Σύγκριση μεθόδων

	Ανάλυση Αιτιώδους Επίπτωσης στην Αξιολόγηση Πολιτικής	Ανάλυση Αιτιώδους Επίπτωσης με Βάση το Bayes
Πεδίο	Αιτιακή Συμπερασματολογία	Αιτιακή Συμπερασματολογία
Οικογένεια	Regression model	Regression model
Έτος προέλευσης	2015	2015
Δημιουργός	Brodersen, Gallusser, Koehler, Remy & Scott (2015); adapted for policy evaluation contexts	Brodersen, Gallusser, Koehler, Remy & Scott (Google)
Τύπος	Bayesian counterfactual / time-series	Bayesian causal inference / time series
Θεμελιώδης πηγή	Brodersen, K. H., Gallusser, F., Koehler, J., Remy, N., & Scott, S. L. (2015). Inferring causal impact using Bayesian structural time-series models. Annals of Applied Statistics, 9(1), 247-274.	Brodersen, K. H., Gallusser, F., Koehler, J., Remy, N., & Scott, S. L. (2015). Inferring causal impact using Bayesian structural time-series models. Annals of Applied Statistics, 9(1), 247-274.
Εναλλακτικές ονομασίες	policy causal impact, BSTS policy evaluation, Bayesian policy impact assessment, CIA policy evaluation	CausalImpact, Bayesian structural time series causal inference, BSTS causal impact, Bayesian intervention analysis
Συναφείς	6	4
Σύνοψη	Policy Evaluation Causal Impact Analysis applies the Bayesian structural time-series (BSTS) framework of Brodersen et al. (2015) to estimate the causal effect of a policy intervention on aggregate outcomes. By constructing a synthetic counterfactual from pre-policy data and control covariates, it asks: what would have happened had the policy not been enacted? The difference between observed and predicted post-policy outcomes is the estimated policy effect.	Bayesian Causal Impact Analysis uses a Bayesian structural time series (BSTS) model to estimate the causal effect of an intervention on a time series outcome. Developed by Brodersen and colleagues at Google in 2015, it builds a probabilistic counterfactual — what the series would have looked like without the intervention — from pre-intervention data and optional control covariates, then compares it with the observed post-intervention values to produce a fully Bayesian posterior over the causal effect.