DoWhyClassExercise (Oct11)(1)

School

Boston University *

*We aren’t endorsed by this school

Course

BA472

Subject

Computer Science

Date

Jan 9, 2024

Type

Pages

Uploaded by MagistrateHyena2457

#!/usr/bin/env python3 # -*- coding: utf-8 -*- """ Created on Wed Oct 11 13:20:15 2023 This document was created by Dr. N. Orkun Baycik and cannot be shared with anyone without permission @author: nobaycik """ import pandas as pd import numpy as np IncomeData = pd.read_csv("/Users/shunnosuke/Desktop/BA472/Income.txt", delimiter = "\t") print(IncomeData) print(IncomeData) import dowhy from dowhy import CausalModel import warnings warnings.filterwarnings('ignore') #Create a causal diagram causal_graph = """ digraph { Age; PostGradDegree; Age -> PostGradDegree; Age -> AnnualIncome; PostGradDegree -> AnnualIncome; } """ from dowhy import CausalModel #Build the model in DoWhy model= CausalModel( data = IncomeData, graph=causal_graph.replace("\n", " "), treatment='PostGradDegree', outcome='AnnualIncome') model.view_model() #Identify the causal effect. Pearl's calculations in the

background estimands = model.identify_effect() #print(estimands) #----------------------------------------------BACKDOOR LINEAR REGRESSION---------------------------------------------- #Causal Effect Estimation. There are few methods to Estimate the Causal Effect causal_estimate_reg = model.estimate_effect(estimands, method_name="backdoor.linear_regression", test_significance=True) #Validation of assumptions. Add a placebo treatment. Replace the true treatment variable with an independent random variable; #If the assumption was correct, the estimate should go close to zero. placebo_refute_blr = model.refute_estimate(estimands, causal_estimate_reg, method_name="placebo_treatment_refuter", num_simulations=20) #Validation of assumptions. Data Subset Refuter replace the given dataset with a randomly selected subset; # #If the assumption was correct, the estimation should not change that much. # subset_refute_bdm = model.refute_estimate(estimands, causal_estimate_dmatch, # method_name="data_subset_refuter", num_simulations=20) # print("BACKDOOR DISTANCE MATCHING RESULTS") # print("Results with placebo treatment refuter:") # print(placebo_refute_bdm) # print("Results with data subset refuter:") # print(subset_refute_bdm) #---------------------------------------------------------------- ----------------------------------------- #----------------------------------------------BACKDOOR PROPENSITY SCORE MATCHING----------------------------------------------

causal_estimate_match = model.estimate_effect(estimands, method_name="backdoor.propensity_score_matching", #target_units="ate", test_significance=True) #Validation of assumptions. Add a placebo treatment. Replace the true treatment variable with an independent random variable; #If the assumption was correct, the estimate should go close to zero. placebo_refute_bpsm = model.refute_estimate(estimands,causal_estimate_match, method_name = "placebo_treatment_refuter", num_simulations=20) #Validation of assumptions. Data Subset Refuter replace the given dataset with a randomly selected subset; #If the assumption was correct, the estimation should not change that much. placebo_refute_bpsw = model.refute_estimate(estimands,causal_estimate_ipw, method_name = "placebo_treatment_refuter", num_simulations=20) #Validation of assumptions. Add a placebo treatment. Replace the true treatment variable with an independent random variable; #If the assumption was correct, the estimate should go close to zero. subset_refute_bpsw = model.refute_estimate(estimands,causal_estimate_ipw, method_name = "data_subset_refuter", num_simulations=20) print("BACKDOOR PROPENSITY SCORE WEIGHTING RESULTS") print("Results with placebo treatment refuter:") print(placebo_refute_bpsw) print("Results with data subset refuter:") print(subset_refute_bpsw) #---------------------------------------------------------------- -----------------------------------------

Your preview ends here

Eager to read complete document? Join bartleby learn and gain access to the full version

Access to all documents
Unlimited textbook solutions
24/7 expert homework help

#For a refutation test, the p-value denotes whether the test has found a problem with the estimate. #If p-value <0.05, this means that the estimate has a problem. If not, then we cannot conclude anything. #Since both p-values are >0.05, it means that the two tests are unable to find a problem in the estimate. #Note that refutations test the correctness of the estimating procedure, but not whether the effect is significantly away from zero. #---------------------------------------------------------------- -----------------------------------------

Related Documents

ModuleSixMilestone Document.docx

2-3 Intro to PyCharm Resendez.docx

2Santanna__Gorbey_HIS_200__Applied_History (1).docx

INT 220 Conference Call Invitation.docx

SCS 100 Module Three Activity MacDonald.docx

SCS 100 Module Four Activity MacDonald.docx

DoWhyProductivityExerciseSolutions.py

DoWhyClassExercise (Oct10).py

578 Quiz 3.pdf

Hart_Assignment 2 (1).docx

Quiz1_Practice_InterestCalc.pdf

CS 305 Module Five Coding Assignment Checksum Verification_Rupert.docx

Recommended textbooks for you

Np Ms Office 365/Excel 2016 I Ntermed

Computer Science

ISBN:9781337508841

Author:Carey

Publisher:Cengage

C++ for Engineers and Scientists

Computer Science

ISBN:9781133187844

Author:Bronson, Gary J.

Publisher:Course Technology Ptr

Programming Logic & Design Comprehensive

Computer Science

ISBN:9781337669405

Author:FARRELL

Publisher:Cengage

EBK JAVA PROGRAMMING

Computer Science

ISBN:9781337671385

Author:FARRELL

Publisher:CENGAGE LEARNING - CONSIGNMENT

C++ Programming: From Problem Analysis to Program...

Computer Science

ISBN:9781337102087

Author:D. S. Malik

Publisher:Cengage Learning

Systems Architecture

Computer Science

ISBN:9781305080195

Author:Stephen D. Burd

Publisher:Cengage Learning

SEE MORE TEXTBOOKS

Recommended textbooks for you

Np Ms Office 365/Excel 2016 I Ntermed
Computer Science
ISBN:9781337508841
Author:Carey
Publisher:Cengage
C++ for Engineers and Scientists
Computer Science
ISBN:9781133187844
Author:Bronson, Gary J.
Publisher:Course Technology Ptr
Programming Logic & Design Comprehensive
Computer Science
ISBN:9781337669405
Author:FARRELL
Publisher:Cengage
EBK JAVA PROGRAMMING
Computer Science
ISBN:9781337671385
Author:FARRELL
Publisher:CENGAGE LEARNING - CONSIGNMENT
C++ Programming: From Problem Analysis to Program...
Computer Science
ISBN:9781337102087
Author:D. S. Malik
Publisher:Cengage Learning
Systems Architecture
Computer Science
ISBN:9781305080195
Author:Stephen D. Burd
Publisher:Cengage Learning