Author: Spencer Woody; Mauricio Garcia Tec; Maytal Dahan; Kelly Gaither; Spencer Fox; Lauren Ancel Meyers; James G Scott
Title: Projections for first-wave COVID-19 deaths across the US using social-distancing measures derived from mobile phones Document date: 2020_4_22
ID: 87lxnslh_30
Snippet: The model is fit by a penalized nonlinear least-squares procedure, encouraging the parameters of each state's λ i (t) curve to be shrunk towards a common conditional mean, given social-distancing covariates. They interpret the result as a hierarchical Bayesian MAP estimate under an assumed prior, and use the inverse Hessian matrix at the MAP estimate as plug-in estimate of the posterior covariance matrix for the model parameters......
Document: The model is fit by a penalized nonlinear least-squares procedure, encouraging the parameters of each state's λ i (t) curve to be shrunk towards a common conditional mean, given social-distancing covariates. They interpret the result as a hierarchical Bayesian MAP estimate under an assumed prior, and use the inverse Hessian matrix at the MAP estimate as plug-in estimate of the posterior covariance matrix for the model parameters.
Search related documents:
Co phrase search for related documents- bayesian MAP estimate and prior assumed bayesian MAP estimate: 1
- conditional mean and model parameter: 1
- covariance matrix and hessian matrix: 1
- covariance matrix and inverse hessian matrix: 1
- covariance matrix and MAP estimate: 1
- covariance matrix and model parameter: 1
- hessian matrix and inverse hessian matrix: 1
- hessian matrix and MAP estimate: 1
- inverse hessian matrix and MAP estimate: 1
Co phrase search for related documents, hyperlinks ordered by date