Grinstead & Snell: pg. 212-215
Monday, March 6, 2017
Parameter estimation
Function optimization. Maximum likelihood estimation. 		[slides-6]
Wednesday, March 8, 2017
Linear regression
Simple regression and parameter estimation. 		[slides-7]
  • Diez et al: 7.1, 7.2, 7.4
Monday, March 13, 2017
Linear regression (cont'd)
Multiple regression. Linear regression in Python. 		[slides-7]
  • Diez et al: 8.1
Wednesday, March 15, 2017
Linear regression (cont'd)
More practice with regression. Feature engineering. (tentative)
Monday, March 20, 2017
Logistic regression
Revisiting classification. 		[slides-8]
Wednesday, March 22, 2017
Logistic regression (cont'd)
Logistic regression in Python.
Monday, March 27, 2017
No class – Spring break
Wednesday, March 29, 2017
No class – Spring break
Monday, April 3, 2017
Clustering
K-means clustering and mixture models. 		[slides-9]
Wednesday, April 5, 2017
Predictive modeling
Review classification and regression. Final project planning.
Monday, April 10, 2017
Evaluation
Evaluation metrics for classification and regression. 		[slides-10]
Wednesday, April 12, 2017
Lab
Work on final projects.
Monday, April 17, 2017
Evaluation (cont'd)
Evaluation metrics in Python.
Wednesday, April 19, 2017
Lab
Work on final projects.
Monday, April 24, 2017
Hypothesis concepts
Test statistics and p-values. Chi-squared testing. 		[slides-11]
Wednesday, April 26, 2017
Lab
Work on final projects.
Monday, May 3, 2017
Lab
Work on final projects. Prepare for presentations.
Wednesday, May 5, 2017
Hypothesis concepts
Continuous testing. 		[slides-12]