Viewing Discretionary Accruals through the Univariate Lens : A Conditional Heteroscedastic Mean-Variance Approach

On a firm-by-firm basis, we apply the univariate conditional heteroscedastic (UCH) mean-variance modeling technique – hereafter called ‘UCH Model' – to propose a new way to decoupling a firm's discretionary from non-discretionary accruals. Exploiting the intuition that linear dependence in accruals embodies all plausible accruals determinants, what the UCH Model essentially does is it kills any linear dependence in accruals estimation errors to isolate firm-specific shocks to accruals reporting so that ‘model misspecification' and ‘low test power' concerns – known to have plagued existing accruals models – are mechanically eliminated. Validation tests reveal that this new discretionary accruals measure appeals to economic theories (i.e. ‘smoothing' and other managerial intents) largely popularized in literature. While this measure substantially co-moves with existing measures, we show that the UCH Model outperforms classical models on several grounds aside those captioned above. We therefore encourage accounting researchers to apply this methodology as well in slicing other accounting variables