Principal Component Analysis (PCA)

Principal Component Analysis (PCA) More...

Functions
int __stdcall	NDK_PCA_COMP (double **pXData, size_t nXSize, size_t nXVars, LPBYTE varMask, size_t nMaskLen, WORD standardize, WORD nCompIndex, WORD retType, double *retVal, size_t nOutSize)
	Returns statistics and fitted values for the i-th principal component.
int __stdcall	NDK_PCA_VAR (double **pXData, size_t nXSize, size_t nXVars, LPBYTE varMask, size_t nMaskLen, WORD standardize, WORD nVarIndex, WORD wMaxPC, WORD retType, double *retVal, size_t nOutSize)
	Returns stats or fitted values for the i-th variable using a subset of the principal components.
int __stdcall	NDK_PCR_PARAM (double **pXData, size_t nXSize, size_t nXVars, LPBYTE mask, size_t nMaskLen, double *pYData, size_t nYSize, double intercept, double alpha, WORD nRetType, WORD ParamIndex, double *retVal)
	Calculates the regression coefficient values for a given input variable.
int __stdcall	NDK_PCR_FORE (double **pXData, size_t nXSize, size_t nXVars, LPBYTE mask, size_t nMaskLen, double *pYData, size_t nYSize, double intercept, double *target, double alpha, WORD nRetType, double *retVal)
	Calculates the model's estimated values, standard errors, and related statistics.
int __stdcall	NDK_PCR_FITTED (double **pXData, size_t nXSize, size_t nXVars, LPBYTE mask, size_t nMaskLen, double *pYData, size_t nYSize, double intercept, WORD nRetType)
	Returns an array of the fitted values of the conditional mean, residuals or leverage measures.
int __stdcall	NDK_PCR_ANOVA (double **pXData, size_t nXSize, size_t nXVars, LPBYTE mask, size_t nMaskLen, double *pYData, size_t nYSize, double intercept, WORD nRetType, double *retVal)
	Calculates the regression model (of principal components) analysis of variance (ANOVA) values.
int __stdcall	NDK_PCR_GOF (double **pXData, size_t nXSize, size_t nXVars, LPBYTE mask, size_t nMaskLen, double *pYData, size_t nYSize, double intercept, WORD nRetType, double *retVal)
	Calculates a measure for the goodness of fit (e.g., R square, adjusted R square, MSRE, LLF, AIC, etc.).
int __stdcall	NDK_PCR_PRFTest (double **pXData, size_t nXSize, size_t nXVars, double *pYData, size_t nYSize, double intercept, LPBYTE mask1, size_t nMaskLen1, LPBYTE mask2, size_t nMaskLen2, double alpha, WORD nRetType, double *retVal)
	Calculates the p-value and related statistics of the partial f-test for PCR (used for testing the inclusion/exclusion variables).
int __stdcall	NDK_PCR_STEPWISE (double **pXData, size_t nXSize, size_t nXVars, LPBYTE mask, size_t nMaskLen, double *pYData, size_t nYSize, double intercept, double alpha, WORD nMode)
	Returns a list of the selected variables after performing the stepwise regression.

Detailed Description

Principal component analysis (PCA) is a mathematical procedure that uses an orthogonal linear transformation to convert a set of observations of possibly correlated variables into values of linearly uncorrelated variables called principal components.

Function Documentation

NDK_PCA_COMP()

int __stdcall NDK_PCA_COMP	(	double **	pXData,
		size_t	nXSize,
		size_t	nXVars,
		LPBYTE	varMask,
		size_t	nMaskLen,
		WORD	standardize,
		WORD	nCompIndex,
		WORD	retType,
		double *	retVal,
		size_t	nOutSize )

Returns statistics and fitted values for the i-th principal component.

