A brief and personal overview is given of developments in matrix algebra,
statistics and computing during the years of my participating in these activities,
1945 2005.
Data Mining is relatively new in the field of statistics, although widely used elsewhere. Is it a good idea
to discard the model-based methods in favour of Data Driven methods? Data driven methods produce a
high degree of accuracy, but very little interpretability. Model based methods are interpretable, but lack
accuracy. Data mining techniques are commonly used where the data collection has been automated. I
will show these methods are also useful in the large survey setting.
