Outliers and comparing two data sets
Compare two classes' standing long jumps using an average and the range, drag one value far out and watch the mean, median and range react, and decide whether an outlier is a mistake or real.
- UK: Year 8
- France: grade 10
- Germany: grade 7
- Iran: grade 11
- Afghanistan: grade 10
- Russia: grade 7
Guide
This studio follows KS3 Statistics: "compare observed distributions … using measures of central tendency … and spread (range, consideration of outliers)".
To compare two data sets, say two things: an average (such as the median), which tells you where the values usually are, and a measure of spread (such as the range), which tells you how spread out they are. One on its own is not enough.
More spread means the values are less consistent; whether that is "better" or "worse" depends on the situation.
An outlier is a value far away from the rest. It pulls the mean towards it but hardly moves the median. We only leave an outlier out when there is a reason to think it is a mistake; if it is real, we keep it.
Ask: "Could this value be real? How could we find out?"