We develop an ordinary least squares estimator of the long-memory parameter from a fractionally integrated process that is alternative to Geweke and Porter-Hudak (1983) estimator. Using wavelet transform process, we establish log-linear relationship between coefficients' variance scaling equal log-memory parameter. This yields consistent when population replaced by their sample variance. derive small bias test it against GPH McCoy–Walden maximum likelihood conducting number Monte Carlo...

ADVERTISEMENT RETURN TO ISSUEPREVArticleNEXTChemical Pharmacology of Catha EdulisGordon A. Alles, M. David Fairchild, Mark Jensen, and AllesCite this: J. Med. Chem. 1960, 3, 2, 323–352Publication Date (Print):March 1, 1961Publication History Published online1 May 2002Published inissue 1 March 1961https://pubs.acs.org/doi/10.1021/jm50015a010https://doi.org/10.1021/jm50015a010research-articleACS PublicationsRequest reuse permissionsArticle Views237Altmetric-Citations60LEARN ABOUT THESE...

There are a number of estimators long-memory process' parameter when the is assumed to hold constant over entire data set, but currently no estimator exists for time-varying parameter. In this paper we construct an that based on time-scale properties wavelet transform. Because wavelets localised in time they able capture statistical locally stationary longmemory process, and since also scale identify self-similarity scaling behaviour found process. Together produce approximate log-linear...

Barnett originated the Divisia monetary aggregates, which in continuous time exactly track any aggregator function under perfect certainty. With user costs measuring prices of services components, Barnett's aggregates are based on Francois Divisia's derivation line integral from first-order conditions for optimizing behavior by economic agents We derive an extended index (Euler equations) that apply risk. Our is first extension number theory into domain decision making risk and thereby...

Abstract. In this paper, a semiparametric, Bayesian estimator of the long‐memory stochastic volatility model's fractional order integration is presented. This new relies on highly efficient, Markov chain Monte Carlo (MCMC) sampler posterior distribution. The MCMC algorithm set forth in time‐scale domain wavelet representation. key to and centerpiece quick efficient multi‐state latent volatility's coefficients. A coefficients only possible because near‐independent multivariate distribution...

By design a wavelet's strength rests in its ability to localize process simultaneously time-scalespace. The time series time-scale space directly leads the computationalefficiency of wavelet representation N £ matrix operator by allowing largest elements thewavelet represented represent [Devore, et al. (1992a) and (1992b)]. Thisproperty allows many dense matrices have sparse when transformed wavelets.In this paper we generalize long-memory parameter estimator McCoy Walden (1996)...

We rank institutions and researchers based on a standardized page count of their econometric theory publications over the last 11 years (1986–1996) in economics statistics journals. Our ranking criteria differ from those employed by Hall (1987, Econometric Theory 3, 171–194; 1990, 6, 1–16) Baltagi (1998, 14, 1–43). weight publication publishing journal's “impact factor,” which measures impact profession. also depart previous rankings focusing only theoretical econometrics. reveal Yale...

In this paper, I provide a plausible explanation as to why past studies have been unable find support for the long‐run Fisher effect. My argument is that exogenous shocks inflation rates in industrialized economies not produced permanent change necessary testing Instead of finding nonstationary, unit‐root process like previous effect studies, here each country's rate found follow mean‐reverting, fractionally integrated, long‐memory process. Applying bivariate, maximum likelihood estimator...

It has been argued by several authors that the inflationary dynamics in Brazil follow a unit root process, thus displaying some inertia. Indeed, Cati, et al. (Journal of Applied Econometrics, 1999) have found are nearly fully inertial. We estimate fractional differencing parameter using an ARFIMA specification for inflation rate country and our results suggest better modeled long memory process than mechanism, implying there is no inertia inflation, contrary to what other researchers. also...

This paper extends the existing fully parametric Bayesian literature on stochastic volatility to allow for more general return distributions. Instead of specifying a particular distribution innovation, we use nonparametric methods flexibly model skewness and kurtosis while continuing dynamics with structure. Our semiparametric approach provides full characterization distributional uncertainty. We present Markov chain Monte Carlo sampling estimation theoretical computational issues simulation...

In this paper, we let the data speak for itself about existence of volatility feedback and often debated risk–return relationship. We do by modeling contemporaneous relationship between market excess returns log-realized variances with a nonparametric, infinitely-ordered, mixture representation observables’ joint distribution. Our nonparametric estimator allows deviation from conditional Gaussianity through non-zero, higher ordered, moments, like asymmetric, fat-tailed behavior, along...

During the combustion of coal and other carbonaceous materials, heterogeneous reaction NO with evolving char created in process is important for understanding formation reduction NO. This investigation quantifies effects burnout level conditions on kinetics by chars made from coals ranging rank lignite to low-volatile bituminous (Beulah Zap, Dietz, Utah Blind Canyon, Pittsburgh #8, Pocahontas #3) as well graphite coconut char. Kinetic data were measured a packed-bed reactor at temperatures...

We develop an ordinary least squares estimator of the long-memory parameter from a fractionally integrated process that is alternative to Geweke and Porter-Hudak (1983) estimator. Using wavelet transform process, we establish log-linear relationship between coefficients' variance scaling equal log-memory parameter. This yields consistent when population replaced by their sample variance. derive small bias test it against GPH McCoy–Walden maximum likelihood conducting number Monte Carlo...