Concept information
Terme préférentiel
weighted least squares
Définition
- Weighted least squares (WLS) is a standard compensation technique for nonconstant error variance (heteroscedasticity), which is common in political science data. By assigning individual weights to the observations the heteroscedasticity can be removed by design. [Source: International Encyclopedia of Political Science; Weighted Least Squares]
Concept générique
Appartient au groupe
URI
http://data.loterre.fr/ark:/67375/N9J-X36FJ51X-T
{{label}}
{{#each values }} {{! loop through ConceptPropertyValue objects }}
{{#if prefLabel }}
{{/if}}
{{/each}}
{{#if notation }}{{ notation }} {{/if}}{{ prefLabel }}
{{#ifDifferentLabelLang lang }} ({{ lang }}){{/ifDifferentLabelLang}}
{{#if vocabName }}
{{ vocabName }}
{{/if}}