Confounding and Interaction III 2006

Information about Confounding and Interaction III 2006

Published on January 24, 2008

Author: Prudenza

Source: authorstream.com

Content

Winter Electives:  Winter Electives Molecular and Genetic Epidemiology Decision and Cost-effectiveness Analysis Grantwriting for Career Development Awards (Workshop – not for credit hours) Medical Informatics Slide2:  Next Tuesday (12/5/06) 8:15 to 9:45: Journal Club 10:00 to 1:00 pm: Mitch Katz Note chapters in his text book Lunch provided 1:30 to 2:45: Last Small Group Section Web-based course evaluation Bring laptop Distribute Final Exam Exam due 12/12 (in hands of Olivia by 4 pm) by email or China Basin 5700 Confounding and Interaction: Part III:  Confounding and Interaction: Part III When Evaluating Association Between an Exposure and an Outcome, the Possible Roles of a 3rd Variable are: Intermediary Variable Effect Modifier Confounder No Effect Forming “Adjusted” Summary Estimates to Evaluate Presence of Confounding Concept of weighted average Woolf’s Method Mantel-Haenszel Method Clinical/biological decision rather than statistical Handling more than one potential confounder Limitations of Stratification to Adjust for Confounding the motivation for multivariable regression When Assessing the Association Between an Exposure and a Disease, What are the Possible Effects of a Third Variable?:  When Assessing the Association Between an Exposure and a Disease, What are the Possible Effects of a Third Variable? EM + _ Confounding: ANOTHER PATHWAY TO GET TO THE DISEASE Effect Modifier (Interaction): MODIFIES THE EFFECT OF THE EXPOSURE D I C Intermediary Variable: No Effect ON CAUSAL PATHWAY Assumption: The third variable a priori is felt to be relevant What are the Possible Roles of a 3rd Variable?:  What are the Possible Roles of a 3rd Variable? Intermediary Variable Effect Modifier (interaction) Confounder No Effect Effect Modifier? (numerically assess both magnitude and statistical differences) yes no Confounder? (numerically assess difference between adjusted and crude; not a statistical decision) yes no Report stratum-specific estimates Report “adjusted” summary estimate Report Crude Estimate (3rd variable has no effect) Intermediary Variable? (conceptual decision) Report Crude Estimate no yes Effect of a Third Variable: Statistical Interaction:  Effect of a Third Variable: Statistical Interaction Stratified Crude No Caffeine Use Heavy Caffeine Use RR crude = 1.7 RRno caffeine use = 2.4 RRcaffeine use = 0.7 . cs delayed smoking, by(caffeine) caffeine | RR [95% Conf. Interval] M-H Weight -----------------+------------------------------------------------- no caffeine | 2.414614 1.42165 4.10112 5.486943 heavy caffeine | .70163 .3493615 1.409099 8.156069 -----------------+------------------------------------------------- Crude | 1.699096 1.114485 2.590369 M-H combined | 1.390557 .9246598 2.091201 -----------------+------------------------------------------------- Test of homogeneity (M-H) chi2(1) = 7.866 Pr>chi2 = 0.0050 Report interaction; confounding is not relevant Statistical Tests of Interaction: Test of Homogeneity (heterogeneity):  Statistical Tests of Interaction: Test of Homogeneity (heterogeneity) Null hypothesis: The individual stratum-specific estimates of the measure of association differ only by random variation i.e., the strength of association is homogeneous across all strata i.e., there is no interaction The test statistic will have a chi-square distribution with degrees of freedom of one less than the number of strata Report vs Ignore Interaction? Some Guidelines:  Report vs Ignore Interaction? Some Guidelines Is an art form: requires consideration of both clinical and statistical significance If Interaction is not Present, What Next?:  If Interaction is not Present, What Next? Case-control study of post-exposure AZT use in preventing HIV seroconversion after needlestick (NEJM 1997) Crude ORcrude = 0.61 (95% CI: 0.26 - 1.4) Post-exposure prophylaxis with AZT after a needlestick:  Post-exposure prophylaxis with AZT after a needlestick HIV AZT Use Severity of Exposure Confounding by Indication Evaluating for Interaction :  Evaluating for Interaction Potential