In the field of gamma-ray astronomy, irregular and noisy datasets make difficult the characterization of light-curve features in terms of statistical significance while properly accounting for trial factors associated with the search for variability
at different times and over different timescales. In order to address these difficulties, we propose a method based on the Haar wavelet decomposition of the data. It allows statistical characterization of possible variability, embedded in a white noise background, in terms of a confidence level. The method is applied to artificially generated data for characterization as well as to the the very high energy M87 light curve recorded with VERITAS in 2008 which serves here as a realistic application example.
