taking the theory to the data: a proposal romer: advanced macroeconomics, chapter 9: inflation and...
TRANSCRIPT
Taking the theory to the data:A proposal
Romer: Advanced Macroeconomics, Chapter 9:Inflation and Monetary Policy
‘Specific to General’ versus ‘General to Specific’
The role of ceteris paribus in a theory model versusin an empirical model
What causes inflation?
Many potential causes:Shocks shifting the AD curve to the right or the AS curve to the left leads to higher prices
Inflation and money growth
Endogenous, exogenous variables? Ceteris paribus assumptions?
Equlilibrium in the money market:
Inverting the equilibrium money relation:
Deviations from long-run benchmark levels:
Time dependence of macro data
• Stationary variables with a short time dependence, i.e. a low degree of time persistence, transitory effcts
• Nonstationary variables with long time dependence, i.e. high degree of time persistence, permanent effects.
Distinguish between:
Stationary and nonstationary movements in the data
• stationary movements have a short memory (transitory components)
• nonstationary movements have a long memory (persistent components)
• cointegration between nonstationary variables eliminate the nonstationarity. A cointegration relation can often be interpreted as a long-run economic relation
• distinguish between short-run and long-run structures in the data
How do we measure long-term movements in the data?
• Deterministic trends (usually linear)
• Stochastic trends (persistent movements in the data
• A combination of the two
• The increments of a deterministic trend are constant over time• The increments of a stochastic trend are random over time
• First and second order stochastic trends
1970 1975 1980 1985 1990 1995 2000 2005
0.0
0.5
1.0
1.5 Lp
1970 1975 1980 1985 1990 1995 2000 2005
0.000
0.025
0.050Dp
1970 1975 1980 1985 1990 1995 2000 2005
0.02
0.04 DpMA
The I(2) Scenario
Defining autonomous shocks • Theoretically• Empirically
• Shocks shifting the AD curve• Shocks shifting the AS curve
Why does nonstationarity matter for the statistical modelling?
• Standard statistical inference is based on stationarity.
• Some new inferences is needed, but by transforming the data into differences and cointegration relations stationarity is recovered.
• Pulling and pushing forces
Why does nonstationarity matter for the economic modelling?
• Most economic models are developed for a stationary world
• The role of the ceteris paribus assumption
• The role of expectations– Model based rational expectations
– Imperfect knowledge expectations
I had the great good fortune in the 1960s to initiate the profession’s work on plausible microfoundations for macroeconomic modeling taking into account the knowledge and the information that the micro actors could reasonably be supposed to have – truly a revolutionary movement. Unfortunately, the rational expectations models appearing in the 1970s sidestepped the problem of expectations formation under uncertainty by blithely supposing that the model’s actors (tellingly dubbed “agents”) knew the “correct” model and the correct model was the analyst’s model – whatever that model might be that day. The stampede toward “rational expectations,” referred to as a “revolution” though it was only a generalization of the neoclassical idea of equilibrium, derailed the movement I initiated. In the end, this way of modeling has not illuminated how the world economy works. Happily for me and I believe for the profession of economics, this book gives signs of bringing us back on track – on a road toward an economics possessing a genuine microfoundation and at the same time a capacity to illuminate some of the many aspects of the modern economy that the rational expectations approach cannot by its nature explain.