Example Notebooks

Contents:

• DoWhy:一个简单例子
  • 建立因果模型
    • Interface 1: 输入因果图(recommended)
    • Interface 2: 指定共同原因和工具变量
  • 稳健性分析
    • Adding a random common cause variable
    • Adding an unobserved common cause variable
    • Replacing treatment with a random (placebo) variable
    • Removing a random subset of the data
• 相关性还是因果效应？
  • 数据集
  • Does Treatment cause Outcome?
    • STEP 1: Model the problem as a causal graph
    • STEP 2: Identify causal effect using properties of the formal causal graph
    • STEP 3: Estimate the causal effect
    • Step 4: Refuting the estimate
• DoWhy: 因果效应估计方法
  • 方法1：回归
  • 方法2：分层
  • 方法3：匹配
  • 方法4：加权方法
  • 方法5：工具变量法
  • 方法6：断点回归法
• 用 DoWhy 和 EconML 估计条件平均因果效应
  • 线性模型
  • EconML 方法
    • CATE Object 和置信区间
    • New inputs 的因果效应
  • Works with any EconML method
    • Continuous treatment, Continuous outcome
    • Binary treatment, Binary outcome
    • 工具变量法
    • Metalearners
  • Refuting the estimate
    • Random
    • Adding an unobserved common cause variable
    • Replacing treatment with a random (placebo) variable
    • Removing a random subset of the data
• DoWhy 因果 API Demo
  • 获得因果模型和数据
  • 对比线性回归模型
• Do-sampler 简介
  • Pearlian 干预
    • Statefulness
    • Integration
    • Specifying Interventions
  • Demo
• Different ways to load an input graph
  • Loading GML graphs
  • Loading DOT graphs
• 工具变量法估计因果效应
• IHDP 因果效应估计
  • 1.Model
  • 2.Identify
  • 3. Estimate (using different methods)
    • 3.1 Using Linear Regression
    • 3.2 Using Propensity Score Matching
    • 3.3 Using Propensity Score Stratification
    • 3.4 Using Propensity Score Weighting
  • 4. Refute
    • 4.1 Adding a random common cause
    • 4.2 Using a placebo treatment
    • 4.3 Data Subset Refuter
• Lalonde 数据集上因果推断
  • Run DoWhy analysis: model, identify, estimate
  • Sanity check: compare to manual IPW estimate
• Lalonde Pandas API Example
  • 获得数据
  • do 算子
  • 因果效应估计
  • Specifying Interventions