| Abstrakt: |
This paper investigates the validity of a bootstrap least square estimate of a polynomial correlation model whose error terms are an autoregressive fractionally integrated moving average ARFIMA (p,d,q) strongly dependent time series. For an (r + 1)×1 vector β of unknown parameters, βa an 'adjusted' least square estimate of β, β* a bootstrap estimate of β, it is shown that the distribution of √ n(β*- - βa) converges to that of √ n(βa - β), where n is the sample size. The result in this paper extends the correlation part of the results obtained by [9] and [6] to the case where the error term exhibits a long memory time series. [ABSTRACT FROM AUTHOR] |
