What works in Boston may not work in Los Angeles:Understanding site di↵erences and generalizing e↵ects
from one site to another.
Kara Rudolphwith Mark van der Laan
RWJF Health and Society ScholarUC Berkeley / UC San Francisco
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 1 / 39
Outline
1Motivation
Motivating example
2Methodologic Challenges
3Approach
4Results
5Future directions
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 2 / 39
Motivation
Should we expect that a policy/program/intervention implemented inone place will have the same e↵ect when implemented in anotherplace?
Not always.
1 Di↵erences in site-level variables (e.g., implementation, economy) thatmodify intervention e↵ectiveness, AND/OR
2 Di↵erences in person-level variables (i.e, population composition) thatmodify intervention e↵ectiveness.
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 3 / 39
Motivation
Should we expect that a policy/program/intervention implemented inone place will have the same e↵ect when implemented in anotherplace?
Not always.
1 Di↵erences in site-level variables (e.g., implementation, economy) thatmodify intervention e↵ectiveness, AND/OR
2 Di↵erences in person-level variables (i.e, population composition) thatmodify intervention e↵ectiveness.
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 3 / 39
Motivation
Should we expect that a policy/program/intervention implemented inone place will have the same e↵ect when implemented in anotherplace?
Not always.
1 Di↵erences in site-level variables (e.g., implementation, economy) thatmodify intervention e↵ectiveness, AND/OR
2 Di↵erences in person-level variables (i.e, population composition) thatmodify intervention e↵ectiveness.
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 3 / 39
Motivation
Should we expect that a policy/program/intervention implemented inone place will have the same e↵ect when implemented in anotherplace?
Not always.
1 Di↵erences in site-level variables (e.g., implementation, economy) thatmodify intervention e↵ectiveness, AND/OR
2 Di↵erences in person-level variables (i.e, population composition) thatmodify intervention e↵ectiveness.
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 3 / 39
Motivation
Budgets are limited.
Need to target the policy/intervention to those places that stand tobenefit most.
E.g., planned expansion of intervention. Where should it be expandedto have the largest e↵ect? How is success defined?
Can you think of any practical examples of this?
Research question: What do we expect the e↵ect of anintervention to be in a new place, accounting for populationcomposition?
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 4 / 39
Motivation
Budgets are limited.
Need to target the policy/intervention to those places that stand tobenefit most.
E.g., planned expansion of intervention. Where should it be expandedto have the largest e↵ect? How is success defined?
Can you think of any practical examples of this?
Research question: What do we expect the e↵ect of anintervention to be in a new place, accounting for populationcomposition?
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 4 / 39
Motivation
Budgets are limited.
Need to target the policy/intervention to those places that stand tobenefit most.
E.g., planned expansion of intervention. Where should it be expandedto have the largest e↵ect? How is success defined?
Can you think of any practical examples of this?
Research question: What do we expect the e↵ect of anintervention to be in a new place, accounting for populationcomposition?
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 4 / 39
Motivation
Budgets are limited.
Need to target the policy/intervention to those places that stand tobenefit most.
E.g., planned expansion of intervention. Where should it be expandedto have the largest e↵ect? How is success defined?
Can you think of any practical examples of this?
Research question: What do we expect the e↵ect of anintervention to be in a new place, accounting for populationcomposition?
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 4 / 39
Motivation
Budgets are limited.
Need to target the policy/intervention to those places that stand tobenefit most.
E.g., planned expansion of intervention. Where should it be expandedto have the largest e↵ect? How is success defined?
Can you think of any practical examples of this?
Research question: What do we expect the e↵ect of anintervention to be in a new place, accounting for populationcomposition?
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 4 / 39
Outline
1Motivation
Motivating example
2Methodologic Challenges
3Approach
4Results
5Future directions
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 5 / 39
Motivating Example
Moving To Opportunity (MTO)1
https://upload.wikimedia.org/
http://www.chicagomag.com
1Kling, J. R. et al. Experimental analysis of neighborhood e↵ects. Econometrica 75, 83–119 (2007).
