Mathematics/Statistics/Normalization - Revision history

Brodriguez: Brodriguez moved page Statistics/Normalization to Mathematics/Statistics/Normalization

2020-10-25T17:21:13Z

Brodriguez moved page Statistics/Normalization to Mathematics/Statistics/Normalization

← Older revision

Revision as of 17:21, 25 October 2020

Brodriguez: Add video reference

2020-05-18T13:23:00Z

Add video reference

← Older revision		Revision as of 13:23, 18 May 2020
Line 35:		Line 35:
	* <math>\bar{x}</math> is the attribute [[Statistics/Core_Measurements#Mean\|mean]].		* <math>\bar{x}</math> is the attribute [[Statistics/Core_Measurements#Mean\|mean]].
	* <math>\sigma</math> is the attribute [[Statistics/Core_Measurements#Standard Deviation\|standard deviation]].		* <math>\sigma</math> is the attribute [[Statistics/Core_Measurements#Standard Deviation\|standard deviation]].


			For further explanation, see [https://youtu.be/5S-Zfa-vOXs this youtube video].


	== Normalization by Decimal Scaling ==		== Normalization by Decimal Scaling ==
	{{ ToDo \| Fill in section. }}		{{ ToDo \| Fill in section. }}

Brodriguez: Add a line

2020-05-18T13:18:50Z

Add a line

← Older revision		Revision as of 13:18, 18 May 2020
Line 26:		Line 26:
	Also known as "z-score normalization".		Also known as "z-score normalization".

	Zero-Mean Normalization normalizes attribute values based on the mean and standard deviation.		Zero-Mean Normalization normalizes attribute values based on the mean and standard deviation.<br>
			In other words, this calculates how many standard deviations a value is above or below the mean.

	<math>new\_value = \frac{old\_value - \bar{x}}{\sigma}</math>		<math>new\_value = \frac{old\_value - \bar{x}}{\sigma}</math>

Brodriguez: Add normalization methods

2020-05-17T14:51:23Z

Add normalization methods

← Older revision		Revision as of 14:51, 17 May 2020
Line 5:		Line 5:

	For example, if trying to run analysis with "weight" and "height" attributes for a population of individuals, the unit of measurement used will implicitly change how much importance each attribute has in the analysis. Alternatively, we can normalize them both to a range between [0, 1], so that both attributes have equal importance in analysis, regardless of units of measurement.		For example, if trying to run analysis with "weight" and "height" attributes for a population of individuals, the unit of measurement used will implicitly change how much importance each attribute has in the analysis. Alternatively, we can normalize them both to a range between [0, 1], so that both attributes have equal importance in analysis, regardless of units of measurement.

			Below are some common normalization types.

			== Min-Max Normalization ==
			Min-max normalization is a form of simple linear transformation, where values are simply scaled down to the desired interval.

			{{ Warn \| This form of normalization will result in errors if a value added at a later date falls outside of the original data range. In such a case, it's important to re-normalize the entire dataset, using the original data.}}

			<math>new\_value = \frac{old\_value - old\_min}{old\_max - old\_min} ( new\_max - new\_min ) + new\_min</math>

			Where:
			* <math>old\_value</math> is the original value of the item to adjust.
			* <math>old\_min</math> is the original [[Statistics/Data_Characteristics#Min\|minimum]] of the given attribute.
			* <math>old\_max</math> is the original [[Statistics/Data_Characteristics#Max\|maximum]] of the given attribute.
			* <math>new\_min</math> is the new [[Statistics/Data_Characteristics#Min\|minimum]] to use for the given attribute.
			* <math>new\_max</math> is the new [[Statistics/Data_Characteristics#Max\|maximum]] to use for the given attribute.


			== Zero-Mean Normalization ==
			Also known as "z-score normalization".

			Zero-Mean Normalization normalizes attribute values based on the mean and standard deviation.

			<math>new\_value = \frac{old\_value - \bar{x}}{\sigma}</math>

			Where:
			* <math>old\_value</math> is the original value of the individual dataset item to adjust.
			* <math>\bar{x}</math> is the attribute [[Statistics/Core_Measurements#Mean\|mean]].
			* <math>\sigma</math> is the attribute [[Statistics/Core_Measurements#Standard Deviation\|standard deviation]].


			== Normalization by Decimal Scaling ==
			{{ ToDo \| Fill in section. }}

Brodriguez: Create page

2020-05-17T14:36:10Z

Create page

New page

Normalization is a method to make values fall within a "common range".<br>
For example, in Data Mining and Neural Networks, it's common to normalize values so that they fall into the (inclusive) range of [-1, 1] or [0, 1].

Normalization keeps the ratio of values in an attribute, while ensuring that no single attribute has a significantly larger range than the others. Discrepancy in the ranges an attribute spans may cause one attribute to have more weight (and thus importance) in statistical analysis than other attributes, even when no such correlation should otherwise be expected to exist.

For example, if trying to run analysis with "weight" and "height" attributes for a population of individuals, the unit of measurement used will implicitly change how much importance each attribute has in the analysis. Alternatively, we can normalize them both to a range between [0, 1], so that both attributes have equal importance in analysis, regardless of units of measurement.