References in periodicals archive ?
Part 2 focuses on the "frozen history" necessary for applying standard statistical procedures to time series data and culminates with Herman Wold's identification of the stationary stochastic process in 1938.
1) In one of the first papers to adopt this approach, Hamilton and Flavin [1986] examined twenty-three years of annual data--1962 to 1984--to determine whether the deficit follows a stationary stochastic process.
Their preface defines the subject: "A discrete-time stationary stochastic process is said to have long memory if its autocovariances tend to zero hyperbolically slowly as the lag tends to infinity, but their sum diverges.