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 6 / 39
Motivating Example
In discussing di↵erences in e↵ects across sites, MTO researchers concluded:
Of course, if it had been possible to attribute di↵erences inimpacts across sites to di↵erences in site characteristics, thatwould have been very valuable information. Unfortunately, thatwas not possible. With only five sites, which di↵er ininnumerable potentially relevant ways, it was simply not possibleto disentangle the underlying factors that cause impacts to varyacross sites. (This is true for both the quantitative analysis andfor any qualitative analysis of the impacts that might beundertaken.)2
Why are the researchers saying this? Do you agree?
2Orr, L. et al. Moving to opportunity: Interim impacts evaluation. (2003), p.B11.
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 7 / 39
Motivating Example
Research Question (MTO-specific): Are di↵erences in interventione↵ects across cities due to di↵erences in implementation? City-leveldi↵erences (e.g, the economy)? Or di↵erences in populationcomposition?
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 8 / 39
Outline
1Motivation
Motivating example
2Methodologic Challenges
3Approach
4Results
5Future directions
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 9 / 39
Methodologic Challenges
Typically, multi-site data are analyzed using fixed e↵ects.
Usually assumes that we answered “Yes” to whether we expect theintervention e↵ect in one site is the same as the other site.
Why is that the case?
Dummy variables for site changes the intercept but not the treatmente↵ect coe�cient. Assume that the conditional e↵ect (regressioncoe�cient) of the intervention in one site is the same as in another site.
Need to apply the results from one city/site to a target city/sitebased on the observed population composition.
Transportability/ generalizability/ external validity.
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 10 / 39
Methodologic Challenges
Typically, multi-site data are analyzed using fixed e↵ects.
Usually assumes that we answered “Yes” to whether we expect theintervention e↵ect in one site is the same as the other site.
Why is that the case?
Dummy variables for site changes the intercept but not the treatmente↵ect coe�cient. Assume that the conditional e↵ect (regressioncoe�cient) of the intervention in one site is the same as in another site.
Need to apply the results from one city/site to a target city/sitebased on the observed population composition.
Transportability/ generalizability/ external validity.
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 10 / 39
Methodologic Challenges
Typically, multi-site data are analyzed using fixed e↵ects.
Usually assumes that we answered “Yes” to whether we expect theintervention e↵ect in one site is the same as the other site.
Why is that the case?
Dummy variables for site changes the intercept but not the treatmente↵ect coe�cient. Assume that the conditional e↵ect (regressioncoe�cient) of the intervention in one site is the same as in another site.
Need to apply the results from one city/site to a target city/sitebased on the observed population composition.
Transportability/ generalizability/ external validity.
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 10 / 39
Methodologic Challenges
Typically, multi-site data are analyzed using fixed e↵ects.
Usually assumes that we answered “Yes” to whether we expect theintervention e↵ect in one site is the same as the other site.
Why is that the case?
Dummy variables for site changes the intercept but not the treatmente↵ect coe�cient. Assume that the conditional e↵ect (regressioncoe�cient) of the intervention in one site is the same as in another site.
Need to apply the results from one city/site to a target city/sitebased on the observed population composition.
Transportability/ generalizability/ external validity.
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 10 / 39
Methodologic Challenges
Typically, multi-site data are analyzed using fixed e↵ects.
Usually assumes that we answered “Yes” to whether we expect theintervention e↵ect in one site is the same as the other site.
Why is that the case?
Dummy variables for site changes the intercept but not the treatmente↵ect coe�cient. Assume that the conditional e↵ect (regressioncoe�cient) of the intervention in one site is the same as in another site.
Need to apply the results from one city/site to a target city/sitebased on the observed population composition.
Transportability/ generalizability/ external validity.
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 10 / 39
Methodologic Challenges
Typically, multi-site data are analyzed using fixed e↵ects.
Usually assumes that we answered “Yes” to whether we expect theintervention e↵ect in one site is the same as the other site.
Why is that the case?
Dummy variables for site changes the intercept but not the treatmente↵ect coe�cient. Assume that the conditional e↵ect (regressioncoe�cient) of the intervention in one site is the same as in another site.
Need to apply the results from one city/site to a target city/sitebased on the observed population composition.
Transportability/ generalizability/ external validity.
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 10 / 39
What’s been done
Most common: Use fixed e↵ects for site.
- Conditional e↵ect is not as policy relevant as marginal e↵ect
- We usually don’t believe the assumption
Common-ish: Post-stratification/ direct standardization.3E.g.,age-adjusted rates of disease for comparisons between populations.
