1、Econometric Analysis of Panel Data,William GreeneDepartment of EconomicsStern School of Business,Econometric Analysis of Panel Data,10. Dynamic Models, Heterogeneity and Nonstationary Panel Data,Cross Country Growth Convergence,Heterogeneous Dynamic Model,“Fixed Effects” Approach,Country Means,Count
2、ry Means (cont.),Time Series,Pooling,Essentially the same as the time series case. OLS or GLS are inconsistentThere could be no instrument that would work (by construction),A Mixed/Fixed Approach,A Mixed Fixed Model Estimator,Nair-Reichert and Weinhold on Growth,Weinhold (1996) and NairReichert and
3、Weinhold (2001) analyzed growth and development in a panel of 24 developing countries observed for 25 years, 19711995. The model they employed was a variant of the mixed-fixed model proposed by Hsiao (1986, 2003). In their specification, GGDPi,t = i + i dit GGDPi,t-1 + 1i GGDIi,t-1 + 2i GFDIi,t-1 +
4、3i GEXPi,t-1 + 4 INFLi,t-1 + i,t GGDP = Growth rate of gross domestic product,GGDI = Growth rate of gross domestic investment,GFDI = Growth rate of foreign direct investment (inflows),GEXP = Growth rate of exports of goods and services,INFL = Inflation rate.The constant terms and coefficients on the
5、 lagged dependent variable are country specific.The remaining coefficients are treated as random, normally distributed, with means k andunrestricted variances. They are modeled as uncorrelated. The model was estimated using a modification of the HildrethHouckSwamy method,Analysis of Macroeconomic Da
6、ta,Integrated seriesThe problem with regressions involving nonstationary seriesSpurious regressionsUnit roots and misleading relationshipsSolutions to the “problem”Random walks and first differencingRemoving common trendsCointegration: Formal solutions to regression models involving nonstationary da
7、taExtending these results to panelsLarge T and small T cases.Parameter heterogeneity across countries,Nonstationary Data,Integrated Series,Stationary Data,Unit Root Tests,KPSS Test-1,KPSS Test-2,Cointegrated Variables?,Cointegrating Relationships,Implications:Long run vs. short run relationshipsProb
8、lems of spurious regressions (as usual)Problem for existing empirical studies: Regressions involving variables of different integration. E.g., regressions of flows on stocks,Money demand example,Panel Unit Root Tests,Implications,Separate analyses by countryHow to combine data and test statisticsCoi
9、ntegrating relationships across countries,Purchasing Power Parity,Application,“Some international evidence on price determination: a non-stationary panel Approach,” Paul Ashworth, Joseph P. Byrne, Economic Modelling, 20, 2003, p. 809-838.80 quarters, 13 OECD countrieslog pi,t = 0 + 1log(unit labor costi,t) + 2 log(world price,t) + 3 log(intermediate goods pricei,t) + 4 (log-output gapi,t) + i,tVarious tests for unit roots and cointegration,
