Week 1 - Introduction Flashcards
What is Nonexperimental data?
Data not accumulated through controlled experiments on individuals, firms or segments of the economy (sometimes called observational data)
What is Experimental Data?
Often collected in laboratory environments for natural sciences. In social science, this is a lot harder, and if we were to try to make a society a lab like environment, it would probably be morally repugnant
What is an empirical analysis?
Uses data to test a theory or to estimate a relationship
How to structure an empirical economic analysis?
A formal economic model is constructed. This consists of a mathmatical equation that describes various relationships, or behaviours.
How does an econometric model relate to an economic model? Give an example
An economic model will attempt to explain a behavior through a series of factors, or behaviors. To make it an econometric model, we need to somehow turn these factors into variables that can be observed.
E.g Becker’s model of criminal activity contains a variable ‘wage earned in criminal activity’. To be made into an econometric model, a dataset must be found which estimates this
What does u contain
unobserved factors - it is the error term
What is cross sectional data?
Consists of a sample of indidividuals, households firms etc taken at a given point in time
Important assumption: It is obtained through random sampling
What is time series data?
Consists of observations on a varible or several varibles over time
More difficult to analyse than cross sectional data due to observations being rarely indepdent across time.
Needs to take into account frequency of data collection
What are pooled cross sections?
Both cross sectional and time series based. Comes from different years, with the same data set.
One can test the effect of a policy, by looking at the data set before and after it’s implementation
What is panel data?
Consists of a time series for each cross sectional member in the data set.
Distinction between it and pooled cross sections, is that the same cross sectional units are followed over a given time period
Define ceteris paribus. Give an example
‘other factors being equal’. For a causal inference to occur, this has to be true.
Analyzing consumer demand, we are interested in knowing the effect of changing the price of a good on its quantity demanded, which holding all other factors. If income, prices of other goods, taste aren’t fixed, then we cannot know the causal effect of a price change on quantity demanded
What is counterfactual reasoning? Why is it important?
Imagining an economic unit, in two or more different states of the world. By doing this, we can deduce how a certain intervention has an effect, as long as everything else is held constant