- Breaks down with continuous characteristics or multiple charactersticsbecause of small cell sizes
- No standard errors/ no inference
3Miettinen, O. S. Standardization of risk ratios. American Journal of Epidemiology 96, 383–388 (1972).
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 11 / 39
What’s been done
Most common: Use fixed e↵ects for site.
- Conditional e↵ect is not as policy relevant as marginal e↵ect
- We usually don’t believe the assumption
Common-ish: Post-stratification/ direct standardization.3E.g.,age-adjusted rates of disease for comparisons between populations.
- Breaks down with continuous characteristics or multiple charactersticsbecause of small cell sizes
- No standard errors/ no inference
3Miettinen, O. S. Standardization of risk ratios. American Journal of Epidemiology 96, 383–388 (1972).
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 11 / 39
What’s been done
Most common: Use fixed e↵ects for site.
- Conditional e↵ect is not as policy relevant as marginal e↵ect
- We usually don’t believe the assumption
Common-ish: Post-stratification/ direct standardization.3E.g.,age-adjusted rates of disease for comparisons between populations.
- Breaks down with continuous characteristics or multiple charactersticsbecause of small cell sizes
- No standard errors/ no inference
3Miettinen, O. S. Standardization of risk ratios. American Journal of Epidemiology 96, 383–388 (1972).
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 11 / 39
What’s been done
Most common: Use fixed e↵ects for site.
- Conditional e↵ect is not as policy relevant as marginal e↵ect
- We usually don’t believe the assumption
Common-ish: Post-stratification/ direct standardization.3E.g.,age-adjusted rates of disease for comparisons between populations.
- Breaks down with continuous characteristics or multiple charactersticsbecause of small cell sizes
- No standard errors/ no inference
3Miettinen, O. S. Standardization of risk ratios. American Journal of Epidemiology 96, 383–388 (1972).
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 11 / 39
What’s been done
Most common: Use fixed e↵ects for site.
- Conditional e↵ect is not as policy relevant as marginal e↵ect
- We usually don’t believe the assumption
Common-ish: Post-stratification/ direct standardization.3E.g.,age-adjusted rates of disease for comparisons between populations.
- Breaks down with continuous characteristics or multiple charactersticsbecause of small cell sizes
- No standard errors/ no inference
3Miettinen, O. S. Standardization of risk ratios. American Journal of Epidemiology 96, 383–388 (1972).
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 11 / 39
What’s been done
Most common: Use fixed e↵ects for site.
- Conditional e↵ect is not as policy relevant as marginal e↵ect
- We usually don’t believe the assumption
Common-ish: Post-stratification/ direct standardization.3E.g.,age-adjusted rates of disease for comparisons between populations.
- Breaks down with continuous characteristics or multiple charactersticsbecause of small cell sizes
- No standard errors/ no inference
3Miettinen, O. S. Standardization of risk ratios. American Journal of Epidemiology 96, 383–388 (1972).
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 11 / 39
What’s been done
Less common, rare: Model-based approaches: Horvitz-Thompsonweighting (model-based standardization),4propensity scorematching,5and principal stratification6
- Relies on correct model specification
- Inference with machine learning is unclear
- With exception of principal stratification, have not been extended toencouragement-design interventions
Pearl and Bareinbom: formalized theory and assumptions fortransportability7
4Cole, S. R. & Stuart, E. A. Generalizing Evidence From Randomized Clinical Trials to Target Populations The ACTG 320Trial. American journal of epidemiology 172, 107–115 (2010).
5Stuart, E. A. et al. The use of propensity scores to assess the generalizability of results from randomized trials. Journal of
the Royal Statistical Society: Series A (Statistics in Society) 174, 369–386 (2011).6Frangakis, C. The calibration of treatment e↵ects from clinical trials to target populations. Clinical trials (London,
England) 6, 136 (2009).7Pearl, J. & Bareinboim, E. Transportability across studies: A formal approach tech. rep. (DTIC Document, 2011).
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 12 / 39
What’s been done
Less common, rare: Model-based approaches: Horvitz-Thompsonweighting (model-based standardization),4propensity scorematching,5and principal stratification6
- Relies on correct model specification
- Inference with machine learning is unclear
- With exception of principal stratification, have not been extended toencouragement-design interventions
Pearl and Bareinbom: formalized theory and assumptions fortransportability7
4Cole, S. R. & Stuart, E. A. Generalizing Evidence From Randomized Clinical Trials to Target Populations The ACTG 320Trial. American journal of epidemiology 172, 107–115 (2010).
