Design and analysis General considerations

Data collected in experiments, surveys, case smdies, and historical investigations may be quaUtative or quantitative, each data form requiring consideration and selection of potential analysis procedures. Data differ in quaUty, and the range of statistical tests which are appropriate needs to be determined prior to data collection (Tables 1.1 and 1.2). 

Nominal or categorical When numbers or other symbols are used to classify an object, person or characteristic, measurement is at its weakest. Also known as classificatory scale, eg, classifying items 

Ordinal or rank Where objects in one category are not only different from those in other categories but also stand in some kind of relation to them, eg, grades in assessment A B C 

Interval This scale has the characteristics of an ordinal scale, and the distance or difference between two numbers has meaning, eg, temperature 

Ratio This scale has the characteristics of an interval scale, and has a true zero point as its origin, eg, weight 

---