The Applied Biostatistics Association (TABA) invites you to a seminar, light supper & conversation:
Topic: How Complete is your Literature Search?
Presenter: Charles Goldsmith
Abstract: How Complete Is Your Literature Search? (or, What is HORIZON Estimation?)
Most published manuscripts contain a literature review section and some even contend they are a summary of the published world literature such as Cochrane Reviews. However, few if any of these documents state how complete their searches are or if they indeed should be considered complete. Charlie has been working to get colleagues to include a Horizon Estimate as part of a paper when it claims literature completeness.
If the search contains at least 2 difference sources for the literature citations, then a very old statistical technique called Capture Mark Recapture (CMR) can be used to estimate the number of missed citations, the completeness of the search strategy, and whether the search order can be made more optimal in how soon the search can be conducted in the future. Examples of the method, with numerical estimates and confidence intervals will be used to show how CMR can be used to create reports that can be used to answer questions and create graphs about completeness and search order that may be helpful with your future papers. Some of these examples are also contained in published articles with Charlie’s collaborators. Longitudinal data has become common in applied research, and methods such as mixed models and Generalized Estimating Equations (GEEs) are commonplace in the applied statistician’s toolbox. But what if the timings at which visits occur vary among patients in a way that is potentially informative about the outcome of interest? For example, when analyzing disease trajectories from family practice data, what if sicker patients visit more often? You then run the risk of over-estimating the burden of disease, unless you handle your data carefully. This talk will highlight settings under which standard methods (mixed models, GEEs) can be expected to work, settings under which they should be used with caution, and alternative approaches to analysis (weighting, outputation, and joint models). These concepts will be illustrated using examples from paediatric rheumatology and oncology.
When: Monday November 6, 2017
6-7 pm seminar (free, but please register if you can)
7 pm light meal & conversation (optional, $15 regular, 5$ students, registration required)
Where: Room 7-605, Princess Margaret Hospital, 610 University Avenue
To attend, please RSVP by or on Thursday November 2nd:
* for seminar only, please email us by clicking here:
mailto:taba.exec@gmail.com?subject=SeminarOnly
* for seminar and dinner, please email us by clicking here:
mailto:taba.exec@gmail.com?subject=SeminarAndDinner
If you plan to attend the dinner, we accept a mailed cheque, Interac email money transfer or cash at the event. If you have to cancel the dinner we request a 48 hour notice otherwise TABA has to pay for it. For Interac email money transfer (not PayPal): do the transfer via your bank to taba.exec@gmail.com and send a separate email via your own email program to us (taba.exec@gmail.com) giving the answer to the security question you used so that we can accept the transfer. For cheques: mail cheque, payable to TABA, to
Lorinda Simms
Eli Lilly Canada Inc.
3650 Danforth Ave
Toronto, ON
M1N 2E8
********************************************************************
We’d love to see your company name here as a sponsor:
please contact Lorinda Simms (taba.exec@gmail.com) or Ruth Croxford (taba.exec@gmail.com).
*********************************************************************