Parameters

[in]	pXData	(Required) is the independent (explanatory) variables data matrix, such that each column represents one variable.
[in]	nXSize	(Required) is the number of observations in pXData.
[in]	nXVars	(Required) is the number of independent (explanatory) variables (columns) in pXData.
[in]	varMask	(Required) is the boolean array to choose the explanatory variables in the model. If missing, all variables in X are included.
[in]	nMaskLen	(Required) is the number of elements in the varMask.
[in]	standardize	(Required) is a flag or switch to standardize the input variables prior to the analysis: Value Standardize 1 Standardize (subtract mean and divide by standard deviation) 2 Subtract mean (subtract mean).
[in]	nCompIndex	(Required) is the component number to return.
[in]	retType	(Required) is a switch to select the return output (1 = proportion of variance (default), 2 = variance, 3 = eigenvalue, 4 = loadings, 5 = PC data). Value Return 1 Proportion of total variance 2 Variance 3 Eigenvalue 4 Loading or weights for input variables 5 Principal component (PC) data
[out]	retVal	(Required) is a pointer to a variable to hold the calculated test statistics.
[in]	nOutSize	(Required) is the size of the retVal.

Returns

status code of the function call: zero = success, positive = success with a warning, and negative = error occurred.

Return values

NDK_SUCCESS	success
NDK_INVALID_ARG	failed (see remarks)
NDK_EMPTY_TIME_SERIES	(see remarks)
NDK_FAILED	failed

Remarks

1. The data sample may include one or more observation with missing values (i.e., NaN).
2. If the value of the nSize is zero, the function will fail and return NDK_INVALID_ARG.
3. If the value of the pData argument is NULL, the function will fails and return NDK_INVALID_ARG.
4. The function moves the missing values to the end of the array, and update the nSixe argument with the number of non-missing values in the array.

Requirements

Requirement	Value
Target Platform	Windows
Header	SFSDK.h (include Windows.h)
Library	SFSDK.lib
DLL	SFSDK.dll

Since

v1.68

See also

• NDK_PCA_VAR
• NDK_PCR_PARAM
• NDK_PCR_FORE
• NDK_PCR_FITTED
• NDK_PCR_ANOVA
• NDK_PCR_GOF
• NDK_PCR_PRFTest
• NDK_PCR_STEPWISE

NDK_PCA_VAR()

int __stdcall NDK_PCA_VAR	(	double **	pXData,
		size_t	nXSize,
		size_t	nXVars,
		LPBYTE	varMask,
		size_t	nMaskLen,
		WORD	standardize,
		WORD	nVarIndex,
		WORD	wMaxPC,
		WORD	retType,
		double *	retVal,
		size_t	nOutSize )

Returns stats or fitted values for the i-th variable using a subset of the principal components.

Parameters

[in]	pXData	(Required) is the independent (explanatory) variables data matrix, such that each column represents one variable.
[in]	nXSize	(Required) is the number of observations in pXData.
[in]	nXVars	(Required) is the number of independent (explanatory) variables (columns) in pXData.
[in]	varMask	(Required) is the boolean array to choose the explanatory variables in the model. If missing, all variables in X are included.
[in]	nMaskLen	(Required) is the number of elements in the varMask.
[in]	standardize	(Required) is a flag or switch to standardize the input variables prior to the analysis: Value Standardize 1 Standardize (subtract mean and divide by standard deviation) 2 Subtract mean (subtract mean).
[in]	nVarIndex	(Required) is the input variable number.
[in]	wMaxPC	(Required) is the number of principal components (PC) to include.
[in]	retType	(Required) is a switch to select the return output (1 = Final communality (default), 2 = Loading/weights, 3 = Fitted values, 4 = Residuals). Value Return 1 Final communality 2 Loading or weights for factors 3 Fitted input variable (from PCs). 4 Residuals
[out]	retVal	(Required) is a pointer to buffer (e.g., variable or array) to hold the calculated values.
[in]	nOutSize	(Required) is the size of the buffer pointed to by retVal.

Returns

status code of the function call: zero = success, positive = success with a warning, and negative = error occurred.

Return values

NDK_SUCCESS	success
NDK_INVALID_ARG	failed (see remarks)
NDK_EMPTY_TIME_SERIES	(see remarks)
NDK_FAILED	failed

Remarks

1. The data sample may include one or more observation with missing values (i.e., NaN).
2. If the value of the nSize is zero, the function will fail and return NDK_INVALID_ARG.
3. If the value of the pData argument is NULL, the function will fails and return NDK_INVALID_ARG.
4. The function moves the missing values to the end of the array, and update the nSixe argument with the number of non-missing values in the array.

