Table 2.13: Significance after correction for dependence: a bootstrap based approach.

Panel A: Bootstrap results under the null of a random walk, autoregressive, exponential garch model and a model which incorporates the structural change in the data for the LIFFE cocoa futures series in the period 1983:1-1987:12. The table lists the fractions of simulation results which are larger than the results for the original data series. The rows tPerf>tc, tBuy>tc, tSell<-tc, tBuy-Sell>tc and tBuy>tctSell<-tc show the fraction of the 500 bootstrapped time series for which the percentage of trading strategies with a significantly positive mean excess return, with a significantly positive mean buy return, with a significantly negative mean sell return, with a significantly positive mean buy-sell difference and with a significantly positive mean buy as well as a significantly negative mean sell return is larger than the same percentages when the trading strategies are applied to the original data series.
  RW AR EGARCH Trend
tPerf>tc 0.002 0.038 0.03 0.414
tBuy>tc 0.032 0.074 0.05 0.478
tSell<-tc 0.14 0.274 0.334 0.528
tBuy-Sell>tc 0 0.012 0.002 0.248
tBuy>tctSell<-tc 0.006 0.016 0.012 0.426





Panel B: Bootstrap results under the null of a random walk, autoregressive, exponential garch model and a model which incorporates the structural change in the data for the LIFFE cocoa futures series in the period 1983:1-1987:12. The table lists the fractions of simulation results which are larger than the results for the original data series. The rows tPerf<-tc, tBuy<-tc, tSell>tc, tBuy-Sell<-tc and tBuy<-tctSell>tc show the fraction of the 500 bootstrapped time series for which the percentage of trading strategies with a significantly negative mean excess return, with a significantly negative mean buy return, with a significantly positive mean sell return, with a significantly negative mean buy-sell difference and with a significantly negative mean buy as well as a significantly positive mean sell return is larger than the same percentages when the trading strategies are applied to the original data series.

  RW AR EGARCH Trend
tPerf<-tc 0.964 0.936 0.942 0.96
tBuy<-tc 0.87 0.838 0.902 0.858
tSell>tc 0.572 0.502 0.428 0.776
tBuy-Sell<-tc 0.968 0.95 0.942 0.952
tBuy<-tctSell>tc 0.342 0.274 0.278 0.542

85