PEMODELAN REGRESI HECKIT UNTUK KONSUMSI SUSU DI PROVINSI JAWA TENGAH

Dwi Asti Rakhmawati, Dwi Ispriyansti, Agus Rusgiyono

Abstract


In multiple regression if the response variable is dummy variable then it can not be used because it will produce biased and inconsistent estimator. The appropriate method for binary response variables is Heckit Regression. Estimation of Heckit Regression parameter using Two Step Method of Procurement is the selection equation and the result equation. In the selection equation will get new variable that is Invers Mills Ratio. While in Equation Result of new variable of Inverse Mills Ratio is added as independent variable along with other independent variable. Heckit Regression method is applied to household milk consume data obtained from 2015 SUSENAS results as many as 201 households. The response variable used is household expenditure for milk consumption. The independent variables used are the working status of the head of the household, the last education of the head of the household, the number of household members, the number of toddler age in the family and the income of the household.

Keywords: Multiple Regression, OLS, Heckit Regression, Two Step Procedure, Milk consumption expenditure.


Full Text:

PDF

Refbacks

  • There are currently no refbacks.



Creative Commons License
Jurnal Gaussian by Departemen Statistika Undip is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Flag Counter