Requirements

Requirement	Value
Target Platform	Windows
Header	SFSDK.h (include Windows.h)
Library	SFSDK.lib
DLL	SFSDK.dll

Since

v1.68

See also

• NDK_PCA_COMP
• NDK_PCR_PARAM
• NDK_PCR_FORE
• NDK_PCR_FITTED
• NDK_PCR_ANOVA
• NDK_PCR_GOF
• NDK_PCR_PRFTest
• NDK_PCR_STEPWISE

NDK_PCR_ANOVA()

int __stdcall NDK_PCR_ANOVA	(	double **	pXData,
		size_t	nXSize,
		size_t	nXVars,
		LPBYTE	mask,
		size_t	nMaskLen,
		double *	pYData,
		size_t	nYSize,
		double	intercept,
		WORD	nRetType,
		double *	retVal )

Calculates the regression model (of principal components) analysis of variance (ANOVA) values.

Parameters

[in]	pXData	(Required) is the independent (explanatory) variables data matrix, such that each column represents one variable.
[in]	nXSize	(Required) is the number of observations in pXData.
[in]	nXVars	(Required) is the number of independent (explanatory) variables (columns) in pXData.
[in]	mask	(Required) is the boolean array to choose the explanatory variables in the model. If missing, all variables in X are included.
[in]	nMaskLen	(Required) is the number of elements in the varMask.
[in,out]	pYData	(Required) is the response or the dependent variable data array (one dimensional array of cells).
[in]	nYSize	(Required) is the number of observations in pYData.
[in]	intercept	(Required) is the constant or the intercept value to fix (e.g., zero). If missing (i.e., NaN), an intercept will not be fixed and is computed typically.
[in]	nRetType	(Required) is a switch to select the return output (1 = fitted values (default), 2 = residuals, 3 = std. residuals, 4 = X (cleaned), 5 = Y (cleaned)). Value Return 1 SSR (sum of squares of the regression) 2 SSE (sum of squares of the residuals) 3 SST (sum of squares of the dependent variable) 4 MSR (mean squares of the regression) 5 MSE (mean squares error or residuals) 6 F-Stat (test score) 7 Significance F (P-value of the test)
[out]	retVal	(Required) is a pointer to a variable to hold the value of the calculated ANOVA statistics.

Returns

status code of the function call: zero = success, positive = success with a warning, and negative = error occurred.

Return values

NDK_SUCCESS	success
NDK_INVALID_ARG	failed (see remarks)
NDK_EMPTY_TIME_SERIES	(see remarks)
NDK_FAILED	failed

Remarks

1. The data sample may include one or more observation with missing values (i.e., NaN).
2. If the value of the nSize is zero, the function will fail and return NDK_INVALID_ARG.
3. If the value of the pData argument is NULL, the function will fails and return NDK_INVALID_ARG.
4. The function moves the missing values to the end of the array, and update the nSixe argument with the number of non-missing values in the array.

Requirements

Requirement	Value
Target Platform	Windows
Header	SFSDK.h (include Windows.h)
Library	SFSDK.lib
DLL	SFSDK.dll

Since

v1.68

See also

• NDK_PCA_COMP
• NDK_PCA_VAR
• NDK_PCR_PARAM
• NDK_PCR_FORE
• NDK_PCR_GOF
• NDK_PCR_FITTED
• NDK_PCR_PRFTest
• NDK_PCR_STEPWISE

NDK_PCR_FITTED()

int __stdcall NDK_PCR_FITTED	(	double **	pXData,
		size_t	nXSize,
		size_t	nXVars,
		LPBYTE	mask,
		size_t	nMaskLen,
		double *	pYData,
		size_t	nYSize,
		double	intercept,
		WORD	nRetType )

Returns an array of cells for the i-th principal component (or residuals).

