mondrian.olap.fun
Class LinReg

java.lang.Object
  org.eigenbase.xom.XMLUtil
      org.eigenbase.xom.XOMUtil
          mondrian.olap.Util
              mondrian.olap.fun.FunUtil
                  mondrian.olap.fun.FunDefBase
                      mondrian.olap.fun.LinReg

All Implemented Interfaces:

FunDef

Direct Known Subclasses:

LinReg.InterceptFunDef, LinReg.PointFunDef, LinReg.R2FunDef, LinReg.SlopeFunDef, LinReg.VarianceFunDef

public abstract class LinReg
extends FunDefBase

Abstract base class for definitions of linear regression functions.

See Also:

LinReg.InterceptFunDef, LinReg.PointFunDef, LinReg.R2FunDef, LinReg.SlopeFunDef,

Correlation coefficient

Correlation coefficient

The correlation coefficient, r, ranges from -1 to + 1. The nonparametric Spearman correlation coefficient, abbreviated rs, has the same range.

Value of r (or rs)	Interpretation
r= 0	The two variables do not vary together at all.
0 > r > 1	The two variables tend to increase or decrease together.
r = 1.0	Perfect correlation.
-1 > r > 0	One variable increases as the other decreases.
r = -1.0	Perfect negative or inverse correlation.

If r or rs is far from zero, there are four possible explanations:

The X variable helps determine the value of the Y variable.

• The Y variable helps determine the value of the X variable.
• Another variable influences both X and Y.
• X and Y don't really correlate at all, and you just happened to observe such a strong correlation by chance. The P value determines how often this could occur.

r2

Perhaps the best way to interpret the value of r is to square it to calculate r2. Statisticians call this quantity the coefficient of determination, but scientists call it r squared. It is has a value that ranges from zero to one, and is the fraction of the variance in the two variables that is shared. For example, if r2=0.59, then 59% of the variance in X can be explained by variation in Y. Likewise, 59% of the variance in Y can be explained by (or goes along with) variation in X. More simply, 59% of the variance is shared between X and Y.

(Source).

Also see: least squares fitting.

Nested Class Summary

static class	LinReg.InterceptFunDef Definition of the LinRegIntercept MDX function.
static class	LinReg.PointFunDef Definition of the LinRegPoint MDX function.
static class	LinReg.R2FunDef Definition of the LinRegR2 MDX function.
static class	LinReg.SlopeFunDef Definition of the LinRegSlope MDX function.
(package private) static class	LinReg.Value
static class	LinReg.VarianceFunDef Definition of the LinRegVariance MDX function.

Nested classes/interfaces inherited from class mondrian.olap.fun.FunUtil

FunUtil.SetWrapper

Nested classes/interfaces inherited from class mondrian.olap.Util

Util.ErrorCellValue, Util.PropertyList

Field Summary

static int	Intercept
(package private) static Resolver	InterceptResolver
static int	Point
(package private) static Resolver	PointResolver
static int	R2
(package private) static Resolver	R2Resolver
(package private) int	regType Code for the specific function.
static int	Slope
(package private) static Resolver	SlopeResolver
static int	Variance
(package private) static Resolver	VarianceResolver

Fields inherited from class mondrian.olap.fun.FunDefBase

flags, parameterCategories, returnCategory, signature

Fields inherited from class mondrian.olap.fun.FunUtil

BooleanNull, DoubleEmpty, DoubleNull, emptyStringArray, IntegerNull, NullMember

Fields inherited from class mondrian.olap.Util

EmptyValue, JdbcVersion, nl, nullValue, PreJdk15, Retrowoven

Constructor Summary

protected

LinReg(FunDef funDef, int regType)

Method Summary

static LinReg.Value	accuracy(LinReg.Value value)
Calc	compileCall(ResolvedFunCall call, ExpCompiler compiler) Converts a call to this function into executable objects.
protected static void	debug(String type, String msg)
static List	forecast(LinReg.Value value)
static LinReg.Value	linearReg(List xlist, List ylist)
protected static LinReg.Value	process(Evaluator evaluator, ListCalc listCalc, DoubleCalc yCalc, DoubleCalc xCalc, boolean isTuples)

Methods inherited from class mondrian.olap.fun.FunDefBase

castType, createCall, getDescription, getName, getParameterCategories, getResultType, getReturnCategory, getSignature, getSyntax, unparse, validateArg

