Bruce
That's what happens when you let the computer
scientists, statitsticians and beancounters take over something originally
produced by social researchers (in SPSS's case, graduate political science
students). The rot started after the final design conference I organised
at LSE in 1974 for the new SPSS: the disastrous demo at the later Novotel launch
by Major Lester (which Jim Ring and I had to rescue) confirmed our worst
fears. SPSS had been well and truly kidnapped by aliens!
corr ..../pri nos.
...used to produce a matrix with asterisks, but no
sig or n. Useful check for deriving attitude scales and the
like. Elementary linkage analysis (McQuitty, manually on the matrix) saved
a lot of paper and time and the rough-and-ready approach was just as good as
factor analysis, cluster analysis and and all that.
As Tukey once said, "All the statistics in the
world won't save you if you asked the wrong question in the first place."
Think I'll stick to social science.
John
PS I hope SPSS let me keep my academic author
status! I can't afford to pay for my licence.
Locked
