Econ113 - Introduction to Econometrics (Summer 2013)

UCSC Econ 113 - Introduction to Econometrics (Summer 2013)

This course is an introduction to the theory and application of statistics to economic problems. This course focuses on the techniques used in empirical research with a particular focus on intuitive understanding. Weekly problem sets will introduce real world applications and teach you the fundamentals of statistical programming. No prior knowledge of computer programming is required. Class meets three times a week for lectures and once per week for section, which are strongly suggested though not mandatory.

Lectures - Timeline of Topics Covered

Quizzes (10% of grade) - Short multiple choice quizzes will be given at random points during lecture. The goal of quizzes are to incentivize attendance and a minimum level of lecture prep and review. Thus no makes-up. 

Homework (15% of grade) - Problem sets are assigned weekly (or more frequently). Although you may work in groups on problem sets, you must turn in your own homework and write up the answers on your own. Solutions are posted when HWs are due.
Turning in Homework: at lecture on the due date.

  • Homework 0 - Run through all 7 lessons on Code-School's Try-R. - Should take less than two hours. Thirty minutes if you're quick. 

  • Homework 1 - Expected value, mean, variance, and bias. Inference about the location of the mean. Using R. 
    Questions [pdf] - All Solutions [pdf]
Problem 1 - due Monday July 1st at start of class
Expected value calculation, discrete random event. solutions [pdf]
Problem 2 - due Monday July 1st at start of class
Expected value calculation, discrete random event. solutions [pdf]
Problem 3 - due Monday July 1st at start of class
Probability. solutions [pdf]
Problem 4 - due Monday July 1st at start of class
Expected value of mean and variance estimators, systematic error and mean zero error. solutions [pdf]
Problem 5 - due Friday June 28th at start of class
Hand calc mean, variance and standard deviation, simple summary stats with R. solutions [pdf]
Problem 6- due Monday July 1st at start of class
Continuous random events, normal distribution, z-score probability calculation. solutions [pdf]
Problem 7 - due Wednesday July 3rd at start of class
Hypothesis test with sample statistic. solutions [pdf]
Problem 8 - due Friday June 28th at start of class
R! Load data, summary statistics, subsetting, measurement error revisited. solutions [pdf]
Problem 9 - due Wednesday July 3rd at start of class
R continued, unbiased-ness assumptions, small-sample hypothesis test. solutions [pdf]
Problem 10 - due Wednesday July 3rd at start of class
R continued, large-sample hypothesis test. solutions [pdf]

  • Homework 2 - Simple OLS, inference on regressions, p-value, R-squared, unbiasedness assumptions. Also regressions with R, calculating omitted variable bias calculations. Also some non-linear regressions (log-level, level-log, etc).  
    Questions [pdf] - Solutions - RCode
Problem 1 - due Monday July 8th at class start
Derive covariance, correlation and OLS estimates by hand, rescale cov, plot OLS estimate, interpret regression coefficient estimates and consider bias, walk through assumptions that lead to unbiased result, R-squared, plus some R. solutions (pdf)
Problem 2 - due Monday July 8th at class start
Example of omitted variable bias. Derive OLS, calculate bias. solutions (pdf)
Problem 3 - due Monday July 8th at class start
Quick fire omitted variable bias questions. solutions (pdf)
Problem 4 - due Monday July 8th at class start
Non-linear regression (level-level, log-level, etc.), derive interpretations, additional issues. solutions (pdf)

  • Homework 3 & 4 - Multivariate regressions and inference,  Enriched Models. F-test. (Wololdridge Ch 3-7)
    Questions [pdf]

    Problem 1 - due Wednesday July 17th
    Multivariate Regression by hand, SST, SSR, R-squared and p-value. solutions (pdf)
    Problem 2 - due Monday July 22nd
    Example of attenuation bias, measurement error in x. solutions (pdf)
    Problem 3 - due Wednesday July 17th
    We work through a quadratic model, estimate the model, report results, predict values, find the max, interpret coefficients, and plot. solutions (pdf)
    Problem 4 - due Wednesday July 17th
    Correction on observables, the effect of adding variables to a model, hypothesis test  and p-value practice, presenting results in organized table. solutions (pdf)
    Problem 5 - due Monday July 22nd
    Standardizing/normalizing results, interpret results. solutions (pdf)
    Problem 6 - due Monday July 22nd
    Confidence intervals, Dummy Variables and dummy plus interaction terms. solutions (pdf)
    Problem 7 - due Monday July 22nd
    Categorical variables, dummy variable trap, multiple dummy variables and interpretation. solutions (pdf)
    Problem 8 - due Monday July 22nd
    Category variables, multiple dummy variables and interpretation. solutions (pdf)
    Problem 9 - due Wednesday July 17th
    Accuracy of a prediction, simple regression, rewrite to get a prediction, interpret it and error. solutions (pdf)
    Problem 10 - due Monday July 22nd
    Multivariate regression with a quadratic term, F-test. solutions (pdf)
  • Problem 11 - due Monday July 22nd
    F-test and adjusted R-squared, nested vs unnested models. Dummy plus dummy with interaction term.  solutions (pdf)
    Problem 12 - due Wednesday July 17th
    Regression predictions, and the accuracy of our prediction. Standardize variables and reinterpret. solutions (pdf)
    Problem 13 - due Monday July 22nd
    General review, F-test, joint significance test, standardizing data. solutions (pdf)

Instructor: Curtis Kephart,
Course Location: Jack Baskin Auditorium 101 (map)
Course Time: Mon, Wed & Fri 9:00 AM to 11:30 AM 
Course Syllabus [pdf]

eduroam Campus wifi - wifi in the classroom

Teaching Assistant(s):

Other Resources

 - Introductory Econometrics (Any Edition) by Jeffrey Wooldridge
           More Optional Readings
           Reserve copies at Sci & Eng Library

Some disorganized Econometrics and R Resources

Statistical Analysis Software: We will be using R. 
1. Download and Install R:
R is a free and open source statistical software. Feel free to use SAS or STATA if you have a strong preference for either.
2. Download and Install RStudio:
RStudio is a free and open source integrated development environment that is easier to work with and vastly superior to the console-and-script set-up that comes with the basic R installation.

  Office Hours      

    Curtis' Office Hours 
    When: 12:30 PM Wedneday
    Where: E2, Room 403C (map)

  TA Office Hours    
    Thursdays 10-11AM
    Room E2, 403G


    With Jae
    JBE 101 (map), 
    Tues 10AM - Noon

    MSI Meeting Times  

    Karl Rubio -  sign up
      Mon 12:15-1:15PM JBE 169
      Tuesday 2-3:00PM ARC 202
      Wednesday Noon-1PM Arc 216
      Thurs 2:30-3:30PM SS2 137

    Tentative Exam Dates  

    Exams - no calculators. no notes

    Midterm: July 10th
    Solutions: Version A - Version B
    (30% of grade) 
    Final: July 26th at 9-11:30 AM
    Solutions Sketch
(45% of grade) The Final will be comprehensive, but will emphasize later material.