Represents an Analysis of Variance (ANOVA) model.
SystemObject Extreme.DataAnalysis.ModelsModel Extreme.StatisticsAnovaModel Extreme.StatisticsOneWayAnovaModel Extreme.StatisticsOneWayRAnovaModel Extreme.StatisticsTwoWayAnovaModel
Namespace:
Extreme.Statistics
Assembly:
Extreme.Numerics (in Extreme.Numerics.dll) Version: 8.1.1
public abstract class AnovaModel : Model
Public MustInherit Class AnovaModel
Inherits Model
public ref class AnovaModel abstract : public Model
[<AbstractClassAttribute>]
type AnovaModel =
class
inherit Model
end
The AnovaModel type exposes the following members.
Top
| Name | Description |
---|
 | AdjustedRSquared |
Gets the adjusted R Squared value for the regression.
|
 | AnovaTable |
Gets the AnovaTable that summarizes the results of this model.
|
 | BaseFeatureIndex |
Gets an index containing the keys of the columns
that are required inputs to the model.
(Inherited from Model.) |
 | Computed | Obsolete.
Gets whether the model has been computed.
(Inherited from Model.) |
 | CovarianceMatrix |
Gets the covariance matrix of the model parameters.
|
 | Data |
Gets an object that contains all the data used as input to the model.
(Inherited from Model.) |
 | DegreesOfFreedom |
Gets the total degrees of freedom of the data.
|
 | DependentVariable |
Gets or sets the dependent variable in the ANOVA model.
|
 | Fitted |
Gets whether the model has been computed.
(Inherited from Model.) |
 | FStatistic |
Gets the F statistic for the regression.
|
 | Grouping |
Gets the grouping object that maps observations to their cell.
|
 | InputSchema |
Gets the schema for the features used for fitting the model.
(Inherited from Model.) |
 | IsBalanced |
Gets whether all the cells in the ANOVA design have the
same number of observations.
|
 | LogLikelihood |
Gets the log-likelihood that the model generated the data.
|
 | MaxDegreeOfParallelism |
Gets or sets the maximum degree of parallelism enabled by this instance.
(Inherited from Model.) |
 | ModelSchema |
Gets the collection of variables used in the model.
(Inherited from Model.) |
 | NumberOfObservations |
Gets the number of observations the model is based on.
(Inherited from Model.) |
 | ObservationsPerCell |
Gets the number of observations per cell.
|
 | ParallelOptions |
Gets or sets an object that specifies how the calculation of the model should be parallelized.
(Inherited from Model.) |
 | Parameters |
Gets a vector containing the estimated values of the model parameters.
|
 | PValue |
Gets the probability corresponding to the F statistic for the regression.
|
 | RSquared |
Gets the R Squared value for the regression.
|
 | StandardError |
Gets the standard error of the regression.
|
 | Status |
Gets the status of the model, which determines which information is available.
(Inherited from Model.) |
 | SupportsWeights |
Indicates whether the model supports case weights.
(Inherited from Model.) |
 | Weights |
Gets or sets the actual weights.
(Inherited from Model.) |
Top
Top
The AnovaModel class is an abstract base class
for all classes that implement Analysis of Variance (ANOVA) models. It
inherits from RegressionModelT, and defines a number of additional properties
and methods useful in analysis of variance.
ANOVA models are a specialized form of regression model
whose independent variables or predictors are all categorical in nature.
The categorical scales are called factors.
Use the GetFactor(Int32) method to get the factor that corresponds
to a specific independent variable.
The Cells property returns a
vector or matrix of Cell objects.
There is one cell for every combination of factor levels.
The IsBalanced property indicates whether all cells
have the same number of observations.
One of the assumptions in analysis of variance is
that the variances of the data in each cell are the same.
The GetHomogeneityOfVariancesTest(TestOfHomogeneityOfVariances) returns
a hypothesis test object /// that allows you to verify this assumption.
This is an abstract base class, and cannot be instantiated directly.
Instead, use one of the derived classes listed in the following table.
Reference