confounder: severity of exposure Minor Severity Major Severity Crude Stratified ORcrude =0.61 OR = 0.0 OR = 0.35 Slide12:  Is there interaction? Is there confounding? What is the adjusted measure of association? Assuming Interaction is not Present, Form a Summary of the Unconfounded Stratum-Specific Estimates:  Assuming Interaction is not Present, Form a Summary of the Unconfounded Stratum-Specific Estimates Construct a weighted average Assign weights to the individual strata Summary Estimate = Weighted Average of the stratum-specific estimates a simple mean is a weighted average where the weights are equal to 1 which weights to use depends on type of effect estimate desired (OR, RR, RD) and characteristics of the data e.g., Woolf’s method Mantel-Haenszel method Forming a Summary Estimate for Stratified Data :  Forming a Summary Estimate for Stratified Data Minor Severity Major Severity Crude Stratified ORcrude = 0.61 OR = 0.0 OR = 0.35 How would you weight these strata? According to sample size? No. of cases? Summary Estimators: Woolf’s Method:  Summary Estimators: Woolf’s Method aka Directly pooled or precision estimator Woolf’s estimate for adjusted odds ratio where wi wi is the inverse of the variance of the stratum-specific log(odds ratio) Calculating a Summary Effect Using the Woolf Estimator:  Calculating a Summary Effect Using the Woolf Estimator e.g. AZT use, severity of needlestick, and HIV Minor Severity Major Severity Crude Stratified ORcrude =0.61 OR = 0.0 OR = 0.35 Summary Estimators: Woolf’s Method:  Summary Estimators: Woolf’s Method Conceptually straightforward Best when: number of strata is small sample size within each strata is large Cannot be calculated when any cell in any stratum is zero because log(0) is undefined 1/2 cell corrections have been suggested but are subject to bias Formulae for Woolf’s summary estimates for other measures (e.g., RR, RD) available in texts and software documentation sensitive to small strata, cells with “0” computationally messy Summary Estimators: Mantel-Haenszel:  Summary Estimators: Mantel-Haenszel Mantel-Haenszel estimate for odds ratios ORMH = wi = wi is inverse of the variance of the stratum-specific odds ratio under the null hypothesis (OR =1) Summary Estimators: Mantel-Haenszel:  Summary Estimators: Mantel-Haenszel Mantel-Haenszel estimate for odds ratios “relatively” resistant to the effects of large numbers of strata with few observations resistant to cells with a value of “0” computationally easy most commonly used Calculating a Summary Effect Using the Mantel-Haenszel Estimator:  Calculating a Summary Effect Using the Mantel-Haenszel Estimator ORMH = ORMH = Minor Severity Major Severity Crude Stratified ORcrude =0.61 OR = 0.0 OR = 0.35 Calculating a Summary Effect in Stata :  Calculating a Summary Effect in Stata epitab command - Tables for epidemiologists see “Survival Analysis and Epidemiological Tables Reference Manual” To produce crude estimates and 2 x 2 tables: For cross-sectional or cohort studies: cs variablecase variable exposed For case-control studies: cc variablecase variableexposed To stratify by a third variable: cs varcase varexposed, by(varthird variable) cc varcase varexposed, by(varthird variable) Default summary estimator is Mantel-Haenszel , pool will also produce Woolf’s method Calculating a Summary Effect Using the Mantel-Haenszel Estimator:  Calculating a Summary Effect Using the Mantel-Haenszel Estimator e.g. AZT use, severity of needlestick, and HIV . cc HIV AZTuse,by(severity) pool severity | OR [95% Conf. Interval] M-H Weight -----------------+------------------------------------------------- minor | 0 0 2.302373 1.070588 major | .35 .1344565 .9144599 6.956522 -----------------+------------------------------------------------- Crude | .6074729 .2638181 1.401432 Pooled (direct) | . . . M-H combined | .30332 .1158571 .7941072 -----------------+------------------------------------------------- Test of homogeneity (B-D) chi2(1) = 0.60 Pr>chi2 = 0.4400 Test that combined OR = 1: Mantel-Haenszel chi2(1) = 6.06 Pr>chi2 = 0.0138 Minor Severity Major Severity Crude Stratified ORcrude =0.61 OR = 0.0 OR = 0.35 Calculating a Summary Effect Using the Mantel-Haenszel Estimator:  