# Projects

#### Cardiovascular Surgery Outcomes

Leveraging clinical registry data for research into outcomes following cardiovascular surgery.

#### JoineR-M: Joint Modelling of Repeated Measurements and Time-to-Event Data

The development of methodology and software for fitting joint models to multivariate longitudinal and time-to-event data.

#### Medical Statistics Education

Medical statistics teaching for clinicians.

#### Statistical Ecotoxicological Modelling

Ecotoxicological risk assessment for chemicals using species sensitivity distributions.

#### joineR: Joint Modelling of Repeated Measurements and Time-to-Event Data

An R package to fit joint models to a single repeated measure and a time-to-event outcome (single or competing risks) using an EM algorithm.

#### joineRML: Joint Modelling of Multivariate Longitudinal Data and Time-to-Event Outcomes

An R package to fit joint models to multivariate repeated measures data and a time-to-event outcome using an MCEM algorithm.

# Selected Publications

ICVTS

ICVTS

Int J Biostat

J R Stat Soc A

JAMA Intern Med

### Joint modelling of time-to-event and multivariate longitudinal outcomes: recent developments and issues

BMC Med Res Methodol

### External model validation of binary clinical risk prediction models in cardiovascular and thoracic surgery

J Thorac Cardiovasc Surg

J R Soc Med

Heart

Env Toxicol Chem

# Recent Publications

• Finding the forest through the trees in statistics: let the Statistical Primers in EJCTS/ICVTS guide you

• Finding the forest through the trees in statistics: let the Statistical Primers in EJCTS/ICVTS guide you

• Statistical primer: performing repeated-measures analysis

• Statistical primer: performing repeated-measures analysis

• Joint models of longitudinal and time-to-event data with more than one event time outcome: a review

• A comparison of joint models for longitudinal and competing risks data, with application to an epilepsy drug randomized controlled trial

• Acute aortic dissection - A UK national perspective of volume- outcomes relationship utilizing National Institute for Cardiovascular Outcomes Research (NICOR) data

• Quantitative proteomics of cerebrospinal fluid in paediatric pneumococcal meningitis

• Estimated reductions in cardiovascular and gastric cancer disease burden through salt policies: an IMPACT NCD microsimulation study

• National registry data and record linkage to inform postmarket surveillance of prosthetic aortic valve models over 15 years

# Recent Posts

I have submitted updates to both joineR (now version 1.2.1) and joineRML (now version 0.3.0) to CRAN this week. In addition, we now have fantastic looking hex sticker badges from the remarkable hexSticker package. As always, we value user feedback on these packages and will continue to update them.

### Competing risks in joineR

Description As of version 1.2.0, joineR fits the joint model proposed by Williamson et al. (2008) for joint models of longitudinal data and competing risks. Here, the longitudinal data submodel remains as per that analyzed in Henderson et al. (2000), namely $Y_i(t) = X_i(t)^\top \beta + Z_i(t)^\top U_i + \epsilon_i(t),$ where $Y_i(t)$ is a repeated measurement on subject $i$ at time $t$, $U_i$ is a latent vector that follows a zero-mean multivariate normal distribution, $X_i(t)$ and $Z_i(t)$ are vectors of explanatory variables that may be time-constant or time-varying, and the $\epsilon_i(t)$ are mutually independent errors, $\epsilon_i(t) \sim N(0, \tau^2)$.

### Using joineRML v0.1.1

The joineRML package implements methods for analyzing data from multiple longitudinal studies in which the responses from each subject consists of time-sequences of repeated measurements and a possibly censored time-to-event outcome. The modelling framework for the repeated measurements is the multivariate linear mixed effects model. The model for the time-to-event outcome is a Cox proportional hazards model with log-Gaussian frailty. Stochastic dependence is captured by allowing the Gaussian random effects of the linear model to be correlated with the frailty term of the Cox proportional hazards model.

# Teaching

I am a teaching instructor for the following courses/workshops:

I have previously been a tutor for the following courses at Liverpool University and Durham University:

• SAM 2017 Conference Workshop on Joint Modelling using R
• Statistics (for Veterinary Science undergraduates)
• Introductory Statistics to Scientists (for faculty staff and students) [material available here]
• Spatial and Temporal Statistical Modelling for Population Health Sciences (short course) [material available here]
• Statistics I (for Mathematics undergraduates)
• Statistics II computer laboratory classes (for Mathematics undergraduates)
• Integration and Probability I (for Mathematics undergraduates)