Short course: There are still a few places available on this course.
Longitudinal data analysis using the Unix version of S-plus and
Oswald, 2-4 June 1998
---------------------------------------------------------------------
* Fees only 90 pounds per 3 day course for full-time students,
British academic staff and ESRC-funded researchers!
* course is FREE to ESRC funded students.
Longitudinal data - repeated observations made over time on a number of
independent subjects - provide many challenges in data analysis, both in
dealing
with the complexity and size of the data and in methodological issues such
as the modelling of the inherent correlation. Software for longitudinal
data analysis must therefore provide facilities for dealing with such
complexity at all stages of analysis, from reading and manipulating the
data to exploring the data and fitting appropriate models.
Following on from course 3 "Linear models for longitudinal data", this
course will provide instruction in the S-plus package "Oswald:
Object-Oriented Software for the Analysis of Longitudinal Data" developed
at Lancaster University. Through the use of lectures and practical
data-analysis examples with "hands-on" sessions in the Unix workstation
laboratory, this three-day course will cover the following:
1. Introduction to S-plus and Oswald.
2. Data structures and methods for longitudinal data.
3. Exploring longitudinal data: creating graphs, smoothing, exploring
correlation structure.
4. Specifying linear models for longitudinal data.
5. Fitting parametric models for the correlation structure: serial correlation,
random effects, mixed modelling; estimation and testing.
This course assumes no knowledge of S-plus or Oswald, although a familiarity
with statistical computing packages in general will be helpful.
Participants should be familiar with the concepts and models for
longitudinal data as discussed in course 3 "Linear models for longitudinal
data".
This course will be given by David M Smith, Research Associate in the
Department of Mathematics and Statistics at Lancaster University. He is senior
author of the Oswald software package.
References:
Smith D.M., Robertson B.S. and Diggle P.J. (1998) "Oswald: Object-Oriented
Software for the Analysis of Longitudinal Data in S-plus". Software manual,
available from http://www.maths.lancs.ac.uk/Software/Oswald/
Diggle P.J., Liang K. and Zeger S.L. (1994) Analysis of Longitudinal Data,
Oxford University Press, Oxford.
Further information, and a registration form, are available on the
World Wide Web at
http://www.cas.lancs.ac.uk/courses.html
Alternatively, they may be obtained from:
Mary Peckham, Centre for Applied Statistics, Fylde College
Lancaster University, Lancaster LA1 4YF, UK
Tel: +44 (0)1524 593064 (direct line), Fax: +44 (0)1524 592681,
E-mail: [log in to unmask]
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|