5Stuart, E. A. et al. The use of propensity scores to assess the generalizability of results from randomized trials. Journal of
the Royal Statistical Society: Series A (Statistics in Society) 174, 369–386 (2011).6Frangakis, C. The calibration of treatment e↵ects from clinical trials to target populations. Clinical trials (London,
England) 6, 136 (2009).7Pearl, J. & Bareinboim, E. Transportability across studies: A formal approach tech. rep. (DTIC Document, 2011).
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 12 / 39
What’s been done
Less common, rare: Model-based approaches: Horvitz-Thompsonweighting (model-based standardization),4propensity scorematching,5and principal stratification6
- Relies on correct model specification
- Inference with machine learning is unclear
- With exception of principal stratification, have not been extended toencouragement-design interventions
Pearl and Bareinbom: formalized theory and assumptions fortransportability7
4Cole, S. R. & Stuart, E. A. Generalizing Evidence From Randomized Clinical Trials to Target Populations The ACTG 320Trial. American journal of epidemiology 172, 107–115 (2010).
5Stuart, E. A. et al. The use of propensity scores to assess the generalizability of results from randomized trials. Journal of
the Royal Statistical Society: Series A (Statistics in Society) 174, 369–386 (2011).6Frangakis, C. The calibration of treatment e↵ects from clinical trials to target populations. Clinical trials (London,
England) 6, 136 (2009).7Pearl, J. & Bareinboim, E. Transportability across studies: A formal approach tech. rep. (DTIC Document, 2011).
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 12 / 39
What’s been done
Less common, rare: Model-based approaches: Horvitz-Thompsonweighting (model-based standardization),4propensity scorematching,5and principal stratification6
- Relies on correct model specification
- Inference with machine learning is unclear
- With exception of principal stratification, have not been extended toencouragement-design interventions
Pearl and Bareinbom: formalized theory and assumptions fortransportability7
4Cole, S. R. & Stuart, E. A. Generalizing Evidence From Randomized Clinical Trials to Target Populations The ACTG 320Trial. American journal of epidemiology 172, 107–115 (2010).
5Stuart, E. A. et al. The use of propensity scores to assess the generalizability of results from randomized trials. Journal of
the Royal Statistical Society: Series A (Statistics in Society) 174, 369–386 (2011).6Frangakis, C. The calibration of treatment e↵ects from clinical trials to target populations. Clinical trials (London,
England) 6, 136 (2009).7Pearl, J. & Bareinboim, E. Transportability across studies: A formal approach tech. rep. (DTIC Document, 2011).
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 12 / 39
What’s been done
Less common, rare: Model-based approaches: Horvitz-Thompsonweighting (model-based standardization),4propensity scorematching,5and principal stratification6
- Relies on correct model specification
- Inference with machine learning is unclear
- With exception of principal stratification, have not been extended toencouragement-design interventions
Pearl and Bareinbom: formalized theory and assumptions fortransportability7
4Cole, S. R. & Stuart, E. A. Generalizing Evidence From Randomized Clinical Trials to Target Populations The ACTG 320Trial. American journal of epidemiology 172, 107–115 (2010).
5Stuart, E. A. et al. The use of propensity scores to assess the generalizability of results from randomized trials. Journal of
the Royal Statistical Society: Series A (Statistics in Society) 174, 369–386 (2011).6Frangakis, C. The calibration of treatment e↵ects from clinical trials to target populations. Clinical trials (London,
England) 6, 136 (2009).7Pearl, J. & Bareinboim, E. Transportability across studies: A formal approach tech. rep. (DTIC Document, 2011).
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 12 / 39
Outline
1Motivation
Motivating example
2Methodologic Challenges
3Approach
4Results
5Future directions
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 13 / 39
Our contribution
New statistical method for “transporting” e↵ects from one population toanother8
Transport formula for multi-site encouragement-design interventions(extending Pearl and Bareinboim’s work).
Estimation using transport formulas addressing previous gaps:
+ Inference based on theory (even when using machine learning)
+ Double robust: can misspecify multiple models and still get unbiasedestimates
8Rudolph, K. E. & van der Laan, M. J. Double Robust Estimation of Encouragement-design Intervention E↵ectsTransported Across Sites. Under Review (2015).
