Green Silence: Double Machine Learning Carbon Emissions Under Sample Selection Bias

Voluntary carbon disclosure collapses into a paradox of green silence: firms choose to disclose emissions based on strategic incentives (e.g., correcting vendor overestimates), while high emitters may exploit vendor estimation bias. Mirroring Heckman sample selection bias, this selfcensorship skews disclosed emissions into non-random samples, distorting climate risk pricing and policy. We bridge economic problem and machine learning, proposing a Heckman-inspired three-step framework in high-dimensional settings to correct for strategic non-disclosure and ensure variable selection consistency in the presence of sample selection bias. By integrating kernel group lasso (KG-lasso) and double machine learning (DML) from neighbouring firms, i.e., using information from carbon next door, we unveil systematic underestimation: empirical analysis of 3444 unique US firms (2010-2023) rejects the null of no selection bias. Our findings indicate that voluntary disclosure induces adverse selection, where green silence rewards polluters and undermines decarbonization. Underestimation translates to a $2.6 billion shortfall in tax revenues and up to $525 billion hidden social cost of carbon.