Parameters

[in]	pXData	(Required) is the independent (explanatory) variables data matrix, such that each column represents one variable.
[in]	nXSize	(Required) is the number of observations in pXData.
[in]	nXVars	(Required) is the number of independent (explanatory) variables (columns) in pXData.
[in]	mask	(Required) is the boolean array to choose the explanatory variables in the model. If missing, all variables in X are included.
[in]	nMaskLen	(Required) is the number of elements in the varMask.
[in,out]	pYData	(Required) is the response or the dependent variable data array (one dimensional array of cells).
[in]	nYSize	(Required) is the number of observations in pYData.
[in]	intercept	(Required) is the constant or the intercept value to fix (e.g., zero). If missing (i.e., NaN), an intercept will not be fixed and is computed typically.
[in]	nRetType	(Required) is a switch to select the return output (1 = fitted values (default), 2 = residuals, 3 = std. residuals, 4 = X (cleaned), 5 = Y (cleaned)). Value Return 1 Fitted/Conditional Mean 2 Residuals 3 Standardized (aka Studentized) Residuals 4 Leverage (H) 5 Cook's Distance (D)

Returns

status code of the function call: zero = success, positive = success with a warning, and negative = error occurred.

Return values

NDK_SUCCESS	success
NDK_INVALID_ARG	failed (see remarks)
NDK_EMPTY_TIME_SERIES	(see remarks)
NDK_FAILED	failed

Remarks

1. The data sample may include one or more observation with missing values (i.e., NaN).
2. If the value of the nSize is zero, the function will fail and return NDK_INVALID_ARG.
3. If the value of the pData argument is NULL, the function will fails and return NDK_INVALID_ARG.
4. The function moves the missing values to the end of the array, and update the nSixe argument with the number of non-missing values in the array.

Requirements

Requirement	Value
Target Platform	Windows
Header	SFSDK.h (include Windows.h)
Library	SFSDK.lib
DLL	SFSDK.dll

Since

v1.68

See also

• NDK_PCA_COMP
• NDK_PCA_VAR
• NDK_PCR_PARAM
• NDK_PCR_FORE
• NDK_PCR_ANOVA
• NDK_PCR_GOF
• NDK_PCR_PRFTest
• NDK_PCR_STEPWISE

NDK_PCR_FORE()

int __stdcall NDK_PCR_FORE	(	double **	pXData,
		size_t	nXSize,
		size_t	nXVars,
		LPBYTE	mask,
		size_t	nMaskLen,
		double *	pYData,
		size_t	nYSize,
		double	intercept,
		double *	target,
		double	alpha,
		WORD	nRetType,
		double *	retVal )

Calculates the model's estimated values, std. errors and related statistics.

Parameters

[in]	pXData	(Required) is the independent (explanatory) variables data matrix, such that each column represents one variable.
[in]	nXSize	(Required) is the number of observations in pXData.
[in]	nXVars	(Required) is the number of independent (explanatory) variables (columns) in pXData.
[in]	mask	(Required) is the boolean array to choose the explanatory variables in the model. If missing, all variables in X are included.
[in]	nMaskLen	(Required) is the number of elements in the varMask.
[in]	pYData	(Required) is the response or the dependent variable data array (one dimensional array of cells).
[in]	nYSize	(Required) is the number of observations in pYData.
[in]	intercept	(Required) is the constant or the intercept value to fix (e.g., zero). If missing (i.e., NaN), an intercept will not be fixed and is computed typically.
[in]	target	(Required) is the constant or the intercept value to fix (e.g., zero). If missing (i.e., NaN), an intercept will not be fixed and is computed typically.
[in]	alpha	(Required) is the statistical significance or confidence level (i.e. alpha). If missing or omitted, an alpha value of 5% is assumed.
[in]	nRetType	(Required) is a switch to select the return output (1 = Mean Value (default), 2 = Std Error, 3 = Test Score, 4 = P-Value, 5 = Upper Value, 6 = Lower Value). Value Return 1 Mean Value (default) 2 Standard Error. 3 Upper Limit. 4 Lower Limit.
[out]	retVal	(Required) is a pointer to a variable to hold the calculated value or statistics.

Returns

status code of the function call: zero = success, positive = success with a warning, and negative = error occurred.

Return values

NDK_SUCCESS	success
NDK_INVALID_ARG	failed (see remarks)
NDK_EMPTY_TIME_SERIES	(see remarks)
NDK_FAILED	failed

Remarks

1. The data sample may include one or more observation with missing values (i.e., NaN).
2. If the value of the nSize is zero, the function will fail and return NDK_INVALID_ARG.
3. If the value of the pData argument is NULL, the function will fails and return NDK_INVALID_ARG.
4. The function moves the missing values to the end of the array, and update the nSixe argument with the number of non-missing values in the array.

