Intradaily seasonality of returns distribution. A quantile regression approach and intradaily VaR estimation

We investigate intradaily seasonal patterns on the distribution of high frequency financial returns. Using quantile regression we show the expansions and shrinks of the probability law through the day for three years of 15 minutes sampled stock returns. Returns are more dispersed and less concentrated around the median at the hours near the opening and closing. We provide intradaily value at risk assessments and we show how it adapts to changes of dispersion over the day.