Finding standard deviation or error from normalized data.


by doublemint
Tags: data, deviation, error, normalized, standard
doublemint
doublemint is offline
#1
Sep26-11, 07:04 PM
P: 142
Hello All,

I am trying to figure out how to find the standard deviation or error in sets of data. So lets say I have sets x1, x2, x3 and x4 with various values and I found the average and standard deviations for it. Now I have to take the averages, lets say a1, a2, a3, a4, and normalize a2,a3,a4 to a1. Now how do I find the standard deviation or error in the normalized sets? Forgive my ignorance, but I am suppose to do this for a project and I have never taken any stats course before..

Thanks
DoubleMint
Phys.Org News Partner Science news on Phys.org
Cougars' diverse diet helped them survive the Pleistocene mass extinction
Cyber risks can cause disruption on scale of 2008 crisis, study says
Mantis shrimp stronger than airplanes
Stephen Tashi
Stephen Tashi is offline
#2
Sep28-11, 03:20 AM
Sci Advisor
P: 3,175
What do you mean by "normalize"? For example, do you mean that multiply each datum in the data set x2 by the factor (a2/a1) ?

Let the data be the [itex] d_i [/itex]. Let the sample mean be [itex] m[/itex] . Let the scaling factor be [itex] k [/itex]

The mean of the scaled data [itex] k d_i [/itex] is [itex] m k [/itex]

The variance of the scaled data is:

[itex] \sum \frac { ( k d_i - m k )^2}{n} = \sum \frac{k^2 (d_i - k)^2 }{n} = k^2 \sum \frac{(d_i - m)^2}{n} [/itex]

This is [itex] k^2 [/itex] times the variance of the original sample.

So the sample standard deviation of the scaled data is [itex] |k| [/itex] times the standard deviation of the original data.


Register to reply

Related Discussions
Standard deviation of aggregated data Set Theory, Logic, Probability, Statistics 3
Error to standard deviation General Physics 5
Changing standard error to standard deviation. Set Theory, Logic, Probability, Statistics 1
Standard deviation of root mean square error Set Theory, Logic, Probability, Statistics 2
Standard deviation of weighted data Precalculus Mathematics Homework 4