Friday 28 October 2011

2011 Annual Scientific Meeting & AGM (London)




Annual Scientific Meeting & AGM
3rd December 2011
BPS Offices, 30 Tabernacle Street, London, EC2A 4UE
Attendance free
Coffee from 10.30am, Meeting begins at 11am (AGM at 3.30pm)




Keynote Speaker:

Prof Zoltan Dienes: Using Bayes to make the most of null results.


Registration

To register for this free event, please email name, institution, contact details to the Secretary of the Maths, Stats & Computing Section:
Dr Collette Corry cv.corry_at_ulster.ac.uk


Call for papers
The closing date for submissions is Wednesday 26th November 2011

Presentations on both theoretical and substantive applications are welcome in the area of Mathematics, Statistics or Computing in Psychology.  We welcome submissions from postgraduate students.  Abstracts should be submitted (no more than 200 words) with your name, institution and contact details to:  Dr Collette Corry, cv.corry_at_ulster.ac.uk


2011 Ranald Macdonald Postgraduate Research Award


The Mathematical, Statistical and Computing Psychology Section is pleased to invite considerations for the 2011 Ranald Macdonald Postgraduate Research Award. Deadline for applications 30th March 2012

This will be awarded to the best UK Postgraduate thesis/dissertation/project (MSc, MRes, MPhil, Professional Doctorate, DPhil or PhD) using mathematics or statistics in a novel way to investigate an aspect of Psychology. The work and qualification upon which the award is assessed must have been awarded between 1st August 2010 and 31st December 2011.

The award consists of £150 and expenses up to £200 to attend the section's Annual Scientific Meeting in the following year (2012 for the 2011 award). As a condition of accepting the award, the winner will be expected to present on their winning work at that meeting (scheduled for December 2012) and to join the section if they are not already a member.

Details about eligibility and the (simple) application process can be found below or by contacting the Section Secretary Dr Collette Corry.


cv.corry _at_ ulster.ac.uk


Please note the deadline for submissions will be 30th March 2012 at 5pm.

How to apply:

Please send the following to the section secretary Collette Corry via email to:

cv.corry_at_ulster.ac.uk


1. Your full contact details including Name, Institution, Degree Title and Date the qualification was awarded, Address, Email, Telephone number and the Name (s) of Supervisors

2. The extended abstract from your thesis, which outlines the findings of your work

3. A supporting statement from one of your supervisory team outlining the importance and contribution of your thesis and suitability for the award (no more than 300 words) and listing any peer-reviewed publications associated with the work.

Procedure: Your application will be considered by a panel of Mathematical, Statistical and Computing Section Committee members, and the panel’s decision will be final. One or more submissions will be short-listed and their authors may be invited to submit the complete thesis to the panel for final consideration via PDF. The panel reserves the right not to short-list any candidates if the panel does not deem the quality of submissions to be sufficiently high. From time to time the panel may also seek the views of expert reviewers on the quality of a submission prior to short-listing or to making an award. The panel may, in exceptional circumstances, make a split award between two equally deserving candidates.

Criteria for making the award: Emphasis will be placed on the following criteria:

- use of novel mathematics or statistics

- reference to substantive issues in psychology or related disciplines

- clarity of exposition of the mathematical or statistical concepts

- potential or actual contribution to the field, via peer-reviewed publication

Tuesday 30 August 2011

British Journal of Mathematical and Statistical Psychology archives online

The BJMSP archives going back to the first issue (Volume 1 Part 1 in 1947) are now online for subscribers (including BPS members). It began life as the The British Journal of Psychology (Statistical Section), but became known as the British Journal of Statistical Psychology. Although it changed to the British Journal of Mathematical and Statistical Psychology in 1964 the focus was on mathematical contributions to psychology in its broadest sense (including statistics) rather than narrowly on statistics, though factor analysis dominated in the early years. This was probably partly because of the founding editors (Burt and Thomson) and partly because of the importance of factor analysis at the time.


