|
|
|
|
|
Using the Linear Discriminant Analysis Method to Classify Types of Bowels and Esophageal cancer in Jordan |
|
PP: 1299-1305 |
|
doi:10.18576/isl/120320
|
|
Author(s) |
|
Adeeb Ahmed AL Rahamneh,
Sami Senyal Jresat,
Faraj Zubaidi,
Sulieman Ibraheem Shelash Al-Hawary,
|
|
Abstract |
|
The research aims at achieving the best linear model to distinguish between two types of Bowels and Esophageal cancer in Jordan, using the methodofdiscriminant analysis, the SPSS program was used to analyze the data. The study concluded a number of results, the most prominent of which were: the variables sex (x1), weight (x3), and Platelets Count P.C (x8) which have a significant impact in constructing the discriminatory function. The probability of correct classification of a disease belonging to the first group was equal to (62.8%) and to the second group was equal to (77%). The probability of misclassification in the first group, was equal to (37.2%), and for the second group was (23%), the overall correct classification ratio (71.6%) and the false classification ratio (28.4%),the probability of correct classification of a disease belonging to the first group was equal to (66.4%) and the second group was equal to (77.6%). It was noted that the discriminant analysis method was able to identify the most important independent variables in the diagnosis of both types of Bowel and Esophageal cancer.
|
|
|
|
|
|