Autocorrelation and dynamic methodology with an application to wage determination models

Covered Interest Parity and Speculative Efficiency: Some Empirical Evidence for Australia*

“…Kenward (1975) has iitgued that it is difficult to distinguish between this form of error structure and, for example, alttmative dynamic structures involving lagged dependent variables and other possible forms of autocorrelation. Kenward (1975) has iitgued that it is difficult to distinguish between this form of error structure and, for example, alttmative dynamic structures involving lagged dependent variables and other possible forms of autocorrelation.…”

“…The fact that the use of overlapping data may generate moving average errors is familiar from other contexts, most notably wage equations, where this form of averaging procedure is common. Kenward (1975) has iitgued that it is difficult to distinguish between this form of error structure and, for example, alttmative dynamic structures involving lagged dependent variables and other possible forms of autocorrelation. We have followed the procedure suggested by Kenward and estimated various equations containing lagged dependent variables.…”

Comparing Tests of Autoregressive Versus Moving Average Errors in Regression Models Using Bahadur’s Asymptotic Relative Efficiency

“…[9] and Evans and Honkapohja [10]); (iv) the model is a discrete time approximation to a continuous time model (Bergstrom [11]); (v) Koyck lag distributions are employed (Chow [12,); (vi) overlapping data on the dependent variable are used (Rowley and Wilton [13] and Kenward [14]); (vii) structural time series models are used (Harvey and Todd [15]); (viii) the data have been adjusted using filters such as X-11 (Wallis [16]); or (ix) an error correction model is estimated for series that are cointegrated (Engle and Granger [17]). Nicholls et al [18] and Schwert [19, pp.…”

Testing for Moving Average Regression Disturbances

“…Although there are good reasons why one should suspect MA disturbances in dynamic econometric models (see, for example, Sims, 1974 andNicholls et al, 1975), occasionally there is a need to test for 'Manuscript received February 16, 1982;revised August 24, 1982. MA disturbances in models without lagged dependent variables as regressors. Examples can be found in papers by Zellner & Montmarquette (1971), Rowley & Wilton (1973), and Kenward (1975). The purpose of this paper is to investigate the problem of testing for first order MA (MA(1)) disturbances in such regression models.…”