I am running a 5 mile buffer analysis around a business location, with the objective to calculate the percent of high income earners ($200k+) within that buffer.

Normally, I would intersect the buffer with the surrounding census tracts and calculate a weighted sum for the percentage of high income earners.

But, in this scenario the business is located near the coastline, so about 40% of the 5 mile buffer intersects with ocean, and there is no census data.

This skews the weighted sum because now it includes a null value (a zero value). For example, the weighted sum is now (15% x 7%) + (25% x 5%) + (20% x 6.5%) + (40% x 0%) = 3.6% are high income earners.

3.6% is an incorrect calculation of high income earners. The real value is somewhere between 5% - 7%.

Is there a solution for this problem?

  • 3
    Can't you just clip the buffer to the coastline (or end of census data) and recalculate the area of the buffer (if necessary)? – jbchurchill Mar 20 '18 at 17:49
  • 1
    This can be a solution?: [(15% x 7%) + (25% x 5%) + (20% x 6.5%)] / (15%+25%+20%) = 6% – Kadir Şahbaz Mar 20 '18 at 19:58

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.