Read the summary and the most important questions on Introductory econometrics : a modern approach | 9780324289787 | Jeffrey M. Wooldridge.

• 1 Regression: Multiple

  This is a preview. There are 1 more flashcards available for chapter 1
  Show more cards here

• 1.2 Inference

• What are the assumptions of OLS? (Gauss markov)

  1. Linear in parameters (that the betas in linear)
     
  2. Random sampling ( violated when data is "selected"
  3. Sample variation in x (the x's can't be equal)
  4. ZCM: E(u|x)=0. Key to interpret causally. Violated when:
  • Omitted variables
  • Simultaneity (including reverse causality)
  • Measurement error
  5. Homoscedasticity: The error term has the same variance given any value of x. Var(y|x)= sigma squared. If it doesn't hold and Var(u|x) does not depend on x, the error term exhibits heteroskedasticity.

• What are the steps in empirical economic analysis?

  (1) Careful formulation of the question of interest
  (2) Formulation of an econometric model
  (3) Formulation of hypotheses in terms of unknown model parameters
  (4) Data collection and use of econometric methods to estimate the parameters in the econometric model and formally test hypotheses of interest.
  (5) Carefully interpret the results.

• What is a good estimator?

  Unbiased:
  1. expected Beta zero hat = beta zero 
  2. Expected beta one hat = beta one
  
  Efficient:
  1. Smaller variance relative to another one.

• 1.3.1 Cross-Sectional Data

• What does cross-sectional data mean?

  A cross-sectional data set consists of a sample of individuals, households, firms, countries, etc taken at a given point in time (through random sampling).

• 1.3.2 Time Series Data

• What does Time Series Data mean?

  A time series data set consists of observations on a variable or several variables over time (GDP, money supply)

• 1.3.3 Pooled Cross Sections

• What does pooled cross sections mean?

  Such data have both cross-sectional data and time series features. (Random sampling of households in 1985 with variables like income)

• 1.3.4 Panel or Longitudinal Data

• What does panel data mean?

  A panel data set consists of a time series for each cross-sectional member in the data set. 
  Key distinction with pooled cross sectional data is that the same cross-sectional data are followed over a given time period.

• 1.4 Causality, Ceteris Paribus, and Counterfactual Reasoning

• What is the economist's goal?

  The economist's goal is to infer the causal effect of one variable on another.
  An association between two or more variables may suggest, but does not establish, a causal effect (correlation does not imply causality)
  Ceteris paribus plays a key role in a causal analysis.

• What kind of observational data are there for econometric analysis?

  (1) Experimental data for measuring the return to education cannot be obtained (ethical issues, economic costs,..)
  (2) Nonexperimental (observational) data on education levels and wages for a large group can be obtained by sampling randomly from the population of working individuals

• 2 Time series

  This is a preview. There are 6 more flashcards available for chapter 2
  Show more cards here

• What is a time series?

  Data containing measurements of the "same thing" over time. For instance GDP per capita. It allows us to potentially model the dynamics over time. For instance, changes in the past impact future outcomes, short term vs long-term, seasonality and trends.