Thank you, Dave Karoly

for your post on 2/19 on using Star*Net. The data contained Star*Net's output answered a question I asked back in January about calculating standard errors for distances.

The first distance (5014.4200) and its standard error (0.0076) verify that Star*Net adds the constant term to the product of the variable term and the distance rather than taking the square root of the sum of the squares of those two components. Of course, the same thing is true for the other entries as well.

Including the assumptions about positioning errors for the instrument and the target, the math goes like this:

Std. Err. = sqrt((0.0025 + 5014.4200/1000000)^2 + (0.001)^2 + (0.001)^2) = 0.007646.

So, from one end of Interstate 40 to sort of the other, thank you for publishing all of the data.