Programme And Abstracts For Thursday 30th Of November
Keynote: Thursday 30th 9:00 Mantra
A General Framework For Functional Regression Modelling
Sonja Greven and Fabian Scheipl
LMU Munich
Recent technological advances generate an increasing amount of functional data, data where each observation represents a curve or an image (Ramsay and Silverman, 2005). Examples of technologies that generate functional data include imaging techniques, accelerometers, spectroscopy and spectrometry. Any kind of measurement collected over time - data usually referred to as longitudinal - can also be viewed as potentially sparsely observed functional data.
Researchers are increasingly interested in regression models for functional data to relate functional observations to other variables of interest. We will discuss a comprehensive framework for additive (mixed) models for functional responses and/or functional covariates. The guiding principle is to reframe functional regression in terms of corresponding models for scalar data, allowing the adaptation of a large body of existing methods for these novel tasks. The framework encompasses many existing as well as new models. It includes regression for ‘generalized’ functional data, mean regression, quantile regression as well as generalized additive models for location, shape and scale (GAMLSS) for functional data. It admits many flexible linear, smooth or interaction terms of scalar and functional covariates as well as (functional) random effects and allows flexible choices of bases - in particular splines and functional principal components - and corresponding penalties for each term. It covers functional data observed on common (dense) or curve-specific (sparse) grids. Penalized likelihood based and gradient-boosting based inference for these models are implemented in R packages refund and FDboost, respectively. We also discuss identifiability and computational complexity for the functional regression models covered. A running example on a longitudinal multiple sclerosis imaging study serves to illustrate the flexibility and utility of the proposed model class. Reproducible code for this case study is also available online with the recent discussion paper Greven and Scheipl (2017) this talk is based on.
Thursday 30th 10:30 Narrabeen
Hockey Sticks And Broken Sticks – A Design For A Single-Arm, Placebo-Controlled, Double-Blind, Randomized Clinical Trial Suitable For Chronic Diseases
Hans Hockey1 and Kristian Brock2
1Biometric Matters Ltd.
2Cancer Research UK Clinical Trials Unit
Thursday 30th 10:30 Gunnamatta
Bounding IV Estimates Using Mediation Analysis Thinking
Theis Lange1,2
1University of Copenhagen
2Peking University
Thursday 30th 10:50 Narrabeen
Bayesian Regression With Functional Inequality Constraints
Joshua Bon1, Berwin Turlach1, Kevin Murray1, and Christopher Drovandi2
1University of Western Australia
2Queensland University of Technology
Thursday 30th 11:10 Narrabeen
Genetic Analysis Of Renal Function In An Isolated Australian Indigenous Community
Russell Thomson1, Brendan McMorran2, Wendy Hoy3, Matthew Jose4, Tim Thornton5, Gaétan Burgio2, and Simon Foote2
1Western Sydney University
2ANU
3University of Queensland
4University of Tasmania
5University of Washington
In close consultation with the local land council, and with ethical approval from many ethics committees, we have performed a genome-wide association study (GWAS) on a sample cohort from the 1990s. We also have a follow up data set of 120 study participants from 2014, with DNA sequence data.
I will discuss the statistical analyses of these data sets, with respect to issues of degraded DNA, high error rates and correlated samples.
Thursday 30th 11:10 Gunnamatta
The Performance Of Model Averaged Tail Area Confidence Intervals
Paul Kabaila
La Trobe University
Commonly in applied statistics, there is some uncertainty as to which explanatory variables should be included in the model. Frequentist model averaging has been proposed as a method for properly incorporating this “model uncertainty” into confidence interval construction. Such proposals have been of particular interest in environmental and ecological statistics.
The earliest approach to the construction of frequentist model averaged confidence intervals was to first construct a model averaged estimator of the parameter of interest consisting of a data-based weighted average of the estimators of this parameter under the various models considered. The model averaged confidence interval is centered on this estimator and has width proportional to an estimate of the standard deviation of this estimator. However, the distributional assumption on which this confidence interval is based has been shown to be completely incorrect in large samples.
An important conceptual advance was made by Fletcher & Turek (2011) and Turek & Fletcher (2012) who put forward the idea of using data-based weighted averages across the models considered of procedures for constructing confidence intervals. In this way the model averaged confidence interval is constructed in a single step, rather than first constructing a model averaged estimator.
We review the work of Kabaila et al (2016, 2017) which evaluates the performance of the model averaged tail area confidence interval of Turek & Fletcher (2012) in the “test scenario” of two nested normal linear regression models. Our assessment of this confidence interval is that it performs quite well in this scenario, provided that the data-based weight function is carefully chosen.
References:
- Kabaila, P., Welsh, A.H., & Abeysekera, W. (2016) Model-averaged confidence intervals. Scandinavian Journal of Statistics.
- Kabaila, P., Welsh, A.H. and Mainzer, R. (2017) The performance of model averaged tail area confidence intervals. Communications in Statistics - Theory and Methods.
Thursday 30th 11:30 Narrabeen
Deconstructing The Innate Immune Component Of A Molecular Network Of The Aging Frontal Cortex
Ellis Patrick1, Mariko Taga2, Marta Olah2, Hans-Ulrich Klein2, Charles White3, Julie Schneider4, Lori Chibnik5, David Bennett4, Sara Mostafavi6, Elizabeth Bradshaw2, and Philip De Jager2
Alzheimer’s disease is pathologically characterized by the accumulation of neuritic -amyloid plaques and neurofibrillary tangles in the brain and clinically associated with a loss of cognitive function. The dysfunction of microglia cells has been proposed as one of the many cellular mechanisms that can lead to an increase in Alzheimer’s disease pathology. Investigating the molecular underpinnings of microglia function could help isolate the causes of dysfunction while also providing context for broader gene expression changes already observed in mRNA profiles of the human cortex.
1University of Sydney
2Columbia University
3The Broad Institute
4Rush University
5Harvard University
6Universtiy of British Columbia
Thursday 30th 11:30 Gunnamatta
Bias Correction In Estimating Proportions By Pooled Testing
Graham Hepworth1 and Brad Biggerstaff2
1University of Melbourne
2Centers for Disease Control and Prevention
Pooled testing (or group testing) arises when units are pooled together and tested as a group for the presence of an attribute, such as a disease. We have encountered pooled testing problems in plant disease assessment and prevalence estimation of mosquito-borne viruses.
In the estimation of proportions by pooled testing, the MLE is biased, and several methods of correcting the bias have been presented in previous studies. We propose a new estimator based on the bias correction method introduced by Firth (1993), which uses a modification of the score function. Our proposed estimator is almost unbiased across a range of problems, and superior to existing methods. We show that for equal pool sizes the new estimator is equivalent to the estimator proposed by Burrows (1987), which has been used by many practitioners.
Thursday 30th 11:50 Narrabeen
The Parametric Cure Fraction Model Of Ovarian Cancer
Serifat Folorunso, Angela Chukwu, and Akintunde Odukogbe
University of Ibadan
Thursday 30th 11:50 Gunnamatta
The Skillings-Mack Statistic For Ranks Data In Blocks
John Best
University of Newcastle