University of Cambridge > Talks.cam > Zangwill Club > When experimentation meets limits, but simple correlation is uninformative: modelling developmental influences and other complex phenomena

When experimentation meets limits, but simple correlation is uninformative: modelling developmental influences and other complex phenomena

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Nichola Daily.

In recent years there have been blistering critiques from clinical triallists and Bayesian theorists of the way statistics are used in general science and these have now entered the mainstream (eg Ben Goldacre in the Guardian). This highlights the need for wider/deeper understanding of the principles of method. The problem is greatest where control obliges us to handle multivariate data. Contributions of multiple regression and factor analysis are combined in the technique of structural equation modelling (SEM). A rational approach is possible by adhering to the methodological principle of reconciling empirical adequacy (goodness of fit) with parsimony (simplicity and structural elegance of model). The application of basic principles of method will be illustrated by the rational choice and representation of cascade model of developmental influences in 500 children with ear and hearing problems.

This talk is part of the Zangwill Club series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2019 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity