weighted mean

Home > Statistics Every Writer Should Know > The Stats Board > Discusssion

weighted mean
Message posted by aileen (via 80.192.228.110) on February 7, 2002 at 12:15 PM (ET)

What is the weighted mean?

READERS RESPOND:
(In chronological order. Most recent at the bottom.)

Re: weighted mean
Message posted by JG (via 64.12.103.34) on February 7, 2002 at 6:06 PM (ET)

Each oservation is given a weight - w(i) - with the sum of the weights being 1. An example of this is the mean calculation for grouped data, where w(i) are the relative frequencies.

Re: weighted mean
Message posted by Darius (via 200.23.217.10) on February 7, 2002 at 6:42 PM (ET)

It愀 OK, for the formula:

Weighted_Value= Sum[Weight(i) * Val(i)]

but the sum of the weights could be different from 1 if you use the formula:

Weighted_Value= Sum[Weight(i) * Val(i)]/Sum[Weights]

Weights could be used for Survey data if you want a statistical parameter for the total population.

Weights could be used to determine a value in an interpolation like situation, you have the value at 2:90 and at 3:05 but you need the value at 3:00, the weight of the value = abs(time_determination - time[i])

Your $5 contribution helps cover part the $500 annual cost of keeping this site online.