So – in response to a tweet from @DocNadine Archi will be attempting to do a series of short posts on some ‘stats’ things. What would you like to see covered?

A short and simple one today. Continuous vs. Categorical

Categorical variables, aka discrete variables. These come in only a fixed number of values – like dead/alive, obese/overweight/normal/underweight, Apgar score.

Continuous variables. These can have any value between a theoretical minimum and maximum, like birth weight, BMI, temperature, neutrophil count.

You spotted the Apgar score, yes? Why’s this number not a continuous variable? Well, I tend to think a) if its continuous, then double the number = twice as much (e.g. 2kg baby vs 4kg baby – not the case with Apgar 5 vs Apgar 10) and b) you can get any number from a continuous variable (like 2.456kg, unlike Apgar 3, 4, 5 …)

You need to work out the difference because it dictates what statistical tests you should be thinking about using … mostly …

– Archi

(ps – Some statisticians call categorical data ‘qualitative’ and continuous data ‘quantitative’ just to add an extra layer of confusion)

(pps – I initially thought it was @TessaRDavis who triggered these thoughts. I’ve corrected it now. But @TessaRDavis I’m sure will be joining in with some ideas for future topics ..?)