Value-at-Risk and Average Value-at-Risk are two important risk measures that used to measure the market's risk with quantity structure. However, both of these risk measures have defects in measuring risk. For this reason, the new risk measure GlueVaR has been introduced in 2014. In this paper the new measure is describe and the advantaes of this mesure are explained. A method for estimating the new mesure is provided using the COMPOSITE QUANTILE REGRESSION model. Finally, the efficiency of GlueVaR will be compared with two other mentioned risk measures for log-return data from the American’s stock market and Iran’s stock market.

Value-at-Risk and Average Value-at-Risk are tow important risk measures based on statistical methoeds that used to measure the market's risk with quantity structure.Recently, linear REGRESSION models such as least squares and QUANTILE methods are introduced to estimate these risk measures. In this paper, these two risk measures are estimated by using omposite QUANTILE REGRESSION. To evaluate the performance of the proposed model with the other models, a simulation study was conducted and at the end, applications to real data set from Iran's stock market are illustarted.

Objectives: Ordinary REGRESSION model is basically built for conditional mean to show the relationship between mean and some explanatory variables through a statistical model. Some assumptions like normality should be defined with an acceptable degree of confidence to correctly make inference from this type of model. If a measure other than mean is interested in or these assumptions are not satisfied due to outliers, this model will not be useful. However, QUANTILE REGRESSION is robust to the outliers and is able to build a model for any QUANTILEs (quartles, deciles and percentiles).Method: In this paper the application of QUANTILE REGRESSION is illustrated in the context of mental health data.Conclusion: In our study, QUANTILE REGRESSION findings have shown different relationship of age to mental health for men and women whereas these could not be achieved by mean REGRESSION at all.

In this research risk-return tradeoff examined in scope of ex post facto studies, using OLS Model and QUANTILE REGRESSION Model. By using of daily returns of six indexes of Tehran Stock Exchange (TSE), linear relation between excess return and risk examined that evidence indicates significant (positive) tradeoff between excess return and risk. However, results of QUANTILE REGRESSION model show that risk-return relation is different in returns distribution and vary from negative relation in the lower QUANTILEs to positive relation in the upper QUANTILEs. Linear REGRESSION model and QUANTILE REGRESSION model show also that unexpected variance can explain excess return at least similar to expected variance. The results can also be interpreted with both insight of standard finance and insight of behavioral finance. In standard finance area, risk-return positive relation that exists in upper quintiles is consistent with long run growth of economy. Moreover, negative relation between return and risk in lower quintiles implies more uncertainty and as a result causing stock returns to fall. In behavioral finance area, regime-dependent behavior of slope coefficients is consistent with prediction of prospect theory of investor’s behaviors around the reference point.