The possibilities of calculating similarity based on ordinal characters are
evaluated by distinguishing subtypes of the ordinal scale. Multivariate an
alysis is most problematic when ordinal variables appear together with othe
r scale types in the data. This difficulty is solved by extending Gower's g
eneral coefficient of similarity to ordinal data types, facilitating cluste
r analysis and multidimensional scaling. Two alternatives, a non-metric and
a metric version, are offered. The modified formula implies that ordinal v
ariables are equally weighted with the others, and that partially and fully
ranked data are both applicable, due to the inherent standardisation proce
dure. A morphological data set derived for the moss genus Tortula illustrat
es the new approach.