[R] R vs SPSS

[Stuart Leask]

> > What worries me about SPSS is that it often results in poor statistical
> > practice.  The defaults in dialog boxes are not very good in some cases,
> > and like SAS, SPSS tends to lead users to make to many assumptions
> > (linearity in regression being one of the key ones).
> > -- 
> > Frank E Harrell Jr   Professor and Chair           School of Medicine
> >                       Department of Biostatistics   Vanderbilt
University
> >
> > ______________________________________________
> >
> My worry about SPSS is that it encourages people to do analysis and
> dataset manipulation 'on-the-fly', without leaving behind an audit trail
> that can be used to reconstruct the dataset and results. Certainly, SPSS
> has a 'paste' button which allows you to save a 'syntax' file of
> commands, but most users appear to ignore it. And post-hoc editing of
> graphs and tables cannot be saved thus (unless I'm missing out something
> here).

Hear hear! I found that using SPSS left me knee-deep in un-documented
'intermediate datasets' and graphs I couldn't reproduce unless I spent an
age fiddling. And as for auto-labelled graph axes running from eg. -0.5-6.5
by units of 2, when I'd rather prefer 0-10... ugh, the memories are not
good. And if I see one more dissertation with dense, graphics-rich but
almost unreadable SPSS tables that have clearly just not been thought out...

For me it's not about features, it is the sloppy working styles SPSS
encourages. Take off the GUI and it's probably not too bad(!).

Stuart


This message has been scanned but we cannot guarantee that it and any
attachments are free from viruses or other damaging content: you are
advised to perform your own checks.  Email communications with the
University of Nottingham may be monitored as permitted by UK legislation.