AI-ordlista
Den kompletta ordlistan över AI
Causal Graphical Models
Use of directed acyclic graphs (DAGs) to represent and analyze causal relationships between variables.
Propensity Scores
Statistical methods for balancing treatment and control groups using the conditional probability of being treated.
Instrumental Variables
A technique using variables correlated with the treatment but not directly with the outcome to identify causal effects.
Counterfactuals and Potential Outcomes
Theoretical framework based on comparing observed outcomes with unobserved potential outcomes.
Regression Discontinuity
Causal identification method exploiting thresholds in treatment assignment rules.
Difference-in-Differences
Quasi-experimental approach comparing changes over time between treated and untreated groups.
Causal Inference with Machine Learning
Application of machine learning algorithms to estimate causal effects in high-dimensional data.
Matching Methods
Techniques creating pairs of treated and untreated units with similar characteristics to estimate causal effects.
Mediation Analysis
Decomposition of total effects into direct and indirect effects to understand causal mechanisms.
Bayesian Causal Inference
Probabilistic approach incorporating prior knowledge to estimate causal relationships and their uncertainty.
Granger Causality Tests
Econometric methods to determine if one time series predicts another in time series analysis.
Synthetic Control Methods
Construction of a weighted synthetic control group to estimate the effects of policy interventions.