Requirements

Requirement	Value
Target Platform	Windows
Header	SFSDK.h (include Windows.h)
Library	SFSDK.lib
DLL	SFSDK.dll

Since

v1.68

See also

• NDK_PCA_COMP
• NDK_PCA_VAR
• NDK_PCR_PARAM
• NDK_PCR_FITTED
• NDK_PCR_ANOVA
• NDK_PCR_GOF
• NDK_PCR_PRFTest
• NDK_PCR_STEPWISE

NDK_PCR_GOF()

int __stdcall NDK_PCR_GOF	(	double **	pXData,
		size_t	nXSize,
		size_t	nXVars,
		LPBYTE	mask,
		size_t	nMaskLen,
		double *	pYData,
		size_t	nYSize,
		double	intercept,
		WORD	nRetType,
		double *	retVal )

Calculates a measure for the goodness of fit (e.g., R square, adjusted R square, MSRE, LLF, AIC, etc.).

Parameters

[in]	pXData	(Required) is the independent (explanatory) variables data matrix, such that each column represents one variable.
[in]	nXSize	(Required) is the number of observations in pXData.
[in]	nXVars	(Required) is the number of independent (explanatory) variables (columns) in pXData.
[in]	mask	(Required) is the boolean array to choose the explanatory variables in the model. If missing, all variables in X are included.
[in]	nMaskLen	(Required) is the number of elements in the varMask.
[in,out]	pYData	(Required) is the response or the dependent variable data array (one dimensional array of cells).
[in]	nYSize	(Required) is the number of observations in pYData.
[in]	intercept	(Required) is the constant or the intercept value to fix (e.g., zero). If missing (i.e., NaN), an intercept will not be fixed and is computed typically.
[in]	nRetType	(Required) is a switch to select the return output (1 = R-Square (default), 2 = Adj. R-Square, 3 = RMSE, 4 = LLF, 5 = AIC, 6 = SIC/BIC).. Value Return 1 R-Squared 2 Adjusted R-Squared 3 Regression Error 4 log-likelihood (LLF) 5 Akaike information criterion (AIC) 6 Schwartz/Bayesian information criterion (SBIC)
[out]	retVal	(Required) is a pointer to a variable to hold the value of the calculated GOF statistics.

Returns

status code of the function call: zero = success, positive = success with a warning, and negative = error occurred.

Return values

NDK_SUCCESS	success
NDK_INVALID_ARG	failed (see remarks)
NDK_EMPTY_TIME_SERIES	(see remarks)
NDK_FAILED	failed

Remarks

1. The data sample may include one or more observation with missing values (i.e., NaN).
2. If the value of the nSize is zero, the function will fail and return NDK_INVALID_ARG.
3. If the value of the pData argument is NULL, the function will fails and return NDK_INVALID_ARG.
4. The function moves the missing values to the end of the array, and update the nSixe argument with the number of non-missing values in the array.

Requirements

Requirement	Value
Target Platform	Windows
Header	SFSDK.h (include Windows.h)
Library	SFSDK.lib
DLL	SFSDK.dll

Since

v1.68

See also

• NDK_PCA_COMP
• NDK_PCA_VAR
• NDK_PCR_PARAM
• NDK_PCR_FORE
• NDK_PCR_ANOVA
• NDK_PCR_FITTED
• NDK_PCR_PRFTest
• NDK_PCR_STEPWISE

NDK_PCR_PARAM()

int __stdcall NDK_PCR_PARAM	(	double **	pXData,
		size_t	nXSize,
		size_t	nXVars,
		LPBYTE	mask,
		size_t	nMaskLen,
		double *	pYData,
		size_t	nYSize,
		double	intercept,
		double	alpha,
		WORD	nRetType,
		WORD	ParamIndex,
		double *	retVal )

Calculates the regression coefficients values for a given input variable.