Calculating a Summary Effect Using the Mantel-Haenszel Estimator In addition to the odds ratio, Mantel-Haenszel estimators are also available in Stata for: risk ratio “cs varcase varexposed, by(varthird variable)” rate ratio “ir varcase varexposed vartime, by(varthird variable)” Assessment of Confounding: Interpretation of Summary Estimate:  Assessment of Confounding: Interpretation of Summary Estimate Compare “adjusted” estimate to crude estimate e.g. compare ORMH (= 0.30) to ORcrude (= 0.61) If “adjusted” measure “differs meaningfully” from crude estimate, then confounding is present e.g., does ORMH = 0.30 “differ meaningfully” from ORcrude = 0.61? What does “differs meaningfully” mean? a matter of judgement based on biologic/clinical sense rather than on a statistical test no one correct answer the objective is to remove bias 10% change from the crude often used your threshold needs to be stated a priori and included in your methods section Statistical Testing for Confounding is Inappropriate:  Statistical Testing for Confounding is Inappropriate Testing for statistically significant differences between crude and adjusted measures is inappropriate e.g., when examining an association for which a factor is a known confounder (say age in the association between HTN and CAD) if the study has a small sample size, even large differences between crude and adjusted measures may not be statistically different yet, we know confounding is present therefore, the difference between crude and adjusted measures cannot be ignored as merely chance. bias must be prevented: the difference must be reported as confounding the issue of confounding is one of internal validity, not of sampling error. we must live with – within reason -- whatever effects we see after adjustment for a factor for which there is an a priori belief about confounding we’re not concerned that sampling error is causing confounding and therefore we don’t have to worry about testing for role of chance Confidence Interval Estimation and Hypothesis Testing for the Mantel-Haenszel Estimator:  Confidence Interval Estimation and Hypothesis Testing for the Mantel-Haenszel Estimator e.g. AZT use, severity of needlestick, and HIV . cc HIV AZTuse,by(severity) pool severity | OR [95% Conf. Interval] M-H Weight -----------------+------------------------------------------------- minor | 0 0 2.302373 1.070588 major | .35 .1344565 .9144599 6.956522 -----------------+------------------------------------------------- Crude | .6074729 .2638181 1.401432 Pooled (direct) | . . . M-H combined | .30332 .1158571 .7941072 -----------------+------------------------------------------------- Test of homogeneity (B-D) chi2(1) = 0.60 Pr>chi2 = 0.4400 Test that combined OR = 1: Mantel-Haenszel chi2(1) = 6.06 Pr>chi2 = 0.0138 What does the p value = 0.0138 mean? Mantel-Haenszel Confidence Interval and Hypothesis Testing:  Mantel-Haenszel Confidence Interval and Hypothesis Testing Mantel-Haenszel Techniques:  Mantel-Haenszel Techniques Mantel-Haenszel estimators Mantel-Haenszel chi-square statistic Mantel’s test for trend (dose-response) Summary Effect in Stata – another example:  Summary Effect in Stata – another example e.g. Spermicide use, maternal age and Down’s Age < 35 Age > 35 Crude Stratified OR = 3.4 OR = 5.7 OR = 3.5 Is there confounding present? Which answer should you report as “final”? No Effect of Third Variable:  No Effect of Third Variable Stratified Crude Matches Absent Matches Present OR crude = 21.0 (95% CI: 16.4 - 26.9) ORmatches = 21.0 OR no matches = 21.0 OR adj = 21.0 (95% CI: 14.2 - 31.1) Whether or not to accept the “adjusted” summary estimate in favor of the crude?:  Whether or not to accept the “adjusted” summary estimate in favor of the crude? Methodologic literature is inconsistent on this Bias-variance tradeoff Scientifically most rigorous approach would appear to be to create two lists of potential confounders prior to the analysis: A List: Those factors for which you will accept the adjusted result no matter how small the difference from the crude. Factors you know must be confounders B List: Those factors for which you will accept the adjusted result only if it meaningfully differs from the crude (with some