Home
Archive
Background
FAQ
People
Publications                         

ANALYSIS OF MULTIPLE INFORMANT DATA

Welcome to the home page for the multiple informant data project.  Multiple informant (or multiple source) data are often collected in surveys designed to measure mental health outcomes and risk factors in community or service-based samples (though they arise in other settings as well).  For example, in assessments of a child's mental health status, parents, teachers, children, clinicians, peers, and trained observers have served as informants or sources. Multiple sources have also become increasingly common in hospital-based and outpatient-based assessments of treatments for mental illness and service utilization.  Contemporary studies commonly use two or three informants as data sources.  An inherent feature of multiple informant data is that one anticipates discordant reports. If there is no discordance, the additional reports provide no new information. Multiple sources are used to provide data either on independent variables (risk factors or predictors), or dependent variables (outcomes), or both.  

The project develops methodology for the analysis of multiple informants .  Take a look at What's New in our web.  Other information includes background information on multiple informants, frequently asked questions, macros and examples (under construction), publications, and a list of project members.

This research is funded by NIMH grant R01-MH54693.

What's New

August, 2008: Some old and some new statistical tools for outcomes research, published in Circulation.

July, 2008: A maximum likelihood latent variable regression model for multiple informants, published in Statistics in Medicine.

January, 2008: Statistical methodology for classifying units on the basis of multiple-related measures, published in Statistics in Medicine.

September, 2007: Analysis of partially observed multiple source/multiple informant reports from complex survey data in Stata, presentation at the 4th Italian Stata User's Group meeting.

October, 2007: Differential item functioning between ethnic groups in the epidemiological assessment of depression, published in Journal of Nervous and Mental Disease.

August, 2007: Estimation of marginal regression models with multiple source predictors, in press in Handbook of Statistics.

June, 2007: Assessing surrogacy of data sources for institutional comparisons, published in Health Services and Outcomes Research Methodology.

February, 2007: Much ado about nothing: A comparison of missing data methods and software to fit incomplete data regression models, published in The American Statistician.

September, 2006: Marginal regression models with a time to event outcome and discrete multiple source predictors, published in Lifetime Data Analysis.

August, 2006: Maximum likelihood estimation of marginal pair-wise associations with multiple source predictors, published in Biometrical Journal.

June, 2006: Incorporating missingness for estimation of marginal regression models with multiple source predictors., published in Statistics in Medicine.

July, 2005: Analysis of multiple source/multiple informant data in Stata, presentation at the 4th North American Stata User's Group meeting.

February, 2005: Regression models for the analysis of longitudinal Gaussian data from multiple sources, published in Statistics in Medicine.

August, 2004: Tutorial in biostatistics: regression analysis of multiple source and multiple informant data from complex survey samples, published in Statistics in Medicine.

June, 2004: Innovative statistical approaches in health services research: multiple informant analyses, presented in the 2004 AcademyHealth Annual Research Meeting (ARM).

April, 2004: Assessing missed opportunities for HIV testing in medical settings, published in Journal of General Internal Mediciine.

November, 2003: A potential for bias when rounding in multiple imputation, published in The American Statistician.

June, 2003: Analysis of longitudinal multiple-source binary data using generalized estimating equations, published in Journal of the Royal Statistical Society: Series C (Applied Statistics).

February, 2003: Multiple informants: a new method to assess breast cancer patient's comorbidity, published in the American Journal of Epidemiology; The use of multiple informants in identifying the risk factors of depressive and disruptive disorders: are they interchangeable? published in Social Psychiatry and Psychiatric Epidemiology. 

December, 2002: A method for modeling utilization data from multiple sources: application in a study of linkage to primary care, published in Health Services and Outcomes Research Methodology.

July, 2002:  Maximum likelihood estimation of bivariate logistic models for incomplete responses with indicators of ignorable and non-ignorable missingness published in Applied Statistics.

January, 2002:  Regression analysis of multiple-source longitudinal outcomes: a "Stirling County" depression study published in the American Journal of Epidemiology

October, 2001:  Multiple informants: mortality associated with psychiatric disorders in the Stirling County Study published in the American Journal of Epidemiology.

March, 2001:  Multivariate linear regression analysis of childhood psychopathology using multiple informant data  published in the International Journal of Methods in Psychiatric Research.

Back to Top
visits since August 17, 2004

Last updated August 24, 2008 by Nicholas Horton