We build a 4-equation model of the inflation process in South Africa (which has recently adopted inflation targeting), including the exchange rate, consumer prices, producer price, and import prices. This provides useful information on the speed and extent of exchange rate pass-through, and...

Inflation is a far from homogeneous phenomenon, a fact often neglected in modeling consumer price inflation.  Using a novel methodology grounded in theory, the ten sub-components of the consumer price index (excluding mortgage interest rates), are modeled separately and forecast,...

Inflation targeting central banks will be hampered without good models to assist them to be forward-looking.  Many current inflation models fail to forecast turning points adequately, because they miss key underlying long-run influences.  The world is on the cusp of a dramatic turning point in...

Inflation is a far from homogeneous phenomenon, but this fact is ignored in most work on consumer price inflation. Using a novel methodology grounded in theory, the ten sub-components of the consumer price index (excluding mortgage interest rates, or CPIX) for South Africa are modeled separately...

Most recent work deriving optimal monetary policy utilising New Neo-Classical Synthesis (NNCS) models abstract from the impact of monetary policy on the government`s finances, by assuming that any change in the government`s budget can be financed through lump sum taxes. In this paper, we assume...

Recent attempts to incorporate optimal fiscal policy into New Keynesian models subject to nominal inertia, have tended to assume that policy makers are benevolent and have access to a commitment technology.  A separate literature, on the New Political Economy, has focused on real economies...

This paper develops an asymptotic estimation theory for nonlinear autoregressive models with conditionally heteroskedastic errors.  We consider a functional coefficient autoregression of order p (AR(p)) with the conditional variance specified as a general nonlinear first order generalized...

OLS estimation of an impulse-indicator coefficient is inconsistent, but its variance can be consistently estimated. Although the ratio of the inconsistent estimator to its standard error has a t-distribution, that test is inconsistent: one solution is to form an index of indicators. We provide...

Big Data offer potential benefits for statistical modelling, but confront problems like an excess of false positives, mistaking correlations for causes, ignoring sampling biases, and selecting by inappropriate methods.  We consider the many important requirements when searching for a data-based...

We consider model selection for non-linear dynamic equations with more candidate variables than observations, based on a general class of non-linear-in-the-variables functions, addressing possible location shifts by impulse-indicator saturation.  After an automatic search delivers a simplified...