The convex hull of consecutive pairs of observations from some time series models (Q2443887)

The authors study the asymptotic behavior of the number of vertices of the convex hull of time series pairs from three models. The first is the stochastic volatility process given by \(X_t = \sigma_t Z_t,\) where \(\{Z_t\}\) is a sequence of i.i.d. continuous random variables from a regularly varying distribution at infinity with exponent \(\alpha >0\) and \(\operatorname{E}|Z_t|^\alpha = \infty \) and is independent of \(\{\sigma_t \},\) a stationary volatility sequence of nonnegative random variables with \(\operatorname{E}(\sigma_t^{2 \alpha + \epsilon}) < \infty,\) for some \(\epsilon > 0\). Under some conditions it is shown that the number of vertices of the convex hull of pairs from this process \(N_n\) tends to 4 in probability and the expectation of this tends to 4 and the variance tends to 0 as \(n\) tends to \(\infty\). The second model is for pairs from a moving average process wherein more involved convergence in distribution results are obtained. And, the third model is for pairs from a GARCH process for which it is shown that \(N_n \geq 5\) with positive probability.