After reviewing the simulation performance of general-to-specific automatic regression-model selection, as embodied in PcGets, we show how model selection can be non-distortionary: approximately unbiased ‘selection estimates’ are derived, with reported standard errors close to the sampling standard deviations of the estimated DGP parameters, and a near-unbiased goodness-of-fit measure. The handling of theory-based restrictions, non-stationarity and problems posed by collinear data are considered. Finally, we consider how PcGets can handle three ‘intractable’ problems: more variables than observations in regression analysis; perfectly collinear regressors; and modelling simultaneous equations without a priori restrictions.

/pdf/the-properties-of-automatic-gets-modelling-3612prsfke.pdf

The Properties of Automatic Gets Modelling

Is the proposed East African Monetary Union an optimal currency area? a structural vector autoregression analysis

Bayesian forecasting of parts demand

The present paper investigates the effects of the Asian currency crisis of 1997–1998 on the generalized PPP between several real exchange rates of the Far East countries. Monthly log of real exchange rates of the currencies of Thailand, Malaysia, Indonesia, the Philippines and South Korea vis-a-vis the US dollar and the Japanese yen during 1990–2004 are applied in the investigation. Further tests are conducted between exchange rates vis-a-vis the Thai baht. Tests are conducted for periods before and after the crisis. Results from the Johansen method of multivariate cointegration show a substantial change in the relationship between these real exchange rates before and after the Asian currency crisis. This result is found using rates based on three currencies: US dollar, yen and baht.

Asian currency crisis and the generalized PPP: Evidence from the Far East

We investigate the behaviour of real exchange rates of six East-Asian countries in relation to their two major trading partners–the United States and Japan. These countries, except, Singapore were affected by the financial crisis of the fall 1997. Using monthly frequency data from 1976 to 2002 and the autoregressive distributed lag (ARDL) cointegration procedure we test for the long-run purchasing power parity (PPP) hypothesis. We find no evidence for the weak form of PPP in the pre-crisis period, but strong evidence in the post-crisis period. For the post-crisis period, we also find very small persistence of PPP deviations as indicated by very small half-lives (<7 months) and narrow confidence intervals with an upper bound of 1 year or less in most countries. Our findings reveal that the East Asian countries are returning to some form of PPP-oriented rule as a basis for their exchange rate policies.

http://faculty.smu.edu/millimet/classes/eco6375/papers/baharumshah%20et%20al.pdf

Re-examining purchasing power parity for East-Asian currencies: 1976-2002

Common trends and generalized purchasing power parity

Foreword Part I: Economic Theory 1. Using and Abusing Economic Theory 2. Industry Sunk Cost and Entry Part II: Econometric Theory 3. Sub-Sample Model Selection Procedures in Gets Modelling 4. A Gibbs's Sampler for the Parameters of a Truncated Multivariate Normal Distribution 5. A Necessary and Sufficient Condition for Weak-Exogeneity in Vector Error Correction Models 6. Bayesian Graphical Inference for Economic Time-Series that may have Stochastic or Deterministic Trends Part III: Applications 7. The Impact of Monetary Policy in the UK on the Relationship between the Term Structure of Interest Rates and Future Inflation 8. Missing Data and Interpolation in Dynamic Term-Structure Models 9. Choosing Lag Lengths in Nonlinear Dynamic Models 10. D-TAR versus C-TAR Models? 11. Predicting Incomplete Observations in Unbalanced Panels: A Kalman Filtering-Smoothing Approach Index

Stan Hurn

Papers

Common trends and generalized purchasing power parity

Contemporary Issues In Economics And Econometrics: Theory and Application