| int __stdcall NDK_GLM_VALIDATE | ( | double * | betas, |
| size_t | nBetas, | ||
| double | phi, | ||
| WORD | Lvk | ||
| ) |
Examines the model's parameters for constraints (e.g. positive variance, etc.).
- Returns
- status code of the operation
- Return values
-
NDK_SUCCESS Operation successful NDK_FAILED Operation unsuccessful. See Macros for full list.
- Parameters
-
[in] betas are the coefficients of the GLM model (a one dimensional array) [in] nBetas is the number of the coefficients in betas. Note that nBetas must be equal to nVars+1 [in] phi is the GLM dispersion parameter. Phi is only meaningful for Binomial (1/batch or trial size) and for Gaussian (variance). - Binomial : phi = Reciprocal of the batch/trial size.
- Gaussian : phi = variance.
- Poisson : phi = 1.0
[in] Lvk is the link function that describes how the mean depends on the linear predictor (see GLM_LINK_FUNC). - Identity (default)
- Log
- Logit
- Probit
- Complementary log-log
- Remarks
-
- The underlying model is described here.
- The GLM_CHECK function examines primarily the value of dispersion factor (Phi):
- For Poisson distribution, the dispersion factor (Phi) must be equal to 1(one).
- For Binomial distribution: the dispersion factor (Phi) must be greater than zero, and less than one.
- For Gaussian distribution, the dispersion coefficient (Phi) must be positive.
- Requirements
-
Header SFSDK.H Library SFSDK.LIB DLL SFSDK.DLL
