 |
Department of Public Health
Sciences
|
Home
of the
South LondonIStroke Register SLSR |
 |
||||||
|
|
|||||
| Summary of research activities | ||||||
| My primary research area is the development, implementation, and application of models to address two main problems in stroke research: estimating incidence (capture-recapture models) and modelling outcome (longitudinal and multilevel models, methods for missing data). | ||||||
| Estimating incidence | ||||||
| Incidence
is usually estimated using a register - but the estimation relies
on the unrealistic assumption that the register is 100% complete.
Instead, capture-recapture methods can be used to estimate completeness
of the register and thus total number of strokes. I have developed
capture-recapture methods including covariates, so allowing patients
with some characteristics to be at decreased chance of capture. For
example, patients with mild strokes, who are not admitted to hospital,
may be more likely to be missed by a stroke register. These methods allow more accurate estimation of incidence (using an incomplete register), and also provide information on which cases are most likely to be missed. |
||||||
| Modelling outcome | ||||||
|
I have used
multilevel models to quantify the pattern of stroke recovery over
time, allowing for similarities between measurements on the same
individual at different time-points. The correlation estimates from
this model can be used to predict future recovery for a patient,
based on their recovery to date. We are currently examining the
clinical utility of such predictions. One frequent problem when analysing data on outcome after stroke is the occurrence of missing data. I have investigated methods for dealing with this, including multiple imputation and bootstrap methods. |
||||||
| Key Publications | ||||||
| 2001 | ||||||
| Tilling K. Capture-recapture methods - useful or misleading? IJE 2001;30(1):12-14 | ||||||
| Tilling K, Sterne JAC, Wolfe CDA. Multilevel growth curve models with covariate effects: application to recovery after stroke. Stat Med 2001;20(5):685-704. | ||||||
| Tilling K, Sterne JAC, Wolfe CDA. Estimation of the incidence of stroke using a capture-recapture model including covariates. IJE (in press). | ||||||
| Tilling K, Sterne JAC, Rudd AG, Glass TA, Wityk RJ, Wolfe CDA. A New Method for Predicting Recovery after Stroke. Stroke (in press). | ||||||
| 1999 | ||||||
| Tilling K and Sterne JAC. Capture-recapture models including covariate effects. AJE 1999;149(4):392-400. | ||||||
| Wolfe CDA, Tilling K, Beech R, Rudd AG. Variations in case-fatality and dependency from stroke in west and central Europe. Stroke 1999;30(2):350-356. | ||||||
| Hickman M et al. Estimating the prevalence of problem drug use in inner-London: a discussion of three capture-recapture studies. Addiction 1999;94(11):1653-1662 | ||||||
|
||||||