Parameters

[in]	pXData	(Required) is the independent (explanatory) variables data matrix, such that each column represents one variable.
[in]	nXSize	(Required) is the number of observations in pXData.
[in]	nXVars	(Required) is the number of independent (explanatory) variables (columns) in pXData.
[in]	mask	(Required) is the boolean array to choose the explanatory variables in the model. If missing, all variables in X are included.
[in]	nMaskLen	(Required) is the number of elements in the varMask.
[in]	pYData	(Required) is the response or the dependent variable data array (one dimensional array of cells).
[in]	nYSize	(Required) is the number of observations in pYData.
[in]	intercept	(Required) is the constant or the intercept value to fix (e.g., zero). If missing (i.e., NaN), an intercept will not be fixed and is computed typically.
[in]	alpha	(Required) is the statistical significance or confidence level (i.e. alpha). If missing or omitted, an alpha value of 5% is assumed.
[in]	nRetType	(Required) is a switch to select the return output (1 = Mean Value (default), 2 = Std Error, 3 = Test Score, 4 = P-Value, 5 = Upper Value, 6 = Lower Value). Value Return 1 Mean Value (default) 2 Standard Error. 3 T-Stat. 4 P-Value. 5 Upper Limit. 6 Lower Limit.
[in]	ParamIndex	(Required) is a switch to designate the target parameter (0 = intercept (default), 1 = first variable, 2 = 2nd variable, etc.).
[out]	retVal	(Required) is a pointer to a variable to hold the calculated value.

Returns

status code of the function call: zero = success, positive = success with a warning, and negative = error occurred.

Return values

NDK_SUCCESS	success
NDK_INVALID_ARG	failed (see remarks)
NDK_EMPTY_TIME_SERIES	(see remarks)
NDK_FAILED	failed

Remarks

1. The data sample may include one or more observation with missing values (i.e., NaN).
2. If the value of the nSize is zero, the function will fail and return NDK_INVALID_ARG.
3. If the value of the pData argument is NULL, the function will fails and return NDK_INVALID_ARG.
4. The function moves the missing values to the end of the array, and update the nSixe argument with the number of non-missing values in the array.

Requirements

Requirement	Value
Target Platform	Windows
Header	SFSDK.h (include Windows.h)
Library	SFSDK.lib
DLL	SFSDK.dll

Since

v1.68

See also

• NDK_PCA_COMP
• NDK_PCA_VAR
• NDK_PCR_FORE
• NDK_PCR_FITTED
• NDK_PCR_ANOVA
• NDK_PCR_GOF
• NDK_PCR_PRFTest
• NDK_PCR_STEPWISE

NDK_PCR_PRFTest()

int __stdcall NDK_PCR_PRFTest	(	double **	pXData,
		size_t	nXSize,
		size_t	nXVars,
		double *	pYData,
		size_t	nYSize,
		double	intercept,
		LPBYTE	mask1,
		size_t	nMaskLen1,
		LPBYTE	mask2,
		size_t	nMaskLen2,
		double	alpha,
		WORD	nRetType,
		double *	retVal )

Calculates the p-value and related statistics of the partial f-test for PCR (used for testing the inclusion/exclusion variables).

Parameters

[in]	pXData	(Required) is the independent (explanatory) variables data matrix, such that each column represents one variable.
[in]	nXSize	(Required) is the number of observations in pXData.
[in]	nXVars	(Required) is the number of independent (explanatory) variables (columns) in pXData.
[in]	pYData	(Required) is the response or the dependent variable data array (one dimensional array of cells).
[in]	nYSize	(Required) is the number of observations in pYData.
[in]	intercept	(Required) is the constant or the intercept value to fix (e.g., zero). If missing (i.e., NaN), an intercept will not be fixed and is computed typically.
[in]	mask1	(Required) is the boolean array to choose the explanatory variables in the model. If missing, all variables in X are included.
[in]	nMaskLen1	(Required) is the number of elements in the varMask.
[in]	mask2	(Required) is the boolean array to choose the explanatory variables in the model. If missing, all variables in X are included.
[in]	nMaskLen2	(Required) is the number of elements in the varMask.
[in]	alpha	(Required) is the statistical significance or confidence level (i.e. alpha). If missing or omitted, an alpha value of 5% is assumed.
[in]	nRetType	(Required) is a switch to select the return output (1 = Mean Value (default), 2 = Std Error, 3 = Test Score, 4 = P-Value, 5 = Upper Value, 6 = Lower Value). Value Return 1 P-value 2 Test Statistics (e.g., Z-score). 3 Critical Value.
[out]	retVal	(Required) is a pointer to a variable to hold the calculated test statistics.

