Cross Validated is a question and answer site for people interested in statistics, machine learning, data analysis, data mining, and data visualization. It only takes a minute to sign up.
Sign up to join this community
This is a general question on normalization of data so that all the variables are within the same range.
Why do we normalize data in pattern classification?
How to normalize time series which is multivariate? I have collected motion time series from Kinect skeleton tracking. In general, what is the process of normalization when the features are the joint angles, x,y,z coordinate of the pixel and in cases of features say flower width, size, color ?
Normalization isn't always necessary. We use it with certain methods (such as Principal Component Analysis) because otherwise, the values that have a larger scale will be given an increased weight. Here's a discussion of why normalization is necessary within the PCA context -- the same basic argument applies to other techniques that are sensitive to scale: Why do we need to normalize data before analysis
It would depend on what your intention was with the normalization, and what type of analysis you intended to do. Feature scaling is a pretty common normalization technique, and what I usually default to unless there is a reason to attempt another technique. You can read about other normalization techniques here: http://en.wikipedia.org/wiki/Normalization_(statistics).
