The use of Linear Statistical Model to Predict Tumour Size of Colorectal Cancer

M. A. Shafi, M. S. Rusiman, N. S. A. Hamzah, E. N. Nasibov, N. A. H. M. Azmi

Abstract


Colorectal cancer (CRC) is a type of cancer in the large intestine (colon), the lower part of our digestive system. Most cases of colon cancer begin as small non-cancerous clumps of cells called adenomatous polyps. The aim of this quantitative study is to identify the determinants of patient who have colorectal cancer symptoms in general hospital. The sample study included 180 patients who have colorectal cancer aged above 21 years old and received treatment at general hospital in Kuala Lumpur, Malaysia. Secondary data were obtained through doctors and nurses using cluster sampling. Based on the results of multiple linear regressions (MLR), 11 predictor variables were significant to predict tumour size of colorectal cancer. The statistical measurement error used were mean square error (MSE), root mean square error values (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE).

Keywords


Multiple Linear Regression, mean square error (MSE), root mean square error values (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE)

Full Text:

PDF


Copyright (c) 2017 Journal of Science and Technology

ISSN : 2229-8460

e-ISSN : 2600-7924

jst@uthm.edu.my

Creative Commons License
This OJS site and its metadata are licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.