Returns

status code of the function call: zero = success, positive = success with a warning, and negative = error occurred.

Return values

NDK_SUCCESS	success
NDK_INVALID_ARG	failed (see remarks)
NDK_EMPTY_TIME_SERIES	(see remarks)
NDK_FAILED	failed

Remarks

1. The data sample may include one or more observation with missing values (i.e., NaN).
2. If the value of the nSize is zero, the function will fail and return NDK_INVALID_ARG.
3. If the value of the pData argument is NULL, the function will fails and return NDK_INVALID_ARG.
4. The function moves the missing values to the end of the array, and update the nSixe argument with the number of non-missing values in the array.

Requirements

Requirement	Value
Target Platform	Windows
Header	SFSDK.h (include Windows.h)
Library	SFSDK.lib
DLL	SFSDK.dll

Since

v1.68

See also

• NDK_PCA_COMP
• NDK_PCA_VAR
• NDK_PCR_PARAM
• NDK_PCR_FORE
• NDK_PCR_GOF
• NDK_PCR_FITTED
• NDK_PCR_ANOVA
• NDK_PCR_STEPWISE

NDK_PCR_STEPWISE()

int __stdcall NDK_PCR_STEPWISE	(	double **	pXData,
		size_t	nXSize,
		size_t	nXVars,
		LPBYTE	mask,
		size_t	nMaskLen,
		double *	pYData,
		size_t	nYSize,
		double	intercept,
		double	alpha,
		WORD	nMode )

Returns a list of the selected variables after performing the stepwise regression.

Parameters

[in]	pXData	(Required) is the independent (explanatory) variables data matrix, such that each column represents one variable.
[in]	nXSize	(Required) is the number of observations in pXData.
[in]	nXVars	(Required) is the number of independent (explanatory) variables (columns) in pXData.
[in,out]	mask	(Required) is the boolean array to choose the explanatory variables in the model. If missing, all variables in X are included.
[in]	nMaskLen	(Required) is the number of elements in the varMask.
[in]	pYData	(Required) is the response or the dependent variable data array (one dimensional array of cells).
[in]	nYSize	(Required) is the number of observations in pYData.
[in]	intercept	(Required) is the constant or the intercept value to fix (e.g., zero). If missing (i.e., NaN), an intercept will not be fixed and is computed typically.
[in]	alpha	(Required) is the statistical significance or confidence level (i.e. alpha). If missing or omitted, an alpha value of 5% is assumed.
[in]	nMode	(Required) is a switch to select the return output (1 = Mean Value (default), 2 = Std Error, 3 = Test Score, 4 = P-Value, 5 = Upper Value, 6 = Lower Value). Value Method 1 Forward selection 2 Backward elimination. 3 Bi-direction elimination.

Returns

status code of the function call: zero = success, positive = success with a warning, and negative = error occurred.

Return values

NDK_SUCCESS	success
NDK_INVALID_ARG	failed (see remarks)
NDK_EMPTY_TIME_SERIES	(see remarks)
NDK_FAILED	failed

Remarks

1. The data sample may include one or more observation with missing values (i.e., NaN).
2. If the value of the nSize is zero, the function will fail and return NDK_INVALID_ARG.
3. If the value of the pData argument is NULL, the function will fails and return NDK_INVALID_ARG.
4. The function moves the missing values to the end of the array, and update the nSixe argument with the number of non-missing values in the array.

Requirements

Requirement	Value
Target Platform	Windows
Header	SFSDK.h (include Windows.h)
Library	SFSDK.lib
DLL	SFSDK.dll

Since

v1.68

See also

• NDK_PCA_COMP
• NDK_PCA_VAR
• NDK_PCR_PARAM
• NDK_PCR_FORE
• NDK_PCR_GOF
• NDK_PCR_FITTED
• NDK_PCR_ANOVA
• NDK_PCR_PRFTest