Basic epidemiologic analysis with Stata Part II Biostatistics 212 Lecture 6.

Slides:



Advertisements
Similar presentations
Using Stata’s Margins Command to Estimate and Interpret Adjusted Predictions and Marginal Effects Richard Williams
Advertisements

Do files, log files, and workflow in Stata Biostatistics 212 Lecture 2.
Apr-15H.S.1 Stata: Linear Regression Stata 3, linear regression Hein Stigum Presentation, data and programs at: courses.
© Department of Statistics 2012 STATS 330 Lecture 32: Slide 1 Stats 330: Lecture 32.
M2 Medical Epidemiology
Using Excel Biostatistics 212 Lecture 4. Housekeeping Questions about Lab 3? –replace vs. recode Final Project Dataset! –“Housekeeping” commands vs. data.
Using Excel Biostatistics 212 Lecture 4. Housekeeping Finish Lab 2 today and/or start Lab 3 Mac Addendum Copying and pasting from Stata.
Computing for Research I Spring 2013 Primary Instructor: Elizabeth Garrett-Mayer Regression Using Stata February 19.
Stata and logit recap. Topics Introduction to Stata – Files / directories – Stata syntax – Useful commands / functions Logistic regression analysis with.
Logistic Regression I Outline Introduction to maximum likelihood estimation (MLE) Introduction to Generalized Linear Models The simplest logistic regression.
Basic epidemiologic analysis with Stata Biostatistics 212 Lecture 5.
Generating new variables and manipulating data with STATA Biostatistics 212 Lecture 3.
HSRP 734: Advanced Statistical Methods July 24, 2008.
Advanced Methods and Models in Behavioral Research – 2014 Been there / done that: Stata Logistic regression (……) Conjoint analysis Coming up: Multi-level.
Lecture 17: Regression for Case-control Studies BMTRY 701 Biostatistical Methods II.
Some Terms Y =  o +  1 X Regression of Y on X Regress Y on X X called independent variable or predictor variable or covariate or factor Which factors.
Using Stata’s Margins Command to Estimate and Interpret Adjusted Predictions and Marginal Effects Richard Williams
Generating new variables and manipulating data with STATA Biostatistics 212 Lecture 3.
Introduction to Logistic Regression. Simple linear regression Table 1 Age and systolic blood pressure (SBP) among 33 adult women.
Basic epidemiologic analysis with Stata
Analysis of Complex Survey Data Day 3: Regression.
Basic epidemiologic analysis with Stata Biostatistics 212 Lecture 5.
Multiple Regression 2 Sociology 5811 Lecture 23 Copyright © 2005 by Evan Schofer Do not copy or distribute without permission.
A Longitudinal Study of Maternal Smoking During Pregnancy and Child Height Author 1 Author 2 Author 3.
Multiple Regression III 4/16/12 More on categorical variables Missing data Variable Selection Stepwise Regression Confounding variables Not in book Professor.
Review for Final Exam Some important themes from Chapters 9-11 Final exam covers these chapters, but implicitly tests the entire course, because we use.
Biostat Didactic Seminar Series Analyzing Binary Outcomes: Analyzing Binary Outcomes: An Introduction to Logistic Regression Robert Boudreau, PhD Co-Director.
Stratification and Adjustment
Unit 6: Standardization and Methods to Control Confounding.
Logistic Regression. Outline Review of simple and multiple regressionReview of simple and multiple regression Simple Logistic RegressionSimple Logistic.
Chapter 14 Introduction to Multiple Regression Sections 1, 2, 3, 4, 6.
Simple Linear Regression
Making a figure, dates, and other advanced topics Biostatistics 212 Lecture 6.
Using Excel Biostatistics 212 Lecture 4. Housekeeping Questions about Lab 3? Final Project Dataset! –Check in.
Basic epidemiologic analysis with Stata Biostatistics 212 Lecture 5.
Lecture 12 Model Building BMTRY 701 Biostatistical Methods II.
Making a figure with Stata or Excel Biostatistics 212 Lecture 7.
Using the Margins Command to Estimate and Interpret Adjusted Predictions and Marginal Effects Richard Williams
Making Tables and Figures with Stata Biostatistics 212 Lecture 6.
Organizing a project, making a table Biostatistics 212 Lecture 7.
Organizing a project, making a table Biostatistics 212 Session 5.
Basic epidemiologic analysis with Stata Biostatistics 212 Lecture 5.
Multiple Regression 3 Sociology 5811 Lecture 24 Copyright © 2005 by Evan Schofer Do not copy or distribute without permission.
Introduction to Logistic Regression Rachid Salmi, Jean-Claude Desenclos, Alain Moren, Thomas Grein.
Multiple Regression Lab Chapter Topics Multiple Linear Regression Effects Levels of Measurement Dummy Variables 2.
Organizing a project, making a table Biostatistics 212 Lecture 7.
Using Excel Biostatistics 212 Lecture 4. Housekeeping Questions about Lab 3? –replace vs. recode –Cross-checking/recoding missing values –Analysis of.
April 4 Logistic Regression –Lee Chapter 9 –Cody and Smith 9:F.
Introduction to Statistical Computing in Clinical Research Biostatistics 212.
Analytical epidemiology Disease frequency Study design: cohorts & case control Choice of a reference group Biases Alain Moren, 2006 Impact Causality Effect.
Making Tables and Figures with Stata Biostatistics 212 Lecture 6.
Linear Discriminant Analysis (LDA). Goal To classify observations into 2 or more groups based on k discriminant functions (Dependent variable Y is categorical.
1 Multivariable Modeling. 2 nAdjustment by statistical model for the relationships of predictors to the outcome. nRepresents the frequency or magnitude.
POPLHLTH 304 Regression (modelling) in Epidemiology Simon Thornley (Slides adapted from Assoc. Prof. Roger Marshall)
1 Introduction to Modeling Beyond the Basics (Chapter 7)
Topics Introduction to Stata – Files / directories – Stata syntax – Useful commands / functions Logistic regression analysis with Stata – Estimation –
Introduction to Biostatistics, Harvard Extension School, Fall, 2005 © Scott Evans, Ph.D.1 Contingency Tables.
Stata – be the master Stata. “After I have run my standard commands, what can I do to make my model better (and understand better what is going on)?”
Additional Regression techniques Scott Harris October 2009.
Topics Introduction to Stata – Files / directories – Stata syntax – Useful commands / functions Logistic regression analysis with Stata – Estimation –
business analytics II ▌assignment four - solutions mba for yourself 
Advanced Quantitative Techniques
Discussion: Week 4 Phillip Keung.
Advanced Quantitative Techniques
Introduction to Logistic Regression
BMTRY 747: Introduction Jeffrey E. Korte, PhD
Effective Feedback, Rubrics, and Grading
Soc 3306a Lecture 11: Multivariate 4
Presentation transcript:

