How do perceptions of scientists’ moral values relate to support for science in society? Recent advances in the sociology of science and religion suggest that people associate scientists with moral values in addition to factual knowledge, and that concerns about scientists’ morality are why members of some religious groups are more critical of science than non-religious people. We test this theory using data from a probability sample of U.S. adults that includes new measures of beliefs about scientists’ moral values, such as their compassion, fairness, and generosity (n = 1,513). Results from structural equation models indicate that active members of all religious groups are, to varying degrees, more skeptical than atheists and agnostics of scientists’ moral character. A decomposition of direct and indirect effects indicates that beliefs about scientists’ moral values play an intermediary role in the relationship between religion and support for science, and that support for science among the religious is partially suppressed by their concerns about scientists’ morality. This article offers the first direct evidence of the moral culture the U.S. public associates with scientists. We suggest that religious differences in support for organized science reflect religious differences in beliefs about scientists’ moral values.

Forecasts of regional electricity net-demand, consumption minus embedded generation, are an essential input for reliable and economic power system operation, and energy trading. While such forecasts are typically performed region by region, operations such as managing power flows require spatially coherent joint forecasts, which account for cross-regional dependencies. Here, we forecast the joint distribution of net-demand across the 14 regions constituting Great Britain’s electricity network. Joint modeling is complicated by the fact that the net-demand variability within each region, and the dependencies between regions, vary with temporal, socio-economic and weather-related factors. We accommodate for these characteristics by proposing a multivariate Gaussian model based on a modified Cholesky parameterization, which allows us to model each unconstrained parameter via an additive model. Given that the number of model parameters and covariates is large, we adopt a semi-automated approach to model selection, based on gradient boosting. In addition to comparing the forecasting performance of several versions of the proposed model with that of two non-Gaussian copula-based models, we visually explore the model output to interpret how the covariates affect net-demand variability and dependencies. The code for reproducing the results in this article is available at https://doi.org/10.5281/zenodo.7315105. Supplementary materials for this article are available online, including a standardized description of the materials available for reproducing the work.