Past Events: UCL Women in Mathematical Sciences
Handling missing values in cross-national surveys: a latent variable approach
Wednesday, 11 June 2014, 12.00 - 13.00
Statistics Lecture Room (Torrington Place (1-19) 102)
Sample surveys collect information on a number of variables for a randomly selected number of respondents. Among other things, the aim is often to measure some underlying trait(s) of the respondents through their responses to a set of questions. In the paper, we focus on cross-national surveys. The main research objective is to compare the distribution of the latent variables across countries (structural model). In some applications, latent variables will be considered continuous (e.g. ability) and in some other applications discrete (e.g. health state). Here, our focus will be primarily the modelling of item non-response and studying its effect on cross-countries comparisons. Measurement invariance will be assumed for the observed indicators conditional on the latent variables across countries. Various model extensions are proposed here to model the missing data mechanism together with the measurement and structural model. The model for the missing data mechanism will serve two purposes: first to characterize the item non-response as ignorable or non-ignorable and consequently to study the patterns of missingness and characteristics of non-respondents across countries but also to study the effect that a misspecified model for the missing data mechanism might have on the structural part of the model.
(M. Katsikatsou, J. Kuha, I. Moustaki)
Irini Moustaki is a professor of Social Statistics at the London School of Economics and Political Science. Her research interests are in the areas of latent variable models and structural equation models that are widely used in Social Sciences and Educational Testing for measuring unobserved constructs such as attitudes, health status, behaviours, intelligence, performance, etc. Her methodological work includes treatment of missing data, longitudinal data, detection of outliers, goodness-of-fit tests and advanced estimation methods. Furthermore, she has made methodological and applied contributions in the areas of comparative cross-national studies and epidemiological studies on rare diseases.
Mathematics for solving real problems
Wednesday, 12 March 2014, 12.00 - 13.00
Pearson (North East Entrance) G22 LT
This talk will describe the research developments associated with two projects that I am involved in via my collaborations with both industry and academics from different disciplines. They are two completely different problems, requiring very different approaches and working with very different people, but both rely on the development of new methodology. The first is associated with the development of software to allow for the breakdown of intra-day volatility into daily, monthly and longer term volatility for commodity prices. The second is the development of statistical techniques which allow us to quantify the effect of area deprivation on child pedestrian casualties. Through these two case studies, I will attempt to give a flavour of the issues, both good and bad, that I have found in my experience of collaborative work on real problems.
Emma McCoy is the Deputy Head of the Mathematics Department and a member of the Statistics Section at Imperial College London. She holds an MSc in Computational Statistics from the University of Bath and a PhD from the Department of Mathematics at Imperial. Emma has been a mathematics subject expert for the Department for Education and teaches statistics at the undergraduate and postgraduate level. She regularly participates in mathematics dissemination activities including delivering Royal Institution Mathematics Masterclasses and has given the London Mathematical Society Popular Lecture. Her published research includes work on the development of statistical methodology for time series, with applications in signal processing and financial time series analysis, incorporating methods for prediction and inference. Her most recent research involves the development of novel causal methods for statistical inference.
First Women's Lunch
PhD Students, Postdoctoral Fellows and Staff from CoMPLEX, Mathematics Department, Statistical Science Department
Come and meet other female researchers of the departments in an informal environment. Lunch will be provided.
Wednesday, 30 October 2013, 12.00-14.00
Pearson Room (Room 116), 1-19 Torrington Place
Page last modified on 30 jun 14 19:45