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 14 / 39
Our contribution
New statistical method for “transporting” e↵ects from one population toanother8
Transport formula for multi-site encouragement-design interventions(extending Pearl and Bareinboim’s work).
Estimation using transport formulas addressing previous gaps:
+ Inference based on theory (even when using machine learning)
+ Double robust: can misspecify multiple models and still get unbiasedestimates
8Rudolph, K. E. & van der Laan, M. J. Double Robust Estimation of Encouragement-design Intervention E↵ectsTransported Across Sites. Under Review (2015).
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 14 / 39
Our contribution
New statistical method for “transporting” e↵ects from one population toanother8
Transport formula for multi-site encouragement-design interventions(extending Pearl and Bareinboim’s work).
Estimation using transport formulas addressing previous gaps:
+ Inference based on theory (even when using machine learning)
+ Double robust: can misspecify multiple models and still get unbiasedestimates
8Rudolph, K. E. & van der Laan, M. J. Double Robust Estimation of Encouragement-design Intervention E↵ectsTransported Across Sites. Under Review (2015).
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 14 / 39
Our contribution
New statistical method for “transporting” e↵ects from one population toanother8
Transport formula for multi-site encouragement-design interventions(extending Pearl and Bareinboim’s work).
Estimation using transport formulas addressing previous gaps:
+ Inference based on theory (even when using machine learning)
+ Double robust: can misspecify multiple models and still get unbiasedestimates
8Rudolph, K. E. & van der Laan, M. J. Double Robust Estimation of Encouragement-design Intervention E↵ectsTransported Across Sites. Under Review (2015).
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 14 / 39
Problem: there are a lot of relationships to specify and wedon’t know the truth!
$ = <
:
6S ⇠ WZ ⇠ A,W ,A ⇤W , SY ⇠ Z ,W ,Z ⇤W , S
Can you guess the correct modelswhen W is high dimensional? Allinteractions? Correct form (e.g,linear, quadratic, spline)?
Note: A = instrument/encouragement, Z = exposure, Y = outcome, S =site, W = covariates/characteristics
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 15 / 39
Transport estimators
Targeted maximum likelihood estimators (TMLE) for the followingestimands:
E↵ect of A on Y (intent-to-treat)
E↵ect of Z on Y using randomization of the instrument (complieraverage treatment e↵ect)
E↵ect of Z on Y ignoring randomization
Note: A = instrument/encouragement, Z = exposure, Y = outcome, S =site, W = covariates/characteristics
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 16 / 39
In everyday language, what does TMLE do?
1 Start with identifying the parameter you’re interested in estimating.E.g., the ITTATE, .
2 Get initial estimate for . E.g., run a regression of the Y modelsetting A = 1 and A = 0. The di↵erence will be the initial estimate.
3 The Y model may not be perfect. (If it is, you’re done.) This initialestimate is then adjusted by something called the clever covariate, C ,which is derived from the e�cient influence curve. It uses informationfrom the other models improve upon the initial estimate.
4 This fluctuation can be iterated until convergence.
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 17 / 39
In everyday language, what does TMLE do?
LQLWLDO�HVWLPDWH WUXH�HVWLPDWH 70/(�HVWLPDWH
��&�
��&�
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 18 / 39
Outline
1Motivation
Motivating example
2Methodologic Challenges
3Approach
4Results
5Future directions
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 19 / 39
Performance
Results for intent-to-treat e↵ect of A on Y. Results are similar for thetwo other estimators.
Model specification % Bias Variance Coverage MSEAll models correct -0.67 0.0004 95.01 0.0004S model misspecified -0.49 0.0004 95.34 0.0004Z model misspecified -0.67 0.0004 95.00 0.0004Y model misspecified -0.71 0.0005 95.36 0.0005S,Z models misspecified -0.49 0.0004 95.29 0.0004S,Z,Y models misspecified 6.05 0.0004 94.84 0.0004
Note: A = instrument/encouragement, Z = exposure, Y = outcome, S =site, W = covariates/characteristics
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 20 / 39
Sensitivity to positivity violations
Structural positivity violations: Person with some set of covariatevalues in one treatment/selection group has a zero probability ofbeing in another treatment/selection group.