The first editorial by Burt and Thomson is free to all readers here.

Tuesday 21 June 2011

The Jon Rasbash prize for Quantitative Social Science


A new award - The Jon Rasbash prize for Quantitative Social Science - has been established to commemorate the contributions to quantitative social science of Jon Rasbash, who was Professor of Computational Statistics and Director of the Centre for Multilevel Modelling at the University of Bristol. Jon was principally known for his development of multilevel methodology and its software implementation and for his research on studying social relationships within families.

The £500 prize recognizes early career achievement in the development and/ or application of advanced quantitative methods in any social science discipline. Applicants should be UK residents and in the first 10 years of their research career (including periods of postgraduate study).

The prize will be awarded on the basis of a research paper published in a
peer-reviewed journal in 2010 or 2011. The applicant should be the sole or lead author of the paper. Submissions by 1 December 2011.




Wednesday 25 May 2011

Job opportunity Fixed term (1 year) Senior Biostatistician on Growing up project (New Zealand)

For your information:

Senior Biostatistician (click on title for job description)

Fixed term until June 2012, with possible extension

Growing Up in New Zealand: A longitudinal research study of kiwi children and their families

Growing Up in New Zealand is an exciting and ground breaking longitudinal study that is following approximately 7000 children from before they were born until they are adults, in the context of their families. It aims to understand the developmental environment, life experiences and aspirations of these children and families and will provide evidence to help build effective policy, programmes and initiatives to improve outcomes for all of New Zealand’s children. The families involved in the study reflect the cultural diversity of New Zealand, our evolving society, environment and identity.

Further details about the study can be seen on our website http://www.growingup.co.nz

We are seeking an enthusiastic and highly experienced Senior Biostatistician to lead our biostatistics team and work with our multi-disciplinary research team. You will have expertise in the epidemiological and lifecourse principles of longitudinal research design and data analysis. You will be able to contribute to ensuring the robust design, management, analysis and interpretation of our large complex data sets.

You will possess a PhD or higher degree in Statistics, Biostatistics or relevant disciplines and have expertise working with one or more statistical software packages including SAS.

Some of the key aspects of this role are to develop and execute analysis plans, support the research team to ensure data collection enables robust analysis, to lead and manage the biostatistics team including peer review and quality check of their work, to undertake analysis and interpretation of data and to support the preparation of reports and scientific papers.

Growing Up in New Zealand is led by the University of Auckland within UniServices, the largest research and development company in Australasia and a wholly owned company of The University of Auckland.

The position is a full-time position for a fixed term ending on 30 June 2012 in the first instance, with possibility for extension beyond this.

Please email or phone Florence Falconer for further information: f.falconer@auckland.ac.nz +64 (9) 373 7599 begin_of_the_skype_highlighting +64 (9) 373 7599 end_of_the_skype_highlighting ext. 84451.

If you wish to apply please email your CV and a cover letter to Florence at f.falconer@auckland.ac.nz

Monday 9 May 2011

Special Issue: Advances in Statistical Methods for Clinical and Experimental Psychopathology Data

Readers of the blog may be interested that The Journal of Experimental Psychopathology (Volume 2, Issue 2) has a special issue on Advances in Statistical Methods for Clinical and Experimental Psychopathology Data.

