We examine the efficiency of a GJR-GARCH model where the residuals follow the standardize Pearson type-IV distribution. As a case study we consider the historical daily close price of the Standard and Poor’s index. The model is tested with a variety of loss functions and the efficiency is examined by application of several Value-at-Risk tests and measures. The results indicate that the Pearson type IV distribution performs better than the skewed t-Student especially at the high confidence levels.