Linear Regression

GPTKB entity

Statements (50)
Predicate Object
gptkbp:instanceOf statistical analysis
gptkbp:assesses gptkb:Mean_Squared_Error
gptkb:Root_Mean_Squared_Error
R-squared
Adjusted R-squared
gptkbp:assumes Linearity
Homoscedasticity
Independence of errors
Normality of errors
gptkbp:category Supervised Learning
Parametric Model
Regression Model
gptkbp:detects gptkb:Outliers
Collinearity
Influential Points
gptkbp:estimatedCost Relationship between variables
gptkbp:fittedBy gptkb:Ordinary_Least_Squares
Gradient Descent
gptkbp:hasEquation y = β0 + β1x + ε
gptkbp:hasType Multiple Linear Regression
Simple Linear Regression
https://www.w3.org/2000/01/rdf-schema#label Linear Regression
gptkbp:implementedIn gptkb:Python
gptkb:SAS
gptkb:MATLAB
gptkb:SPSS
gptkb:Excel
R
gptkbp:input One or more Independent Variables
gptkbp:introduced gptkb:Francis_Galton
gptkb:Karl_Pearson
gptkbp:limitation Sensitive to Outliers
Cannot model non-linear relationships without transformation
Affected by Multicollinearity
Assumes Linear Relationship
Assumes no autocorrelation in errors
gptkbp:output Continuous Variable
gptkbp:reduces Sum of Squared Errors
gptkbp:relatedTo gptkb:Lasso_Regression
gptkb:Polynomial_Regression
gptkb:Ridge_Regression
Logistic Regression
gptkbp:requires Quantitative Variables
gptkbp:usedFor Regression Analysis
Predictive Modeling
gptkbp:usedIn gptkb:Machine_Learning
gptkb:Data_Science
Statistics
gptkbp:bfsParent gptkb:Linear_Model
gptkbp:bfsLayer 5