E-books for causal modelling and missing data methods

Project start / end: 1st August 2012 to 31st March 2014

Award holders: William Browne (PI; LEMMA III node), Bianca De Stavola (PATHWAYS node) Paul Clarke (LEMMA III node), Christopher Charlton (LEMMA III node), Mike Kenward (PATHWAYS node), Rhian Daniel (PATHWAYS node)

Staff: Richard Parker, Sarah Miller (PATHWAYS node)

As well as the PI, co-applicants and staff listed above, Harvey Goldstein (LEMMA III node) and Richard Silverwood (PATHWAYS node) have also both been instrumental in helping achieve the project's objectives.

The aims of this project - a collaboration between the LEMMA III and PATHWAYS nodes of the ESRC-funded National Centre for Research Methods (NCRM) - were to produce electronic notebooks (eBooks) for use with the Stat-JR software package for teaching social science researchers about causal modelling and missing data and assisting them in performing their statistical analyses.

To this end, an eBook employing a Stat-JR super-template (2LevelImpute) for 2-level data that allows for missing values in explanatory or response variables, and can handle normal or categorical variables, has been developed, and is now available for download for use with Stat-JR.

An eBook (and supporting template) with examples estimating causal effects in the presence of mediating variables, using the gformula command in Stata, an implementation of the g-computation procedure, has also been developed.