C++ API Reference for Intel® Data Analytics Acceleration Library 2020 Update 1

Namespaces | Enumerations
daal::algorithms::linear_regression::quality_metric::group_of_betas Namespace Reference

Contains classes for computing linear regression quality metrics for group of betas.

Namespaces

 interface1
 Contains version 1.0 of the Intel(R) Data Analytics Acceleration Library (Intel(R) DAAL) interface.
 

Enumerations

enum  Method { defaultDense = 0 }
 
enum  DataInputId { expectedResponses, predictedResponses, predictedReducedModelResponses }
 Available identifiers of input objects for a group of betas quality metrics. More...
 
enum  ResultId {
  expectedMeans, expectedVariance, regSS, resSS,
  tSS, determinationCoeff, fStatistics
}
 Available identifiers of the result of a group of betas quality metrics. More...
 

Enumeration Type Documentation

Enumerator
expectedResponses 

NumericTable n x k. Expected responses (Y), dependent variables

predictedResponses 

NumericTable n x k. Predicted responses (Z)

predictedReducedModelResponses 

NumericTable n x k. Responses predicted by reduced model where p - p0 of p betas are set to zero

enum Method

Available methods for computing the quality metrics for a group of beta coefficients

Enumerator
defaultDense 

Default method

enum ResultId

Enumerator
expectedMeans 

NumericTable 1 x k. Means of expected responses computed for each dependent variable

expectedVariance 

NumericTable 1 x k. Variance of expected responses computed for each dependent variable

regSS 

NumericTable 1 x k. Regression sum of squares computed for each dependent variable

resSS 

NumericTable 1 x k. Sum of squares of residuals computed for each dependent variable

tSS 

NumericTable 1 x k. Total sum of squares of residuals computed for each dependent variable

determinationCoeff 

NumericTable 1 x k. Determination coefficient computed for each dependent variable

fStatistics 

NumericTable 1 x k. F-statistics computed for each dependent variable

For more complete information about compiler optimizations, see our Optimization Notice.