Are two population variances proportional if one population is derived from overlapping subsets of the other population?

by xb4rrm27m5   Last Updated May 15, 2019 18:19 PM

Given:

  • Crashes are rare, random-events, Poisson distribution
  • Crashes are located spatially (resolution 0.1mi) along a roadway that's segmented

E.g.

I want to calculate mean and variance of crash observations per segment normalized by segment length.

If I create a second population derived from the first, by creating overlapping windows of equal length to create a new set of segments, will mean and variance be proportional to original population?

E.g.

Visualization of data and windowed segmenting

Tags : variance


Related Questions


Estimating the variance of a sum of predictions

Updated April 10, 2015 19:08 PM

What is "Entropic Capacity"?

Updated July 26, 2018 16:19 PM