In Reply.—The letter from Dr Stickler addresses two issues: (1) extrapolation of growth patterns from too short observation periods; and (2) use of z scores to document the growth observed in a child, as sequential measurements are examined. There is universal agreement among authorities in biometry that the data analyst should not draw inferences or make predictions outside the boundaries of the observed values. Growth observed for only a few months should not be used to estimate expected growth over a full year.
The use of z scores for evaluating growth status is less universally accepted. A z score is a concise way to express the distance of a particular value from the mean of a normally distributed set of values. A z score of "+ 1" is 1 SD above the mean; a z score of − 1.5 is 1.5 SDs below the mean. This tidy notation has appeal because of