This preview shows pages 1–3. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Lecture Notes 1 1. Economic Forecasting 1. Forecasting the process of estimating or predicting unknown situations Example usually economists predict future economic variables Forecasting applies to a variety of data (1) time series data predicting future data points in time Examples unemployment, interest rates, exchange rates etc. (2) crosssectional data predicting within a class of a variable taken at one point in time Examples Usually associated with households, individuals, businesses, etc. How many businesses bankrupted in 2009? How many people are living in poverty in 2009? (3) panel data combines crosssectional and time series data Example examining unemployment over time in several regions Thus, forecasting is an enormous subject. Timeseries alone can use advanced math and is quite a complex topic Combines statistics, calculus, and economics Examples ARIMA modeling and Vector Auto Regressions 2. Tools for forecasting Forecasting extensively uses econometrics Foundation of econometrics is least squares 2 Also called ordinary least squares, regression, or multiple regression (1) Method y x u i n i i i 1, 2, , = 1 + 2 += where y i and x i are paired observations or variables 1 and 2 are unknown parameters n is the total number of observations u i is the error term associated with observation i Error is also called stochastic, white noise, or random Has an expected value of zero Time series data the error is almost never random Instead they call it an innovation The error term contains information When we estimate the parameters, they are denoted by hats y x i n...
View
Full
Document
 Fall '11
 BLAIR

Click to edit the document details