Basic epidemiologic analysis with Stata Part II Biostatistics 212 Lecture 6

Housekeeping Questions on Lab 3, Excel Extra credit puzzler Lab 4 – last Lab before Final Project –Due November 8 th – DO file to Scott at Final project –Due December 6th

Today... Adjusting for many things at once Logistic regression Testing for trends Extra time for Lab 4?

Last time Binge drinking appears to be associated with coronary calcium –Association partially due to confounding by gender What about race? Age? SES? Smoking?

Multivariable adjustment manual stratification # 2x2 tables Crude association1 Adjust for gender2 Adjust for gender, race4 Adjust for gender, race, age68 Adjust for “” + income, education816 Adjust for “” + “” + smoking2448

Multivariable adjustment cs command cs command –Does manual stratification for you Lists results from every strata Tests for overall homogeneity Adjusted and crude results –Demo cs cac binge, by(male black age)

Multivariable adjustment cs command cs command –Does manual stratification for you Lists results from every strata Tests for overall homogeneity Adjusted and crude results –Demo cs cac binge, by(male black age) –Can’t interpret interactions!

Multivariable adjustment mhodds command mhodds allows you to look at specific interactions, adjusted for multiple covariates –Does same stratification for you –Adjusted results for each interaction variable –P-value for specific interaction (homogeneity) –Summary adjusted result Demo mhodds cac binge age, by(racegender)

Multivariable adjustment mhodds command mhodds allows you to look at specific interactions, adjusted for multiple covariates –Does same stratification for you –Adjusted results for each interaction variable –P-value for specific interaction (homogeneity) –Summary adjusted result Demo mhodds cac binge age, by(racegender) But strata get so thin!

Multivariable adjustment logistic command Assumes logit model –Await biostats class for details! –Coefficients estimated, no actual stratification –Continuous variables used as they are

Multivariable adjustment logistic command Basic syntax: logistic outcomevar [predictorvar1 predictorvar2 predictorvar3…]

Multivariable adjustment logistic command If using any categorical predictors: xi: logistic outcomevar [i.catvar var2…] Creates “dummy variables” on the fly If you forget, Stata won’t know they are categorical, and you’ll get the wrong answer!

Multivariable adjustment logistic command Demo logistic cac binge logistic cac binge male logistic cac binge male black logistic cac binge male black age xi: logistic cac binge male black age i.smoke

Multivariable adjustment logistic command Pro’s –Provides all OR’s in the model –Accepted approach –Can deal with continuous variables –Better estimation for large models? Con’s –Interaction testing more cumbersome, less automatic –More assumptions –Harder to test for trends

Testing for trend Alcohol consumption can be a lot or a little –Does association increase with larger amounts of consumption? –(no j-shaped curve) Test of trend? –Look through epitab suite

Testing for trends tabodds command chi2 test of trend –tabodds cac alccat –Look at output Adjustment for multiple variables possible –tabodds cac alccat, adjust(age male black)

Approaching your analysis Number of potential models/analyses is daunting –Where do you start? How do you finish? My suggestion –Explore –Plan definitive analysis, make dummy tables/figures –Do analysis (do/log files), fill in tables/figures –Show to collaborators, reiterate prn –Write paper

Summary Epitab commands are a great way to explore your data –Emphasis on interaction Logistic regression is a more general approach, ubiquitous, but testing for interactions and trends is more difficult…

Reminder Bring your dataset (cleaned) in two weeks!