Interface UpdatingMultipleLinearRegression
-
- All Known Implementing Classes:
MillerUpdatingRegression,SimpleRegression
public interface UpdatingMultipleLinearRegression
An interface for regression models allowing for dynamic updating of the data. That is, the entire data set need not be loaded into memory. As observations become available, they can be added to the regression model and an updated estimate regression statistics can be calculated.- Since:
- 3.0
-
-
Method Summary
All Methods Instance Methods Abstract Methods Modifier and Type Method Description voidaddObservation(double[] x, double y)Adds one observation to the regression model.voidaddObservations(double[][] x, double[] y)Adds a series of observations to the regression model.voidclear()Clears internal buffers and resets the regression model.longgetN()Returns the number of observations added to the regression model.booleanhasIntercept()Returns true if a constant has been included false otherwise.RegressionResultsregress()Performs a regression on data present in buffers and outputs a RegressionResults object.RegressionResultsregress(int[] variablesToInclude)Performs a regression on data present in buffers including only regressors.
-
-
-
Method Detail
-
hasIntercept
boolean hasIntercept()
Returns true if a constant has been included false otherwise.- Returns:
- true if constant exists, false otherwise
-
getN
long getN()
Returns the number of observations added to the regression model.- Returns:
- Number of observations
-
addObservation
void addObservation(double[] x, double y) throws ModelSpecificationException
Adds one observation to the regression model.- Parameters:
x- the independent variables which form the design matrixy- the dependent or response variable- Throws:
ModelSpecificationException- if the length ofxdoes not equal the number of independent variables in the model
-
addObservations
void addObservations(double[][] x, double[] y) throws ModelSpecificationException
Adds a series of observations to the regression model. The lengths of x and y must be the same and x must be rectangular.- Parameters:
x- a series of observations on the independent variablesy- a series of observations on the dependent variable The length of x and y must be the same- Throws:
ModelSpecificationException- ifxis not rectangular, does not match the length ofyor does not contain sufficient data to estimate the model
-
clear
void clear()
Clears internal buffers and resets the regression model. This means all data and derived values are initialized
-
regress
RegressionResults regress() throws ModelSpecificationException, NoDataException
Performs a regression on data present in buffers and outputs a RegressionResults object.- Returns:
- RegressionResults acts as a container of regression output
- Throws:
ModelSpecificationException- if the model is not correctly specifiedNoDataException- if there is not sufficient data in the model to estimate the regression parameters
-
regress
RegressionResults regress(int[] variablesToInclude) throws ModelSpecificationException, MathIllegalArgumentException
Performs a regression on data present in buffers including only regressors. indexed in variablesToInclude and outputs a RegressionResults object- Parameters:
variablesToInclude- an array of indices of regressors to include- Returns:
- RegressionResults acts as a container of regression output
- Throws:
ModelSpecificationException- if the model is not correctly specifiedMathIllegalArgumentException- if the variablesToInclude array is null or zero length
-
-