pre-specified difference, e.g., 10%) Factors you are less sure about For some analyses, may have no factors on A list. For other analyses, no factors on B list. Always putting all factors on A list may seem conservative, but not necessarily the right thing to do in that there may be a penalty in statistical imprecision Presence or Absence of Confounding by a Third Variable?:  Presence or Absence of Confounding by a Third Variable? Stratifying by Multiple Potential Confounders:  Stratifying by Multiple Potential Confounders Crude Stratified <40 smokers >60 non-smokers 40-60 non-smokers <40 non-smokers 40-60 smokers >60 smokers The Need for Evaluation of Joint Confounding :  The Need for Evaluation of Joint Confounding Variables that evaluated alone show no confounding may show confounding when evaluated jointly Crude Stratified by Factor 1 alone by Factor 2 alone by Factor 1 & 2 Approaches for When More than One Potential Confounder is Present:  Approaches for When More than One Potential Confounder is Present Backward versus forward confounder evaluation strategies relevant both for stratification and especially multivariable modeling (“model selection”) Backwards Strategy initially evaluate all potential confounders together (i.e., look for joint confounding) conceptually preferred because in nature variables are all present and act together Procedure: with all potential confounders considered, form adjusted estimate. This is the “gold standard” one variable can then be dropped and the adjusted estimate is re-calculated (adjusted for remaining variables) if the dropping of the first variable results in a non-meaningful (eg <10%) change compared to the gold standard, it can be eliminated procedure continues until no more variables can be dropped (i.e. are remaining variables are relevant) Problem: with many potential confounders, cells become very sparse and some strata provide no information Example: Backwards Selection:  Example: Backwards Selection Research question: Is prior hospitalization associated with the presence of methicillin-resistant S. aureus (MRSA)? (from Kleinbaum 2003) Outcome variable: MRSA (present or absent) Primary predictor: prior hospitalization (yes/no) Potential confounders: age (<55, >55), gender, prior antibiotic use (atbxuse; yes/no) Assume no interaction Which OR to report? Approaches for When More than One Potential Confounder is Present:  Approaches for When More than One Potential Confounder is Present Forward Strategy start with the variable that has the biggest “change-in-estimate” impact then add the variable with the second biggest impact keep this variable if its presence meaningfully changes the adjusted estimate procedure continues until no other added variable has an important impact Advantage: avoids the initial sparse cell problem of backwards approach Problem: does not evaluate joint confounding effects of many variables An Analysis Plan:  An Analysis Plan Written before the data are analyzed Content Detailed description of the techniques to be used to both explore and formally analyze data Forms the basis of “Statistical Analysis” section in manuscripts Parameters/rules/logic to guide key decisions: which variables will be assessed for confounding and interaction? what p value will be used to guide reporting of interaction? what is a meaningful difference between two estimates (e.g. 10%)? Required for clinical trial registration Can observational work be far behind? Utility: A plan helps to keep the analysis: Focused Reproducible Honest (avoids p value shopping) Stratification to Manage Confounding:  Stratification to Manage Confounding Advantages straightforward to implement and comprehend easy way to evaluate interaction Limitations Looks at only one exposure-disease assoc. at a time Requires continuous variables to be discretized loses information; possibly results in “residual confounding” Deteriorates with multiple confounders e.g. suppose 4 confounders with 3 levels 3x3x3x3=81 strata needed unless huge sample, many cells have “0”’s and strata have undefined effect measures Solution: Mathematical modeling (multivariable regression) e.g. linear regression logistic regression proportional hazards regression

