Model Specification
Background on Modeling
You have to specify a model
before you can estimate one. The basic model has a Numeric/Continuous dependent
variable and a set of independent variables that can be any data type.
Each independent variable has an unknown parameter, which is a weight
showing the importance of that variable. These parameters are unknown
to the analyst, and so they must be estimated from the data. The
method of ordinary least squares (OLS)
is the classical way to estimate them. I give only an outline of
a linear model and issues associated with it. See Gujarati (2003)
for a discussion of OLS and
estimation issues.
Statistical (and economic) theory assumes that a line exists in reality; it’s sometimes said that it exists ...
Get Market Data Analysis Using JMP now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