Practical positivity violations: This probability isn’t strictly zero, butit’s close.
Why is this a problem?
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 21 / 39
Sensitivity to positivity violations
Structural positivity violations: Person with some set of covariatevalues in one treatment/selection group has a zero probability ofbeing in another treatment/selection group.
Practical positivity violations: This probability isn’t strictly zero, butit’s close.
Why is this a problem?
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 21 / 39
Sensitivity to positivity violations
Structural positivity violations: Person with some set of covariatevalues in one treatment/selection group has a zero probability ofbeing in another treatment/selection group.
Practical positivity violations: This probability isn’t strictly zero, butit’s close.
Why is this a problem?
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 21 / 39
Sensitivity to positivity violations
Practical positivity violations are a substantial issue in real world data.
Why might we expect it in the example below?
Pre−Matching
0
2
4
0.00 0.25 0.50 0.75 1.00Predicted probability of job strain
dens
ity
Less job strainMore job strain
Post−Matching
0.0
0.5
1.0
1.5
2.0
0.00 0.25 0.50 0.75 1.00Predicted probability of job strain
dens
ity
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 22 / 39
Sensitivity to positivity violations
Practical positivity violations are a substantial issue in real world data.
Why might we expect it in the example below?
Pre−Matching
0
2
4
0.00 0.25 0.50 0.75 1.00Predicted probability of job strain
dens
ity
Less job strainMore job strain
Post−Matching
0.0
0.5
1.0
1.5
2.0
0.00 0.25 0.50 0.75 1.00Predicted probability of job strain
dens
ity
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 22 / 39
Sensitivity to positivity violations
Which of the 3 estimands is most vulnerable to these violations usingthe MTO data?
What are some other real-world examples that might be vulnerable topositivity violations?
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 23 / 39
Sensitivity to positivity violations
Which of the 3 estimands is most vulnerable to these violations usingthe MTO data?
What are some other real-world examples that might be vulnerable topositivity violations?
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 23 / 39
Sensitivity to positivity violations
CY
(A = 1)Mean(SD)
Min Max
EATEData-generatingmechanism 1
0.49(0.38) 0.05 2.46
Data-generatingmechanism 2
1.07(1.62) 0.15⇥10�2 26.26
Application 2.05(2.76) 4.54⇥10�2 13.11
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 24 / 39
Sensitivity to positivity violations
Specification %Bias SE⇥pn Cov MSE
(1.60)EATE: Without Positivity Violations
All models correct -0.31 1.60 94.94 0.0005S model misspecified -0.38 1.46 93.68 0.0005Z model misspecified -0.31 1.48 93.01 0.0005Y model misspecified -0.29 1.62 95.09 0.0005S,Z models misspecified -0.43 1.36 92.95 0.0004S,Z,Y models misspecified 14.46 1.37 76.27 0.0009
EATE: With Positivity ViolationsAll models correct 0.18 3.60 91.36 0.0029S model misspecified 1.98 1.96 86.33 0.0012Z model misspecified 0.18 2.67 82.93 0.0029Y model misspecified 2.09 4.17 96.05 0.0027S,Z models misspecified 2.18 1.38 79.27 0.0009S,Z,Y models misspecified -52.11 1.41 2.49 0.0065
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 25 / 39
Strategies for addressing positivity violations
Limit the sample to the area of support
Truncate weights
Exclude covariates that are neither 1) confounders of theexposure-outcome relationship, nor 2) a↵ect transportability.
Moving the weights from the clever covariate into the model fittingstep
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 26 / 39
Strategies for addressing positivity violations
Limit the sample to the area of support
Truncate weights
Exclude covariates that are neither 1) confounders of theexposure-outcome relationship, nor 2) a↵ect transportability.
Moving the weights from the clever covariate into the model fittingstep
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 26 / 39
Strategies for addressing positivity violations
Limit the sample to the area of support
Truncate weights
Exclude covariates that are neither 1) confounders of theexposure-outcome relationship, nor 2) a↵ect transportability.
Moving the weights from the clever covariate into the model fittingstep
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 26 / 39
Strategies for addressing positivity violations
Limit the sample to the area of support
Truncate weights
Exclude covariates that are neither 1) confounders of theexposure-outcome relationship, nor 2) a↵ect transportability.