It is edited by Andy Field and Eric Woody:

·         How to Conduct and Statistically Analyze Case-Based Time Series Studies, One Patient at a Time
Michael R Nash, Jeffery J Borckardt, Amineh Abbas, Erin GrayD
·         Performing Taxometric Analysis to Distinguish Categorical and Dimensional Variables
John Ruscio, Ayelet Meron Ruscio, Lauren M Carney
·         Best Practices for Using Median Splits, Artificial Categorization, and their Continuous Alternatives
Jamie DeCoster, Marcello Gallucci, Anne-Marie R Iselin
·         Using Bootstrap Estimation and the Plug-In Principle for Clinical Psychology Data
Daniel B Wright, Kamala London, Andy P Field
·         A Primer on Meta-Analysis in Clinical Psychology
Scott A Baldwin, William R Shadish

Tuesday 19 April 2011

2011 meeting of the European Mathematical Psychology Group

The next meeting of the European Mathematical Psychology Group (EMPG 2011) will be held in Paris, from August 29 to August 31, 2011. The Web site of the conference is now available at the following address:

http://www.infres.enst.fr/~hudry/EMPG/

You will find there the way to register and to submit a communication, as well as other details about the organization. All communications dealing with any subject related to mathematical psychology are welcome.

The main features of EMPG 2011 are the following:

* Dates : 29-30 August 2011

* Place : Telecom ParisTech, Paris, France

* No fees.

* Proceedings:

- a special issue of Electronic Notes in Discrete Mathematics (ENDM) will be devoted to the meeting
- we are studying the possibility to publish full papers in a special issue of Mathematics and Social Sciences

* Important dates:
- May 15, 2011: deadline for the reception of abstracts (1 page, sent to Olivier Hudry (hudry at enstr.fr)
- June 15, 2011: notification of acceptance of the communication
- August 19, 2011: deadline for registration
- August 29-31, 2011: 2011 EMPG meeting
- September 30, 2011: deadline for submitting a contribution to the special issue of ENDM

Monday 7 February 2011

Annual Scientific Meeting 2011 abstracts and links

 Annual Scientific Meeting 2011 abstracts and links

Music and amusis - an experience sampling study

Diana Omigie, Goldsmith’s University (London)

Congenital amusia (CA) is a developmental disorder characterized by deficits in melody perception and production. Empirical research into this condition has the potential to throw light on questions like how the brain processes music and why music listening can bring such pleasure to its listeners. However recent work has focused mainly on the perceptual abilities of people with C.A. and there has been little research into whether and how the observed perceptual deficits affect their appreciation of music in every day life. Assessing the degree with which amusics willingly engage with music in everyday life is a useful way of inferring how they feel about it and consequently evaluating the relationship between music perception and appreciation. We used hierarchical cluster analysis to evaluate the experiences ampling data collected from a total of 34 participants (17 amusics and 17 matched controls) and then observed how amusics were distributed over the resulting analysis solution. We found that at least 60 percent of amusics demonstrated a listening profile that was clearly distinct from that of controls. These amusics showed little evidence of wanting to engage with music in their everyday life. However the remaining amusics who fell into the cluster that mainly contained controls showed evidence of normal music appreciation; choosing to listen regularly and reporting obtaining pleasure from it. This research is important as it reveals contrasting attitudes towards music within the condition known as Congenital amusia. The reasons why appreciation may arise in the absence of normal perception are explored and further analysis is carried out to try to explain why the two groups of amusics show such different attitudes to music.


Research methods achievement predicted by stress, social class, and locus of control, but not dyscalculia

John Barry, City University (London)

Negative attitudes towards learning research methods (RM) are associated with poor grades and dropout. The present cross-sectional internet survey explored preferences for learning RM and factors associated with RM grades. Psychology students (N = 134) from high school to postgraduate level reported that more interaction with their teacher would improve grades. Those with most RM difficulty also wanted: practical work, visual teaching aids, more interesting textbooks, humour in teaching, smaller seminar groups, and more seminars. Using ordinal regression, the significant predictors of better RM grades relative to grades for other modules were: lower stress (p < .001), more advantaged social background (< .005), and internal locus of control (p < .013). The effect of motivation was mediated by stress. Dyscalculia was not associated with RM grade. These findings have implications for ways to improve the teaching of research methods to psychology students.


Multiple hypothesis testing when hypotheses are related logically
using Shaffer’s R test: 
A hierarchical step down procedure with a step up test at each step

Andrew Rutherford, Keele University

Hochberg’s (1988) presented a powerful test based on Simes’ (1986) inequality.  Rom (1990) later improved this test by defining and calculating exact p-values.  Later, Hochberg and Rom (1995) described how to apply their tests when hypotheses were related logically, as described by Shaffer (1986).  However, as Hochberg and Rom’s (1995) account is not easily understood by sophisticated statistical mathematicians, it presents real problems for most other scientists.  This may explain the lack of application of this important work.  In response to my request for worked examples, Juliet Shaffer provided valuable insights into multiple hypothesis testing and Dror Rom delivered a new short-cut method to test logically related hypotheses, which he named Shaffer’s R test.  The background and application of Shaffer’s R test will be described.


Exploring what is hidden: The power of Latent Class Analysis in uncovering barriers to engagement in the arts

Glenn A. Williams, Nottingham Trent University

Latent class analysis is a powerful technique that enables researchers to glean insights into ‘hidden’ psychological experiences.  It has been used in a variety of domains, such as with attempts: to understand psychosis as measured along a continuum of symptom expression; to identify features of computer games that are integral to the gaming experience; and to assess the characteristics of a range of trauma and suicidal behaviour typologies.  The technique is grounded in the psychometric approach and item response theory and is a versatile method to dealing with nominal data in a deep and psychologically grounded way.  This presentation will involve discussion of the key principles and practices when undertaking a latent class analysis.  To illustrate the art and science of latent class analysis, a case example will draw on the nuances of data obtained from a general population survey of over 4,300 respondents and will model a set of various class solutions to unearth the barriers to engagement in the arts that could be present within a community.  


Towards a rational use of mathematics in the psychology of reasoning

Andy Fugard, University of Salzburg

Logic is the mathematics of reasoning.  Traditionally, logic in the psychology of reasoning was taken to mean classical logic and most non-mathematicians received a diagnosis of illogical.  However, there are many logics, including probability logics.  For so-called "basic" conditionals such as "If the card shows a square, then it's red", most people's degree of belief is given by a conditional probability, P(red|square), a justifiably rational interpretation.  However, a significant minority treat an "if" as an "and" (conjunction), which is less easy to justify.  Previously we found that, given a long series of trials, many of those initially showing a conjunction interpretation spontaneously shift to a conditional probability.  In this talk I will present evidence that automatic stimulus-oriented processes are responsible for the conjunctions and inhibitory function is required for a shift.  In another experiment we tested the effect of different expressions of identical  (from the perspective of probability theory) conditionals, e.g., for conditionals concerning four cards numbered 1 to 4: "If the card shows a 2, then it shows a 2 or a 4" versus "If the card shows a 2, then it shows an even number".  For the former type of conditional, most participants' degree of belief was 0, versus 1 for the latter type of conditional.  A theory of relevant deduction, originally developed for classical logic, explains these two interpretations.  These results illustrate the utility, and limitations, of logic for guiding theorizing and designing experiments about how non-mathematicians reason.


Adaptive design for model discrimination

Maarten Speekenbrink, University College London

Psychology is rich in formal models of learning, categorization and decision-making, to name but a few areas. While competing models differ in their substantive assumptions, they often make highly similar predictions. For this reason, model comparison based on empirical data is often inconclusive. Optimizing the design of an experiment for model discrimination is difficult, especially when individual participants differ widely in terms of model parameters. To resolve this problem, we present a method to design experiments adaptively whilst running them, at each trial choosing the stimulus which is expected to minimize the entropy of the posterior probability distribution over a set of competing models. We show the advantages of adaptive design in simulation study. We then present data from an experiment in which the method was applied to discriminate between competing models of category learning, including an exemplar model (the Generalized Context Model) and a decision bound model.

British Journal of Mathematical & Statistical Psychology 2011 Issue 1 online




British Journal of Mathematical and Statistical Psychology
Wiley-Blackwell
is proud to publish the British Journal of Mathematical and
Statistical Psychology
on behalf of The British
Psychological Society
.
Download the first issue of 2011

Keep up to date with British Journal of Health Psychology Testing overall and moderator effects in random
effects meta-regression


Hilde M. Huizenga, Ingmar Visser and Conor V. Dolan



Correcting an analysis of variance for clustering

Larry V. Hedges and Christopher H. Rhoads



Evaluation of convergent and discriminant validity
with multitrait–multimethod correlations


Tenko Raykov



Decision making on ambiguous stimuli such as prosody
by subjects suffering from paranoid schizophrenia, alcohol dependence,
and without psychiatric diagnosis


Karol Fabia´nczyk



Bayesian estimation of semiparametric nonlinear
dynamic factor analysis models using the Dirichlet process prior


Sy-Miin Chow, Niansheng Tang, Ying Yuan, Xinyuan Song
and Hongtu Zhu




Ridge structural equation modelling with correlation
matrices for ordinal and continuous data


Ke-Hai Yuan, Ruilin Wu and Peter M. Bentler



The linear mixed model and the hierarchical
Ornstein–Uhlenbeck model: Some equivalences and differences


Zita Oravecz and Francis Tuerlinckx



Expert tutorial

Binary recursive partitioning: Background, methods,
and application to psychology


Edgar C. Merkle and Victoria A. Shaffer



Statistical software review

R you ready for R?: The CRAN Psychometrics Task View

Ali Ünlü and Takuya Yanagida
About
British Journal of Mathematical and Statistical
Psychology

The British Journal of Psychology
Sign Up for E-alerts


Submit an Article


Subscribe Today!


The Journals of the BPS


BPS Blackwell
Edited
by
: Thom Baguley



Impact Factor: 0.83



ISI Journal Citation Report © Ranking 2009:
7/11 (Psychology, Mathematical); 50/80 (Mathematics Interdisciplinary
Applications); 56/100 (Statistics and Probability); 67/74 (Psychology,
Experimental)



The British Journal of Mathematical and Statistical Psychology
publishes articles relating to areas of psychology which have a greater
mathematical or statistical aspect of their argument than is usually
acceptable to other journals including:

  • mathematical
  • psychology
  • statistics
  • psychometrics
  • decision making
  • psychophysics
  • classification
  • relevant areas of mathematics, computing and computer
    software
These include articles that address substantitive psychological issues
or that develop and extend techniques useful to psychologists. New
models for psychological processes, new approaches to existing data,
critiques of existing models and improved algorithms for estimating the
parameters of a model are examples of articles which may be favoured.



For specific submission requirements, please view the Author Guidelines.



Early View: Articles now appear on Early
View before the paper version is published – Click here to see the Early View articles currently available online;
BPS
Blackwell
For
the complete range of Blackwell BPS books, please go to: www.wiley.com/go/bps
About
The British Psychological Society
The
British Psychological Society
is the representative body for
psychology and psychologists in the UK.



The Journals of the British Psychological Society form an essential
part of the Society's mission to advance and disseminate psychological
knowledge. With a publishing history spanning over 100 years, our
journals portfolio is at the forefront of the psychology community with
international contributions and readership.



For more information or to join the Society, please visit www.bps.org.uk The British Psychological Society
Wiley-Blackwell



wileyonlinelibrary.com/journal/bjhp
Wiley Online Library


here
http://onlinelibrary.wiley.com/user-registration
http://onlinelibrary.wiley.com/user-registration

Monday 17 January 2011

2010 CPD Workshop slides



Slides from all three of the 2010 CPD workshops (held in Nottingham on 13th December) are now available:



R: An introduction for psychologists (Thom Baguley & Danny Kaye, Nottingham Trent University)

Linear mixed models using R (Andy Fugard, Salzburg University)


An introduction to PsychoPy (Jonathan Peirce)