A5051711350- Statistical Methods and Inference
- Advanced Causal Inference Techniques
- Statistical Methods and Bayesian Inference
- Pituitary Gland Disorders and Treatments
- Meningioma and schwannoma management
- Bayesian Modeling and Causal Inference
- Spine and Intervertebral Disc Pathology
- Statistical Methods in Clinical Trials
- Glioma Diagnosis and Treatment
- Cerebrospinal fluid and hydrocephalus
- Head and Neck Surgical Oncology
- Random Matrices and Applications
- Health Systems, Economic Evaluations, Quality of Life
- Growth Hormone and Insulin-like Growth Factors
- Qualitative Comparative Analysis Research
- Traumatic Brain Injury and Neurovascular Disturbances
- Monetary Policy and Economic Impact
- Advanced Statistical Process Monitoring
- Management of metastatic bone disease
- Cervical and Thoracic Myelopathy
- Teratomas and Epidermoid Cysts
- Tumors and Oncological Cases
- HIV-related health complications and treatments
- Cleft Lip and Palate Research
- Adrenal and Paraganglionic Tumors
Leeds General Infirmary
2017-2025
Leeds Teaching Hospitals NHS Trust
2021-2022
Institute of Natural Science
2020
Harvard University Press
2018
Institute for Fiscal Studies
2018
Stanford University
2017
Harvard University
1987-2017
Massachusetts Institute of Technology
2017
Sheffield Teaching Hospitals NHS Foundation Trust
2014
Society for Endocrinology
2014
Summary. AIDS Clinical Trial Group (ACTG) randomized trial 021 compared the effect of bactrim versus aerosolized pentamidine (AP) as prophylaxis therapy for pneumocystis pneumonia (POP) in patients. Although patients to arm experienced a significant delay time POP, survival experience two arms was not significantly different ( p = .32). In this paper, we present evidence that improves but standard intent‐to‐treat comparison failed detect advantage because large fraction subjects either...
Rothman (Epidemiology 1990;1:43-46) recommends against adjustments for multiple comparisons. Implicit in his recommendation, however, is an assumption that the sole objective of data analysis to report and scientifically interpret data. We concur with recommendation when this correct one willing abandon frequentist interpretations summary statistics. Nevertheless, there are situations which additional or even primary goal reach a set decisions based on In such situations, Bayes...
OBJECTIVE The aim of this study was to provide a comprehensive benchmark 30-day ventriculoperitoneal (VP) shunt failure rates for single institution over 5-year period both adult and pediatric patients, compare with the results in previously published literature, establish factors associated failure. METHODS A retrospective database search undertaken identify all VP operations performed single, regional neurosurgical unit during period. Data were collected regarding patient age, sex, origin...
Abstract Consider an unbiased follow‐up study designed to investigate the causal effect of a dichotomous exposure on disease outcome. Under deterministic outcome model, standard ‘95 per cent binomial confidence interval’ may fail cover parameter interest at nominal rate when we take be associated with observed population (regardless whether was sampled from larger superpopulation). I propose new interval estimators that, in this setting, improve upon performance ‘binomial interval.’
Robins et al. (2008Robins ( , 2016b) ) applied the theory of higher order influence functions (HOIFs) to derive an estimator mean outcome Y in a missing data model with at random conditional on vector X continuous covariates; their estimator, contrast previous estimators, is semiparametric efficient under minimal conditions.However (2008, depends non-parametric estimate density X.In this paper, we introduce new HOIF that has same asymptotic properties as but does not require nonparametric...
We consider inference about a scalar parameter under non-parametric model based on one-step estimator computed as plug in plus the empirical mean of an parameter's influence function. focus class parameters that have function which depends two infinite dimensional nuisance functions and such bias interest is expectation product estimation errors functions. Our includes many important treatment effect contrasts causal econometrics, ATE, ATT, integrated contrast with continuous treatment,...
Nasal dermoid sinus cysts are the most common congenital midline nasal lesions. We describe a novel technique for excision of cyst in 2‐year‐old boy using four hand endoscopic approach via small scalp incision behind hairline. The technique, although somewhat challenging, avoids facial scar. Laryngoscope, 123:1862–1864, 2013
Judea Pearl's insight that, when errors are assumed independent, the Pure (aka Natural) Direct Effect (PDE) is non-parametrically identified via Mediation Formula was `path-breaking' in more than one sense! In same paper Pearl described a thought-experiment as way to motivate PDE. Analysis of this experiment led Robins \& Richardson novel conceptualizing direct effects terms interventions on an expanded graph which treatment decomposed into multiple separable components. We further develop...
Abstract Introduction We describe our technique of using reverse frontal bone graft for FOAR patients with metopic or coronal synostosis and present complications the Leeds classification system in craniosynostosis surgery. Methods Since April 2015, seventeen have been operated this technique. perform a that is then reversed, supraorbital margins are drilled out. The orbital bar removed down to make dust on-lay grafts which used fill gaps on exposed dura around temporal region. Results All...
Many economic and causal parameters depend on nonparametric or high dimensional first steps. We give a general construction of locally robust/orthogonal moment functions for GMM, where conditions have zero derivative with respect to show that orthogonal can be constructed by adding identifying moments the influence function effect step moments. Orthogonal reduce model selection regularization bias, as is very important in many applications, especially machine learning debiased estimators...
Transsphenoidal surgery (TSS) remains the treatment of choice for non-functioning pituitary macroadenomas (NFPMA). The value measuring tumour volumes before and after surgery, its influence on endocrine outcomes further residual or recurrent are unknown.Data from patients who underwent endoscopic TSS a NFPMA (2009-2018) in UK tertiary centre were analysed pre- post-operative surgical outcomes.Of 173 with NFPMA, 159 (61% male) naïve. At presentation, 76.2% (77/101) had ≥1 axis deficit. Older...
We would like to start our rejoinder by responding the philosophical comments in Section 6 of KBW's discussion before getting into other more technical comments.In 6, KBW divide statistical procedures structure-driven and methods-driven but also acknowledge that boundary between these two categories is blurry.For example, even for poster child tools -deep neural networks -one common research direction prove some form optimality or robustness under assumptions, often quantified smoothness,...
The two leading techniques in the UK utilised posterior decompression of cervical spinal cord for spondylotic myelopathy (CSM) are skip laminectomy (Skip LAMT) and open (LAMT). To authors' knowledge no studies have directly compared effectiveness versus laminectomy. This study assessed differences neck disability index, sagittal alignment re-operation rates between both treatment options. A retrospective single institution cohort was performed. Subjects underwent skip- or 2008 2016. Patients...