The market basket of techniques boils down to what Dr. Deming called 'enumerative or analytic studies.' Broadly speaking the focus of enumerative studies is to describe a sample or population in some fashion. So generally, for enumerative studies, you are talking about either descriptive statistics (yuk) and their inferential brethren (confidence intervals etc.) or graphical methods where the focus is usually on answering these types of questions:
1. Where's the middle?
2. How spread out is the data?
3. What's the shape look like?
4. How does the data vary over time?
For analytic studies the focus is on prediction. So now modeling techniques prevail.
In either case I encourage using are what I call Peter Bartell's "Three Rules for Data Analysis"...
1. plot the data.
2. Plot The Data.
3. PLOT THE Data.
Now for the disclaimer...as one who for many, many years in industry/business that was at the forefront of either creating KPIs or analyzing them...beware. As Lloyd Nelson was also fond of saying...something along the lines of...""The most important figures that one needs for management are unknown or unknowable, but successful management must nevertheless take account of them." So why people get all worked up over KPIs was always beyond me,