Methods inherited from class mondrian.olap.fun.FunUtil

addMembers, addMembers, addUnique, ancestor, appendTuple, avg, checkCompatible, checkFlag, checkIterListResultStyles, checkListResultStyles, compareHierarchically, compareSiblingMembers, compareValues, compareValues, compareValues, correlation, count, cousin, covariance, createDummyFunDef, decodeCategory, decodeParameterCategories, decodeReturnCategory, decodeSyntacticType, dimensionMembers, equalTuple, evaluateMembers, evaluateMembers, evaluateSet, evaluateSet, evaluateTuples, getLiteralArg, getLiteralArg, getNonEmptyLevelMembers, getNonEmptyMemberChildren, hierarchize, hierarchyMembers, isAncestorOf, isMemberType, levelMembers, makeNullMember, makeNullTuple, max, memberRange, min, newEvalException, newEvalException, percentile, periodsToDate, quartile, removeCalculatedMembers, resolveFunArgs, searchValuesDesc, sign, sortMembers, sortTuples, sortValuesDesc, stdev, sum, sumDouble, sumDouble, toPercent, tupleContainsNullMember, var

Methods inherited from class mondrian.olap.Util

addDatabaseTime, addLevelCalculatedMembers, areOccurencesEqual, assertPostcondition, assertPostcondition, assertPrecondition, assertPrecondition, assertTrue, assertTrue, badValue, camelToUpper, caseSensitiveCompareName, cast, cast, checkCJResultLimit, commaList, compareKey, compareName, convertStackToString, createExpr, createRandom, createSimpleValidator, createUdf, dbTimeMillis, deprecated, enumSetAllOf, enumSetNoneOf, enumSetOf, equal, equalName, equals, equals, getAnnotation, getErrorMessage, getErrorMessage, getFirstDescendantOnLevel, getMemberOrdinalInParent, hash, hash, hashArray, implode, isEmpty, isNull, isSorted, isValidProperty, lookup, lookup, lookup, lookup, lookupCompound, lookupCompound, lookupHierarchyLevel, lookupHierarchyRootMember, lookupHierarchyRootMember, lookupProperty, makeBigDecimalFromDouble, makeFqName, makeFqName, makeFqName, maskVersion, mdxEncodeString, needToImplement, newError, newError, newInternal, newInternal, nonDbTimeMillis, normalizeName, parseCommaList, parseConnectString, parseIdentifier, printMemory, printMemory, quoteForMdx, quoteMdxIdentifier, quoteMdxIdentifier, quoteMdxIdentifier, quoteMdxIdentifier, quotePattern, readFully, readURL, readURL, readURL, readURL, replace, replace, replaceProperties, singleQuoteString, singleQuoteString, toMap, toURL, unexpected, union, union, uniquify, unparse, unparse, wildcardToRegexp

Methods inherited from class org.eigenbase.xom.XOMUtil

addAll, addAll, addChild, addChild, addChildren, addElement, concatenate, createDefaultParser, discard, discard, discard, discard, discard, discard, discard, discard, discard, getFirstInstance, toList, toVector, wrapperToXml

Methods inherited from class org.eigenbase.xom.XMLUtil

getFirstTagName, printAtt, printAtt, printAtt, printAtt, printPCDATA, printPCDATA, printPCDATA, quoteAtt, quoteAtt, quoteAtt, quoteAtt, quotePCDATA, stringEncodeXML, stringHasXMLSpecials

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

regType

final int regType

Code for the specific function.

Point

public static final int Point

See Also:

Constant Field Values

R2

public static final int R2

See Also:

Constant Field Values

Intercept

public static final int Intercept

See Also:

Constant Field Values

Slope

public static final int Slope

See Also:

Constant Field Values

Variance

public static final int Variance

See Also:

Constant Field Values

InterceptResolver

static final Resolver InterceptResolver

PointResolver

static final Resolver PointResolver

SlopeResolver

static final Resolver SlopeResolver

R2Resolver

static final Resolver R2Resolver

VarianceResolver

static final Resolver VarianceResolver

Constructor Detail

LinReg

protected LinReg(FunDef funDef,
                 int regType)

Method Detail

compileCall

public Calc compileCall(ResolvedFunCall call,
                        ExpCompiler compiler)

Description copied from interface: FunDef

Converts a call to this function into executable objects.

The result must implement the appropriate interface for the result type. For example, a function which returns an integer must return an object which implements IntegerCalc.

Specified by:

compileCall in interface FunDef

Overrides:

compileCall in class FunDefBase

debug

protected static void debug(String type,
                            String msg)

process

protected static LinReg.Value process(Evaluator evaluator,
                                      ListCalc listCalc,
                                      DoubleCalc yCalc,
                                      DoubleCalc xCalc,
                                      boolean isTuples)

accuracy

public static LinReg.Value accuracy(LinReg.Value value)

linearReg

public static LinReg.Value linearReg(List xlist,
                                     List ylist)

forecast

public static List forecast(LinReg.Value value)