Is there a calculation or test to determine if the occurrence of a surname in a population in a specific geographical area is statistically significant or just a random distribution?

For example, in a surname study of the most common 42 surnames in a geographic region, the surname Steele occurs 3249 times (3rd most common). The total number of families reporting a surname in the top 42 most common is 79408 and the total population in the geographic region is 119000. Obviously, 3249/119000*100= 2.71% of the population have the Steele surname, but is this statistically significant in population studies?


1 Answer 1


The importance of a fact that 2.71% of a population in a region has a specific surname depends on how many people have that surname worldwide. It will be more important if 1,000 people have it worldwide than if a million do.

What might be better to determine the importance of the region to your family would be to look at the worldwide distribution of the surname through sites that provide Surname Distribution Analysis, such as Harry Wykes' site or Nathan Murphy's site. If a lot of a surname comes from a region, then it will help isolate where the family originated.

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.