Sowell, F. (1992) "Modeling Long-Run Behavior with the Fractional ARIMA Model," Journal of Monetary Economics, 29, 277-302.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....expansion and contraction regimes are defined by the National Bureau of Economic Research recession dates. Our estimates of the tail index for the length of US economic booms and busts closely correspond to the magnitude of the long memory parameter estimated by Diebold and Rudebusch (1989) and Sowell (1992) for real US output, and suggest that a forecast of aggregate output based on a long history of past observations will be inferior to a projection that uses observations from the current regime. Keywords: Business cycles, duration, fat tailed distributions, long swings, long memory, regime ....

....regimes and their switching points. 2 For both economic upswings and downswings we find that the Davis and Resnick method produces estimates of the tail indices between 1 and 3. Our estimates of the tail indices support the long memory parameter estimates found by Diebold and Rudebusch (1989) and Sowell (1992) for fractionally integrated, long memory models of GNP.However, our empirical findings of fat tailed duration length in the US business cycle causes us to question whether previous findings of long memory in aggregate output is a spurious artifact of a regime switching model with ocassionally ....

[Article contains additional citation context not shown here]

Sowell, F. (1992) "Modeling Long-Run Behavior with the Fractional ARIMA Model," Journal of Monetary Economics, 29, 277-302.

....integrated models, these models not only include the unit root and trend stationary processes, but also include processes exhibiting more complex long run dynamics. Because of this ability to model long run behavior series which are fractionally integrated are referred to as long memory processes. Sowell (1990) has conjectured that conventional unit root tests have low power against long memory processes. This has been confirmed by Diebold and Rudebusch (1991) in Monte Carlo simulations with the Dickey Fuller (1981) unit root test. Concluding that a process is I(1) when it is actually a fractionally ....

....first differences. 4.2 Order of Integration To determine which of the cases in Table 1 the seven countries satisfy, we employ Sowell s (1992a) exact maximum likelihood approach in estimating an array of ARFIMA(p,d,q) models, where p; q = 0; 1; 2; 3, for each country s Deltam and Deltay. 6 Sowell (1990) and Diebold and Rudebusch (1991) both show unit root tests to have low power against long memory processes, whereas Canova (1994) urges the use of alternative tests to the unit root test in discerning the true long run characteristics of the data. By estimating an ARFIMA model we replace the ....

Sowell, F. (1992b) "Modeling Long-Run Behavior With the Fractional ARIMA Model," Journal of Monetary Economics, 29, 277-302.

....and Summers (1986) reported strong evidence in favor of hysteresis for several European unemployment rate series. The purpose of this paper is to cast the unemployment hysteresis question within the context of estimated autoregressive fractionally integrated moving average (ARFIMA) models. Sowell (1992) showed how unit root testing can be carried out within this relatively general framework, one which nests both unit root and stationary models. Another benefit is that the ARFIMA approach allows for hysteresis effects for an important class of non unit root alternatives. Further, point estimates ....

Sowell, F.B., 1992, Modeling long-run behavior with the fractional ARIMA model, Journal of Monetary Economics, 29, 277-302.

.... on the dynamic behavior of a political process (Box Steffensmeier and Smith 1998, 2) The importance of taking into account the additional information provided by an estimated ARFIMA model is emphasized in Baillie (1996) Box Steffensmeier and Smith (1996, 1998) Diebold and Rudebusch (1989) and Sowell (1990, 1992b) In the context of Granger causality, filtering an ARFIMA process with a conventional ARMA model will not purge all the autocorrelation from the series so that the residuals from the ARMA model will still be autocorrelated, specifically long memoried. That is, if we use an ARMA(p,q) to ....

Sowell, Fallaw. 1992b. "Modeling Long-Run Behavior with the Fractional ARIMA Model." Journal of Monetary Economics 29: 277-302.

....rather than the asymptotic distribution of the OLS estimator; hence, unit root tests provide meaningful information even for bounded data. See, e.g. Hamilton (1994) p. 447. 7 Examples of such criticism include DeJong et al. 1992) Diebold and Rudebusch (1991) Hassler and Wolters (1994) and Sowell (1990). 3 the popular nonparametric, spectral regression based procedure, called the GPH estimator after its developers, Geweke and Porter Hudak (1983) They show that based on series of length n T a where T is the number of observations and a is the power, the differencing parameter d can be ....

Sowell, F. (1992b) "Modeling Long-Run Behavior with the Fractional ARIMA Model", Journal of Monetary Economics 29, 277-302.

....and may be freely reproduced for educational and research purposes, so long as it is not altered, this copyright notice is reproduced with it, and it is not sold for profit. 1 1. Introduction Motivated by early empirical work in macroeconomics (e.g. Diebold and Rudebusch, 1989, Sowell, 1992) and later empirical work in finance (e.g. Ding, Engle, and Granger, 1993; Andersen and Bollerslev, 1997) the last decade has witnessed a renaissance in the econometrics of long memory and fractional integration, as surveyed for example by Baillie (1996) The fractional unit root boom of the ....

Sowell, F.B. (1992), "Modeling Long-Run Behavior with the Fractional ARIMA Model," Journal of Monetary Economics, 29, 277-302.

....for a moving average (MA) unit root, has recently began to receive more attention following the works of Tanaka (1990) Saikkonen and Luukkonen (1993) Tsay (1993) and Breitung (1994) among others. The third approach, direct estimation of the degree of integration, has been suggested by Sowell (1992), who stressed that underdifferenced ARIMA processes and overdifferenced (noninvertible) ARMA processes can be nested as special cases of fractionally integrated models, and that the degree of integration d of the time series can be directly estimated by fitting an ARFIMA model to the series. ....

Sowell, Fallaw (1992). "Modeling long-run behavior with the fractional ARIMA model," Journal of Monetary Economics 28, 277--302.

No context found.

Sowell, Fallaw (1992a), Modeling Long-run Behavior with the Fractional ARIMA Model, Journal of Monetary Economics 29, 277--302.

No context found.

Sowell, F. B. (1992), Modeling Long Run Behavior with the Fractional ARIMA Model, Journal of Monetary Economics 29, 277-302.

No context found.

Sowell, F., 1992b. Modeling long run behavior with the fractional ARIMA model. Journal of Monetary Economics 29, 277}302.

No context found.

Sowell, F.B. (1992b): "Modeling Long Run Behavior with the Fractional ARIMA Model," Journal of Monetary Economics, 29, 277-302.

No context found.

Sowell, F. (1992b). `Modeling long run behavior with the fractional ARIMA model', Journal of Monetary Economics, Vol. 29,pp. 277 -- 302.

No context found.

Sowell, F., 1992b, Modeling long-run behavior with the fractional ARIMA model, Journal of Monetary Economics, 29, 277-302.

No context found.

F. Sowell, "Modeling Long Run Behavior with the Fractional ARIMA Model", manuscript, Graduate School of Industrial Administration, Carnegie Mellon University, 1990.

No context found.

Sowell, F.B. (1992b), "Modeling Long Run Behavior with the Fractional ARIMA Model," Journal of Monetary Economics, 29, 277-302.

No context found.

Sowell, F. (1992b). Modeling long-run behavior with the fractional ARIMA model. Journal of Monetary Economics, 29:277--302. Flexible seasonal long memory 27

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC