Methodology Research Group:
useful links for mental health researchers
Randomisation services
Design of randomised trials
Analysis of randomised trials - general
Analysis of randomised trials - causal inference
Analysis of randomised trials - missing data
Analysis of randomised trials - multilevel modelling
Reporting standards
Psychometrics
Statistical software
General links
Randomisation services
Directory of randomisation software and services
This is a directory of randomisation software and services for clinical trials, including both simple do-it-yourself software and 24-hour telephone randomisation service. It is intended to help people planning and seeking funding for clinical trials. The directory is housed on the website of Martin Bland, a professor of health statistics in the Department of Health Sciences, University of York.
Bristol Randomised Trials Collaboration, University of Bristol
Health Services Research Unit (HSRU) (University of Aberdeen)
HSRU offer a 24-hour, seven day telephone randomisation service and/or randomisation over the web.
Design of randomised trials
Clinical Trials Toolkit
A Department of Health/Medical Research Council website giving practical help when trying to meet the requirements of the UK Medicines for Human Use (Clinical Trials) Regulations 2004.
Analysis of randomised trials - general
British Medical Journal: Statistics Notes
Gives links to a series of short articles on the use of statistics published between 1994 and 2004, many of them written by Doug Altman and Martin Bland.
Analysis of randomised trials - causal inference
Jamie Robins’ papers
Enormous range of papers, mostly highly technical, on causal inference from complex observational and randomized studies with time-varying exposures or treatments.
Ed Rigdon’s Structural Equation Modelling Page
Provides links to the websites of key people in field of structural equation modelling, software to conduct analysis and other related websites.
Mediation and Moderation
An introduction and guide to the topic of mediation and moderation analysis, including descriptions of the topic and SPSS and SAS software to conduct analysis.
Design and methods of explanatory (causal) analysis for randomised trials of complex interventions in mental health
A University of Manchester Biostatistics research project with a focus on mediation.
Analysis of randomised trials - missing data
www.missingdata.org.uk
Created by the Medical Statistics Unit at the London School of Hygiene and Tropical Medicine. The site offers support to researchers from the social and medical sciences with the analysis of incomplete datasets and acts as a focus for statistical research.
Software for multiple imputation
This software was written by Joe Schafer of the Department of Statistics, The Pennsylvania State University. The software may be used by anyone if credit is given.
Multiple Imputation Online
From the Department of Statistics, TNO Quality of Life, The Netherlands. Contains the software MICE and links to lots of other software.
PEAS (Practial Exemplars and Survey Analysis)
supported by the Economic and Social Research Council Research Methods programme ‘Using imputation for missing values’
Gary King – Harvard University
Gary King develops and applies empirical methods in many areas of social science research, focusing on innovations – from statistical theory to practical application. The site includes programmes – including Ammelia II: a program for missing data (2009).
Analysis of randomised trials - multilevel modelling
Centre for Multilevel Modelling
A research centre based at the University of Bristol. The site offers free download of the widely used MLwiN software for UK academics.
Reporting standards
The CONSORT (Consolidated Standards of Reporting Trials) statement
is a tool intended to improve the reporting of a randomised controlled trial (RCT), enabling readers to understand a trial's design, conduct, analysis and interpretation, and to assess the validity of its results.
Similar statements are available:
in meta-analysis: the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) statement.
in observation studies: the STROBE (STrengthening the Reporting of OBservational studies in Epidemiology) statement.
Psychometrics
The Basics of Item Response Theory
by Frank B Baker
Applying item response theory modeling for evaluating questionnaire item and scale properties
by Bryce B Reeve and Peter Fayers
also National Cancer Institute (US)
Item Response Theory (IRT) and Applications of IRT for Improving Health Outcomes Measurement
Cran Task view: Psychometric methods and models
Latent class analysis in SAS from Methodology Center, Penn State
including .. Latent Class Analysis with Distal Outcome (Excel calculator), LCA outcome probability calculator (Version 1.0) [Software] (2011)
University Park: The Methodology Center, Penn State.
Statistical software
GLLAMM (Generalized Linear Latent And Mixed Models)
Statistical Computing Resources (University of California)
General links
Interest Group on Statistics in Mental Health Research In the American Statistical Association (ASA)
Medical Research Council Clinical Trials Unit
Statistics Departments in UK and Irish universities
page created by the Department of Actuarial Mathematics and Statistics, Heriot-Watt University.
Statistics on the Web
page created by Clay Helberg from Terra XML.
Quantitative Methods Resources
from the web page of Alexander J Shackman
MDRC (formerly the Manpower Demonstration Research Corporation) Methodology Initiative.
Prevention Science and Methodology Group
(Hendricks Brown, Muthen et al).
page last updated 30 March 2012