Beruflich Dokumente
Kultur Dokumente
University of San Francisco Department of Economics Prof. Jesse K. Anttila-Hughes January 21st, 2014
!! Introduction to econometrics !! Review of probability !! Wooldridge Appendixes B and C !! Tuesdays 1-4pm or by appt !! On Blackboard !! Due next Monday !! Get Stata !! Download the data files from Blackboard !! Bring your laptop, with Stata installed and the data files
! Reading:
! Office Hours:
! Problem set #1
! Computer assignment #1
!! Tacit knowledge
!! Including some common basic problems and their solutions / lack thereof
!! Basics of performing econometrics analysis in Stata !! Basics good habit for handling and managing data
!! Simple, intuitive understandings of what econometrics is and what it can and cant do !! A beginners proficiency with Stata !! Enough econometrics to start appreciating how much there is to learn
Administraterrata
! Class:
!! 6:30 9:15 pm on Tuesdays !! 14 lectures total, one midterm
! Grades:
!! 12 Problem sets (drop lowest 2): 35% !! Class participation: 10% !! Midterm exam: 25% !! Final exam: 30%
! Book:
!! Wooldridge 5th Edition
Econometrics
! What is econometrics?
!! The statistics used by economists !! !! !! !! Estimating relationships between economic variables Testing economic theories and hypotheses Forecasting economic variables Evaluating or implementing policies
!! Etc.
! Why do we do econometrics?
! In general, econometrics starts with an economic model (i.e., something youd learn in a theory class) and then generates testable predictions which come from that model
!! The step of explicitly defining a model is often skipped
Other income
!! Functional form of relationship not specified !! Equation could have been postulated without economic modeling
!! Other factors may be relevant, but these are the most important (?)
Frequency of conviction
Age
Hourly wage
! Most of econometrics deals with the specification of the error ! Econometric models may be used for hypothesis testing !! For example, the parameter represents effect of training on wage
Types of data
! Econometric analysis requires data
!! And there are many, many different things that count as data
! In general, we distinguish between the four major kinds of economic data in terms of how they interact between units of observation and time
!! Cross-sectional data !! Time series data
!! Multiple units of obs., single time !! Single unit of obs., multiple times !! Multiple unit of obs., multiple times, but different obs. each time !! Multiple units of observation with multiple time observations for each
!! Panel/Longitudinal data
Types of data
! Cross-sectional data !! Sample of individuals, households, firms, cities, states, countries, other units of interest at a given point of time/in a given period !! Cross-sectional observations must be more or less independent
!! For example, pure random sampling from a population
or
!! Sometimes pure random sampling is violated, e.g. units refuse to respond in surveys, or if sampling is characterized by clustering
Observation number
Hourly wage
Types of data
! Time series data !! Observations of a variable or several variables over time
!! For example, stock prices, money supply, consumer price index, gross domestic product, annual homicide rates, automobile sales,
!! Time series observations are typically serially correlated !! Ordering of observations conveys important information !! Data frequency: daily, weekly, monthly, quarterly, annually, !! Typical features of time series: trends and seasonality !! Typical applications: applied macroeconomics and finance
Types of data
! Time series data on minimum wages and related variables
Unemployment rate
Types of data
! Pooled cross sections !! Two or more cross sections are combined in one data set !! Cross sections are drawn independently of each other !! Pooled cross sections often used to evaluate policy changes !! Example: !! Evaluate effect of change in property taxes on house prices !! Random sample of house prices for the year 1993 !! A new random sample of house prices for the year 1995 !! Compare before/after (1993: before reform, 1995: after reform)
Types of data
! Pooled cross sections on housing prices
Property tax Size of house in square feet Number of bathrooms
Types of data
! Panel or longitudinal data !! The same cross-sectional units are followed over time !! Panel data have both cross-sectional and a time series dimensions
!! Hence, panel data can be used to account for time-invariant unobservables
!! Panel data can be used to model lagged responses !! Example: !! City crime statistics; each city is observed in two years !! Time-invariant unobserved city characteristics may be modeled !! Effect of police on crime rates may exhibit time lag
Types of data
! Two-year panel data on city crime statistics
Each city has two time series observations
! More generally, the statistical tools we have can tell us a lot about how two variables covary ! A particular concern is when our two variables x and y are endogenous, or jointly determined
!! But correlation doesnt imply causation, and to get to causal inference we generally need to know about how the problem works in real life !! Aka x and y influence each other, or theres a third variable Z that affects both
Medicine (Victorian)
Randomization
! Ironically given its late arrival to the scientific method, medicine first developed what we may now consider the be the ultimate tool in causal inference in the sciences: the randomized control trial (or RCT)
! Find a natural experiment that produces something akin to randomization in class size
!! Maimonides Rule in Israel