Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision Both sides next revision
development:zscores [2018/10/21 15:20]
42.49.180.224 old revision restored (2010/02/25 15:48)
development:zscores [2017/08/17 11:21] (current)
127.0.0.1 external edit
Line 1: Line 1:
 +<note warning>
 +The purpose of this page is just to serve as todo or scratch pad for the development project and to list and share some ideas. ​
 +
 +After making changes to the code and/or documentation,​ this page should remain on the wiki as a reminder of what was done and how it was done. However, there is no guarantee that this page is updated in the end to reflect the final state of the project
 +
 +So chances are that this page is considerably outdated and irrelevant. The notes here might not reflect the current state of the code, and you should **not use this as serious documentation**.
 +</​note>​
 +
 ====== What is the best way to homogenize data? ====== ====== What is the best way to homogenize data? ======
 Z-scores are being used as a means to '​normalize'​ the data before doing over-subjects statistics. However, there are many ways of implementing this and at the moment there is not much consensus what the best method is. Z-scores are being used as a means to '​normalize'​ the data before doing over-subjects statistics. However, there are many ways of implementing this and at the moment there is not much consensus what the best method is.
Line 47: Line 55:
  
  
-//--&​gt; ​Problem: these solutions may introduce additional noise!//+//--Problem: these solutions may introduce additional noise!//
  
  
Line 119: Line 127:
  
 The data should be of the form: The data should be of the form:
-&lt;code&gt;+<code>
   baseline ​  = phys           + noise   baseline ​  = phys           + noise
   activation = phys * e1 + e2 + noise   activation = phys * e1 + e2 + noise
-&lt;/code&gt;+</code>
  
-  * with for the additive effect model: e1 = 1, e2 &​gt; ​0, and for the multiplicative effect model: e1 &​gt; ​1, e2 = 0.+  * with for the additive effect model: e1 = 1, e2 0, and for the multiplicative effect model: e1 1, e2 = 0.
   * phys is the physiological signal, consisting of a '​constant'​ (e.g. alpha oscillation) modulated by a slow drift   * phys is the physiological signal, consisting of a '​constant'​ (e.g. alpha oscillation) modulated by a slow drift
   * noise is the '​real'​ external noise, which is random   * noise is the '​real'​ external noise, which is random
  
-&lt;code&gt;+<code>
 phys  = phys_constant + phys_noise * lambda_phys phys  = phys_constant + phys_noise * lambda_phys
 noise = random_noise ​ * lambda_ext noise = random_noise ​ * lambda_ext
-&lt;/code&gt;+</code>
  
   * lambda_phys and lambda_ext are scaling factors for the physiological and external noise, resp.   * lambda_phys and lambda_ext are scaling factors for the physiological and external noise, resp.