# What is difference between detrend and normalization? [closed]

matlab function detrend subtracts the mean from data. If data contains several data columns, detrend treats each data column separately.

One of the normalization technique is subtracting the mean and dividing it by standard deviation.

Since the normalization already subtract the mean from the data, in such case, is it essential to perform (before or after) detrend operation?

What is the significance of each operation?

## closed as unclear what you're asking by Spacedman, Aditya, Toros91, Siong Thye Goh, TwinPenguinsApr 20 '18 at 8:23

Please clarify your specific problem or add additional details to highlight exactly what you need. As it's currently written, it’s hard to tell exactly what you're asking. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.

• Is that what the documentation says? Detrending would more likely be subtracting a straight line fit from the data - removing any increasing or decreasing linear trend - whereas normalisation is a scale and a shift so that the data has mean 0 and sd 1. What does the documentation say? What happens to data when you run these things? Do some experiments with some data. Read the documentation. – Spacedman Apr 17 '18 at 16:03

You detrend data in order to get rid of the linear trend in your data, which might cause spurious regression, misleading evidence that there is some relation between variables.
Normalization means adjusting values measured on different scales to a notionally common scale. Example you give: Standard score $\frac{X - \mu}{\sigma}$ is just one possible method of normalization . It allows you to see where value lies in comparison to mean.
In my experience you would only detrend data in order to create time series model. On the other hand, normalization is frequently used to compare previously not comparable statistics or detect anomalies (in case of standard score). As a result, usage really depends on the use case and you rarely use both at the same time.