Presentation is loading. Please wait.

Presentation is loading. Please wait.

DATA-DRIVEN STATISTICAL RESEARCH -- By Xianghua Luo

Similar presentations


Presentation on theme: "DATA-DRIVEN STATISTICAL RESEARCH -- By Xianghua Luo"— Presentation transcript:

1 DATA-DRIVEN STATISTICAL RESEARCH -- By Xianghua Luo
Why a statistician consultant/collaborator needs to do method research? Help you do your consulting work better Give yourself a closure on a study you’ve been involved in or on a new method you have just learnt Drive yourself to learn new stuff

2 How to find topics? Research on how previous people analyzed the same type of data. What can be improved? How to convince people to use the new method you proposed? Write for both applied statistical journals and scientific journals. (This is the proof that you care about their scientific problems, you understand their problems, and you know their languages)

3 Do you need to have your own funding to support your research?
Depends. If you need to, you will find it not that difficult to find existing data or an ongoing study that you are involved in. So, an R03/R21 on a secondary analysis of an existing data/project might be a good starting point for you. Being a PhD means you will be a PI one way or another someday. Better to practice early.

4 AN EXAMPLE OF DATA-DRIVEN RESEARCH
Analysis of Cigarette Purchase Task Instrument Data with a Left-Censored Mixed Effects Model Liao W, Luo X, Le C, Chu H, Epstein LH, Yu J, Ahluwalis JS, Thomas J. (2013). Analysis of cigarette purchase task instrument data with a left-censored mixed effects model. Experimental and Clinical Psychopharmacology, 21(2):124–-132.

5 Cigarette Purchase Task Survey
Imagine a TYPICAL DAY during which you smoke. The following questions ask how many cigarettes you would consume if they cost various amounts of money. Assume the following: • Available cigarettes are your favorite brand • You have the same income/savings that you have now • You have NO ACCESS to any cigarettes or nicotine products other than those offered at these prices • You consume the cigarettes you request on that day (in other words, no stockpiling) Participants were then asked to respond to the following set of questions: How many cigarettes would you smoke if they were_____ each?: 0¢ (free), 1¢, 5¢, 13¢, 25¢, 50¢, $1, $2, $3, $4, $5, $6, $11, $35, $70, $140, $280, $560, $1,120.

6 Figure. A typical cigarette demand curve for a smoker, derived from cigarette purchase task survey data (log-log coordinate used)

7 Existing statistical methods:
Individual-specific ordinary least square model. Mixed effects model. How the extra zeros/missing values are handled in existing methods? Ignore all zeros or missing values; Impute the first zero with an arbitrary small number ω, e.g. 0.1, but ignoring further zeros; Impute all zeros/missing values with ω.

8 Any problems in the existing methods?
Could the zeros be small values not observable because they are lower than a certain threshold (LOD)? Left-censored mixed effects model What if the zeros are real zero consumptions (i.e., cessation of smoking)? A joint modeling approach with a logistic regression component for the cessation status and a non-linear mixed effects model for the non-zero consumption data. Zhao T, Luo X, Chu H, Le CT, Epstein LH, Thomas JL. (2016). A two-part mixed effects model for cigarette purchase task data with application to a college students smoking study (accepted).

9 What else you can do to improve your consulting skills?
Go to scientific seminars, e.g. Cancer Center Seminar Series Serve as a referee for medical journals Serve as a statistician reviewer in protocol/grant proposal review committees


Download ppt "DATA-DRIVEN STATISTICAL RESEARCH -- By Xianghua Luo"

Similar presentations


Ads by Google