Related presentations


Other presentations created by Prudenza

chapter8 2005
16. 01. 2008
0 views

chapter8 2005

wk10 Satellite Microwave
24. 03. 2008
0 views

wk10 Satellite Microwave

ReidPresentation
22. 01. 2008
0 views

ReidPresentation

Job Hazard Analysis
08. 01. 2008
0 views

Job Hazard Analysis

physics121 lecture02
09. 01. 2008
0 views

physics121 lecture02

Research powerpoint for proverbs
10. 01. 2008
0 views

Research powerpoint for proverbs

FlightInstruments
13. 01. 2008
0 views

FlightInstruments

eacl2003ws ryu i
14. 01. 2008
0 views

eacl2003ws ryu i

coup de chaleur SFAR
15. 01. 2008
0 views

coup de chaleur SFAR

ab regions
15. 01. 2008
0 views

ab regions

l5
17. 01. 2008
0 views

l5

icebreaking games
17. 01. 2008
0 views

icebreaking games

ringsandmoons
17. 01. 2008
0 views

ringsandmoons

d000381
20. 01. 2008
0 views

d000381

vis2006present v4
21. 01. 2008
0 views

vis2006present v4

Media Planning for ISC
23. 01. 2008
0 views

Media Planning for ISC

spatical data mining 20040909
24. 01. 2008
0 views

spatical data mining 20040909

Victorian Wedding Food
05. 02. 2008
0 views

Victorian Wedding Food

icebear w300
05. 02. 2008
0 views

icebear w300

068229 Ch06 slides
06. 02. 2008
0 views

068229 Ch06 slides

Presentation1 weather
12. 02. 2008
0 views

Presentation1 weather

insurv
08. 01. 2008
0 views

insurv

Structural Change L 10
28. 01. 2008
0 views

Structural Change L 10

Cellphones on campus
31. 01. 2008
0 views

Cellphones on campus

lesson3
07. 02. 2008
0 views

lesson3

bits rit
07. 02. 2008
0 views

bits rit

taxonomy
14. 02. 2008
0 views

taxonomy

2003WIPP
09. 01. 2008
0 views

2003WIPP

LBO 2007 brief
24. 01. 2008
0 views

LBO 2007 brief

03 java program
09. 01. 2008
0 views

03 java program

CitingSources
28. 01. 2008
0 views

CitingSources

acts
25. 02. 2008
0 views

acts

wp3
28. 02. 2008
0 views

wp3

enterobac05
21. 02. 2008
0 views

enterobac05

Iraq
03. 03. 2008
0 views

Iraq

2006 Budget presentation to NCAI
05. 03. 2008
0 views

2006 Budget presentation to NCAI

Federalism
14. 03. 2008
0 views

Federalism

Balloon Spacecraft
16. 01. 2008
0 views

Balloon Spacecraft

BECAS PRESENTACION
03. 04. 2008
0 views

BECAS PRESENTACION

Mervyn
15. 02. 2008
0 views

Mervyn

HACS
08. 04. 2008
0 views

HACS

SolitaryPulmonaryNod ule
06. 02. 2008
0 views

SolitaryPulmonaryNod ule

Hawaii Presentation 2008
08. 03. 2008
0 views

Hawaii Presentation 2008

200507am
29. 01. 2008
0 views

200507am

Major constellations
12. 02. 2008
0 views

Major constellations

GW05 XACMLandGlobus Demo
11. 01. 2008
0 views

GW05 XACMLandGlobus Demo

NASAProgram
22. 01. 2008
0 views

NASAProgram

OleMiss
12. 01. 2008
0 views

OleMiss

African American Song
16. 01. 2008
0 views

African American Song

plummer
20. 02. 2008
0 views

plummer

117
22. 01. 2008
0 views

117

CSDKhanGujurattalk
23. 01. 2008
0 views

CSDKhanGujurattalk

Campus Security Authorities
29. 02. 2008
0 views

Campus Security Authorities