13.05.2018 Views

merged

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

Application of Robust Regression in Production of Maize<br />

Arni Natasha Binti Azmar<br />

Supervisor: Assoc. Prof. Dr. Norizan Binti Mohamed<br />

Bachelor of Science (Financial Mathematic)<br />

School of Informatics and Applied Mathematics<br />

Maize is a kind of cereal and it used as a food source of human and animal. This study<br />

discusses the use of robust regression analysis in maize production data. SAS software<br />

has been used in identifying outlier in maize production data. In regression analysis, the<br />

use of least square method would not suitable in solving problem containing outlier. This<br />

study needs a parameter estimation method which is robust where the value of estimation<br />

is not much affected by small changes in the data. The estimators used in this study are<br />

M, MM, S and LTS estimation. The comparison between estimators of robust regression<br />

is performed to get the best robust regression and to construct the best regression model.<br />

Next, the data were contaminated by 10%, 20% and 30% to determine the robustness<br />

of the model. The result show that the model still robust even though the data were<br />

contaminated.<br />

794 | UMT UNDERGRADUATE RESEARCH DAY 2018

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!