Multiple regression models for mungbean production / by Ramerson M. Rupido.
Material type: TextLanguage: English Publication details: Indang, Cavite : 1999. Cavite State University- Main Campus,Description: vii, 23 pages : illustrations ; 28 cmContent type:- text
- unmediated
- volume
- 635.65 R87 1999
- College of Arts and Science (CAS)
Item type | Current library | Collection | Call number | Materials specified | URL | Status | Notes | Date due | Barcode |
---|---|---|---|---|---|---|---|---|---|
Theses / Manuscripts | Ladislao N. Diwa Memorial Library Theses Section | Non-fiction | 635.65 R87 1999 (Browse shelf(Opens below)) | Link to resource | Room use only | SP-1867 | 00007113 |
Special Problem (BS Applied Mathematics--Statistics) Cavite State University
Includes bibliographical references.
College of Arts and Science (CAS)
RUPIDO, RAMERSON MENDOZA, "Multiple Regression Models for
Mungbean Production". Bachelor of Science in Applied Mathematics Major in Statistics, Cavite State University, Indang, Cavite. April 1999. Adviser: Miss Analiza S. Pacia.
The study entitled "Multiple Regression Models for Mungbean Production" was conducted at Cavite State University from January to March 1999. It aimed to estimate a production function for Mungbean in selected farms in Batangas. Specification of the model used in production function had been based on the variables namely: area, fertilizer, labor, and operating expenses. In an attempt to relax the assumption of the ordinary least squares, autocorrelation, multicollinearity, and heteroscedasticity were tested to obtain the best fitting model.
The production function involved actual yield obtained from production using the variables mentioned. The regression revealed that area gave the most significant contribution to the production level. Operating expenses likewise contributed to the yield level, especially when the amount of fertilizer was subsumed to this variable.
The coefficient of determination revealed an impressive result, which meant that the production level was explained mainly by the variables included in the model. However, it is expected that a more acceptable values of the coefficients would be obtained from the regression if more variables would be introduced in the model, hence recommended.
Submitted to the University Library 04-13-1999 SP-1867