Moving the weights from the clever covariate into the model fittingstep
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 26 / 39
Strategies for addressing positivity violations
Truncation Level %Bias SE⇥pn Cov MSE
EATENo modification 0.18 3.60 91.36 0.0029Truncation at 0.01/100 2.29 3.23 92.50 0.0024Truncation at 0.05/20 2.71 2.40 89.78 0.0016Truncation at 0.1/10 2.60 1.90 84.96 0.0013
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 27 / 39
Results
Can our new statistical method shed light on the previouslyintractable problem of not knowing why there are di↵erences ine↵ects across sites?
We take two of the sites: LA and Boston.
Outcome: adolescent school drop out at follow-up.
We use full data from Boston. We ignore the outcome data from LA.Using the outcome model from Boston, we predict the interventione↵ect in LA, accounting for di↵erences in population compositionbetween the two cities.
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 28 / 39
Results
Can our new statistical method shed light on the previouslyintractable problem of not knowing why there are di↵erences ine↵ects across sites?
We take two of the sites: LA and Boston.
Outcome: adolescent school drop out at follow-up.
We use full data from Boston. We ignore the outcome data from LA.Using the outcome model from Boston, we predict the interventione↵ect in LA, accounting for di↵erences in population compositionbetween the two cities.
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 28 / 39
Results
Can our new statistical method shed light on the previouslyintractable problem of not knowing why there are di↵erences ine↵ects across sites?
We take two of the sites: LA and Boston.
Outcome: adolescent school drop out at follow-up.
We use full data from Boston. We ignore the outcome data from LA.Using the outcome model from Boston, we predict the interventione↵ect in LA, accounting for di↵erences in population compositionbetween the two cities.
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 28 / 39
Results
Can our new statistical method shed light on the previouslyintractable problem of not knowing why there are di↵erences ine↵ects across sites?
We take two of the sites: LA and Boston.
Outcome: adolescent school drop out at follow-up.
We use full data from Boston. We ignore the outcome data from LA.Using the outcome model from Boston, we predict the interventione↵ect in LA, accounting for di↵erences in population compositionbetween the two cities.
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 28 / 39
Results
Real results: Boston
●
●
ITTATE CATE
−1.0
−0.5
0.0
0.5
1.0
Bost
on LA
Tran
spor
ted
LA, T
MLE
Bost
on LA
Tran
spor
ted
LA, T
MLE
Inte
rven
tion
Effe
ct o
n R
isk
of S
choo
l Dro
p O
ut
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 29 / 39
Results
Predicted results: LA
●
●
●
●
ITTATE CATE
−1.0
−0.5
0.0
0.5
1.0
Bost
on LA
Tran
spor
ted
LA, T
MLE
Bost
on LA
Tran
spor
ted
LA, T
MLE
Inte
rven
tion
Effe
ct o
n R
isk
of S
choo
l Dro
p O
ut
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 30 / 39
Results
Predicted vs. real results: LA
●
●●
●
●
●
ITTATE CATE
−1.0
−0.5
0.0
0.5
1.0
Bost
on LA
Tran
spor
ted
LA, T
MLE
Bost
on LA
Tran
spor
ted
LA, T
MLE
Inte
rven
tion
Effe
ct o
n R
isk
of S
choo
l Dro
p O
ut
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 31 / 39
Results
The transported estimates for LA are similar to true LA estimates.
Using population composition, we can predict the e↵ect for LA !intervention e↵ect on school dropout is transportable.
This means that the di↵erence in e↵ects between Boston and LA canbe largely explained by population composition.
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 32 / 39
Results
The transported estimates for LA are similar to true LA estimates.
Using population composition, we can predict the e↵ect for LA !intervention e↵ect on school dropout is transportable.
This means that the di↵erence in e↵ects between Boston and LA canbe largely explained by population composition.
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 32 / 39
Results
The transported estimates for LA are similar to true LA estimates.
Using population composition, we can predict the e↵ect for LA !intervention e↵ect on school dropout is transportable.
This means that the di↵erence in e↵ects between Boston and LA canbe largely explained by population composition.
