QM Seminar Programme

The QM Hub has had an active and sustained seminar programme for more than five years, hosting over 20 presentations each academic year.

The programme builds on a tradition of addressing substantive educational research questions using quantitative methods, as well as presenting a particular quantitative method which can serve as inspiration for educational research (and more widely for research in the social sciences). Presentations are given by both academics and higher degree students within friendly lunch-time seminars that are open to all. The programme is convened by Professor Steve Strand, Dr Lars-Erik Malmberg, and Dr Ariel Lindorff.

Presentations take place on Mondays in Seminar Room D from 12:30pm-1:45pm at the Department of Education, 15 Norham Gardens, Oxford OX2 6PY.  Click on the ‘How to find us’ link on the right for directions. If you do not have access to the Department, please call at Reception and you will be directed to the room.

Children’s physical activity and mental health

26 February 2018 12:30 - 13:45
Seminar Room D

Speaker: Jane Ahn, University of London

Convener: Dr Lars-Erik Malmberg

The relationship between physical activity and mental health: findings from the UK Millennium Cohort Study

Background

The benefits of physical activity (PA) on mental health in adults is well established, but less is known about this relationship in children. The aim is to examine the association between objectively measured sedentary time and PA, and mental health in children from the UK Millennium Cohort Study (MCS).

Methods

Accelerometer data were collected at MCS4 (age 7), and mental health was measured at MCS4 and MCS5 (age 11) using the Strengths and Difficulties Questionnaire (SDQ). Associations between mean daily PA minutes at different intensities at MCS4 and SDQ outcomes at MCS5 were estimated using multiple linear regression models.

Results

In fully adjusted models, increased PA at MCS4 was associated with fewer peer problems in boys and girls at MCS5. Greater sedentary time was associated with more peer problems and fewer hyperactivity symptoms in boys and girls. Increased MVPA was associated with more conduct and hyperactivity problems in boys and more hyperactivity in girls.

A study of children starting school and the progress they make in their first year around the world: The iPIPS project (Public Seminar)

26 February 2018 17:00 - 18:30
Seminar Room G/H

Speaker: Professor Peter Tymms, Durham University

Convener: Professor Steve Strand, Quantitative Methods Hub

The iPIPS project is an international study of children starting school around the world and the progress that they make in their first year at school. It is based on the Performance Indicators in Primary Schools (PIPS) baseline which has been used with about 3 million children and translated into more than a dozen languages. The talk will set out the large range of key cognitive and non-cognitive skills exhibited by children on entry to school and the great progress that they usually make during grade 1. It will reflect on the different educational systems found across the world, the differing approaches to education and discuss the challenge of making comparisons across cultures. Finally, some of the progress which has been made in overcoming technical, cultural and psychometric challenges will be outlined.

 

An introduction to Bayesian structural equation modelling

05 March 2018 12:30 - 13:45
Seminar Room D

Speaker: Lars Malmberg, University of Oxford

Bayesian statistical modelling is on a sharp rise in the social science. Its philosophical basis rests on estimating the probability of parameter estimates given data, rather than the probability of data given a model (referred to as null-hypothesis statistical testing, NHST). It is a very feasible technique for situations in which (1) large-sample assumptions for Maximum Likelihood do not hold, or (2) models are complex resulting in misbehaved parameters (e.g., Heywood cases, negative residuals, correlations > 1). Bayesian techniques have been implemented in a range of freeware (e.g., R) and commercial software (e.g., SPSS, Mplus).  I will provide a gentle introduction to the modelling logic and a worked example for Bayesian structural equation models (BSEM).