Quantitative Sciences Unit
Research Methods Seminars
Directions
To get to 1070 Arastradero:Driving: enter the driveway and take the first left into the parking lot and park. Enter through the front door - you will be in the lobby. Take the door on the right and follow it toward the back of the building. Room 109 will be on your left before you reach the glass door leading outside.
Shuttle: 1070 Arastradero is served by the Marguerite Shuttle, which picks up at the medical center on Pasteur Drive.
The Quantitative Sciences Unit (QSU) is hosting a forum to discuss research methods in medicine held on the first Tuesday of every month.
The Research Methods Seminar is an interactive and informal journal club-type format where topical papers in medical research, particularly relevant to faculty in the Department of Medicine, are discussed with an emphasis on the methods and/or study design.
QSU Research Methods Seminar
Location: 1070 Arastradero Road # 109
Time: 4-5pm first Tuesday of the month (unless otherwise noted)
Refreshments served
Free parking
| Upcoming Seminars |
Tuesday, May 7, 2013 Multiple Imputation in Practice -- Approaches for handling categorical and interaction variables Missing data is a pervasive problem in medical and epidemiological research. Multiple imputation (MI), a simulation-based method, is one reasonable approach for handling missing data. Recently, mainstream statistical packages such as SAS, STATA and R have incorporated MI procedures allowing easy access to its use. While in theory MI yields valid results when data are missing at random (MAR), in practice the story is more nuanced. Much of the burden remains on the user for appropriate application in order for validity to hold. For example, MI is not completely straightforward in the presence of categorical variables, derived variables or interaction terms. Further, different software packages not only rely on different methods for imputation but also make different options available for handling these subtleties. Such variations impact results. We discuss common issues that arise in multiple imputation and present practical guidelines based on previous research and available software on how best to employ MI in these scenarios. Optional Reading:
|
We welcome your suggestions for the seminar series and are happy to answer any questions you may have - please contact Linda Enomoto or Jessica Kubo.
We look forward to seeing you at our next seminar!
| Past Seminars | April 2013 Kristin Sainani Writing about Biostatistics |
| March 2013 Iryna V. Lobach Analysis of Gene-Environment Interactions with Measurement Errors in Environmental Exposures |
| February 2013 Ying Lu Statistical Designs for Phase I Cancer Clinical Trials |
| December 2012 Sergio Bacallado An Introduction to Bayesian Analysis Using Case Studies in Medical Research |
| November 2012 Kristin Sainani Introduction to Propensity Scores |
| October 2012 John Ioannidis Genetic Prediction Models: Practice, Metrics and a Discovery Extension |
| May 2012 Ben Goldstein Predicting Acute Sudden Cardiac Death using Electronic Health Records |
| April 2012 Sepideh Modrek An Application of Instrumental Variables: Maternal Education as a Driver for Eliminating Female Circumcision |
| March 2012 Hui Wang Applications of Targeted MLE Based Variable Importance Measurement in Dimension Reduction with Gene Expression Data |
| February 2012 Mike Baiocchi Estimating the Effectiveness of Intensity of Care on Rates of Death for Premature Infants |
| January 2012 Raúl Aguilar Things You Can Do When You Have Missing Covariates |
| December 2011 David Shilane Comparative Effectiveness Research in Cardiology with Messy Data |
| November 2011 Ben Goldstein Prediction in Medical Studies: What, Why & How |
| October 2011 Jane Paik Using Regression Models to Analyze Randomized Trials: Robustness of Survival Models to Misspecification |
| September 2011 David Rehkopf Applying Machine Learning Algorithm to Answer Questions from Observational Data: Essential Complement or Dangerous Tool? |
| June 2011 Susan Gruber Targeted Maximum Likelihood Estimation for Causal Inference |
| May 2011 Gunnar Carlsson Topological Data Analysis for Biology |
| April 2011 Maria E Montez-Rath Methods for Handling Survey Data |
| March 2011 Mark Cullen, Manisha Desai, Jessica Kubo Modeling the Hazard of Injury as a Function of Experience Among Hourly Aluminum Manufacturing Workers |
| February 2011 Jose Montoya Could a Recently Found Virus, XMRV, Cause Chronic Fatigue Syndrome? |
| January 2011 Manisha Desai An Introduction to Missing Data and Imputation Methods |
| December 2010 Wolfgang Winkelmayer Propensity Scores |
| November 2010 Jay Bhattacharya Does Swan-Ganz Catheterization Increase Mortality in the ICU? An Instrumental Variables Bounding Approach |
| October 2010 Tim Assimes Epidemiological Issues in Contemporary Human Genetic Studies |
| September 2010 Doug Owens Where Angels Dare not Tread: Development of a Guideline for Screening Mammography in 40 to 49 year Old Women |
Additional Information:
Welcome to Quantatitive Sciences
Quantative Sciences Overview