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 32 / 39
Aside: the importance of incorporating machinelearning
●
● ●
●
●
●
●
●
ITTATE CATE
−3
−2
−1
0
1
Boston LATransported LA, TMLE Boston LATransported LA, TMLE
diffe
renc
e of
pro
babi
lity
of s
tayi
ng in
sch
ool
model●
●
●
noneparametricsuperlearner
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 33 / 39
Superlearner9
Ensemble machine learning
Weights multiple machine learning algorithms to get best prediction
Guaranteed to perform at least as well as best algorithm included inthe weighting
9Van der Laan, M. J. et al. Super learner. Statistical applications in genetics and molecular biology 6 (2007).
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 34 / 39
Policy implications
We should not expect an intervention/program/policy to have thesame e↵ect in one city as in another city.
In an era of shrinking budgets, important to recognize that whatworks in Boston may not work in LA, so resources can be targetedoptimally.
Broadly useful: multi-site epidemiologic studies, large-scale policy orprogram interventions, clinical trials.
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 35 / 39
Policy implications
We should not expect an intervention/program/policy to have thesame e↵ect in one city as in another city.
In an era of shrinking budgets, important to recognize that whatworks in Boston may not work in LA, so resources can be targetedoptimally.
Broadly useful: multi-site epidemiologic studies, large-scale policy orprogram interventions, clinical trials.
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 35 / 39
Policy implications
We should not expect an intervention/program/policy to have thesame e↵ect in one city as in another city.
In an era of shrinking budgets, important to recognize that whatworks in Boston may not work in LA, so resources can be targetedoptimally.
Broadly useful: multi-site epidemiologic studies, large-scale policy orprogram interventions, clinical trials.
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 35 / 39
Outline
1Motivation
Motivating example
2Methodologic Challenges
3Approach
4Results
5Future directions
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 36 / 39
Future Directions
Examine other strategies to reduce sensitivity to practical positivityviolations, especially excluding covariates and moving the weights.
In-depth application of transportability to MTO to understand therelationship between neighborhood poverty and exposure to violenceand violent behaviors.
Grant application to extend the transportability method to mediationmechanisms. Examine mediation of the relationship betweenneighborhood poverty on adolescent risk behaviors by the schoolenvironment.
Other ideas? Suggestions?
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 37 / 39
Future Directions
Examine other strategies to reduce sensitivity to practical positivityviolations, especially excluding covariates and moving the weights.
In-depth application of transportability to MTO to understand therelationship between neighborhood poverty and exposure to violenceand violent behaviors.
Grant application to extend the transportability method to mediationmechanisms. Examine mediation of the relationship betweenneighborhood poverty on adolescent risk behaviors by the schoolenvironment.
Other ideas? Suggestions?
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 37 / 39
Future Directions
Examine other strategies to reduce sensitivity to practical positivityviolations, especially excluding covariates and moving the weights.
In-depth application of transportability to MTO to understand therelationship between neighborhood poverty and exposure to violenceand violent behaviors.
Grant application to extend the transportability method to mediationmechanisms. Examine mediation of the relationship betweenneighborhood poverty on adolescent risk behaviors by the schoolenvironment.
Other ideas? Suggestions?
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 37 / 39
Future Directions
Examine other strategies to reduce sensitivity to practical positivityviolations, especially excluding covariates and moving the weights.
In-depth application of transportability to MTO to understand therelationship between neighborhood poverty and exposure to violenceand violent behaviors.
Grant application to extend the transportability method to mediationmechanisms. Examine mediation of the relationship betweenneighborhood poverty on adolescent risk behaviors by the schoolenvironment.
Other ideas? Suggestions?
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 37 / 39
How can I do this?
Use the R functions that I wrote
Parametric or semiparametric options
i t t a t e tm l e<�f u n c t i o n ( a , z , y , s i t e ,w, t r unca t e , lbound )
ca te tmle<�f u n c t i o n ( ca , cz , cy , c s i t e , cw , c t r unca t e , c lbound )
n o i n s t r a t e tm l e<�f u n c t i o n ( a , z , y , s i t e ,w, t r unca t e , lbound )
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 38 / 39
Thanks!
www.biostat.jhsph.edu/⇠[email protected]
Robert Wood Johnson Foundation Health & Society Scholars program,UCSF/UCB
Collaborators
Mark van der Laan, UC Berkeley
Jennifer Ahern, UC Berkeley,
Maria Glymour, UCSF
Theresa Osypuk, University of Minnesota
Kara Rudolph (UCB/UCSF) Generalizing e↵ects across sites 39 / 39