assignment 4
DESCRIPTION
answer for assigment 4 of data mining association ruleTRANSCRIPT
![Page 1: Assignment 4](https://reader036.vdocuments.mx/reader036/viewer/2022082714/5695cf831a28ab9b028e6a7b/html5/thumbnails/1.jpg)
ASSIGNMENT 4.Descriptive Statistics
N Minimum Maximum Sum Mean Std. Deviation
Intro 365 0 1 144 .39 .489
DataMining 365 0 1 65 .18 .383
Survey 365 0 1 68 .19 .390
CatData 365 0 1 76 .21 .407
Regression 365 0 1 76 .21 .407
Forecast 365 0 1 51 .14 .347
DOE 365 0 1 63 .17 .378
SW 365 0 1 81 .22 .416
Valid N (listwise) 365
1. From the table the sum column, it can be concluded that Introduction course is the course mostly taken by the customers, there are 144 customers participating in this course.
2. After using the Select Case to select cases which the condition of Intro=1. The following table is obtained. It can be seen that SW is the course mostly taken with the Introduction course. There are 35 people taking both Introduction and SW course
Descriptive Statistics
N Sum
Intro 144 144
DataMining 144 20
Survey 144 22
CatData 144 26
Regression 144 26
Forecast 144 19
DOE 144 17
SW 144 35
Valid N (listwise) 144
3. Confidence=noof people participating∈both Intro∧SW
noof people participating∈Intro= 35144
=0.24
4. Benchmark confidence=noof people participating∈the SW
totalnumber of customers= 81365
=0.22
Number of people taking in SW can be obtained from the table in question 1 (sum column)
Lift ratio=0.240.22
=1.09525 ≈1
![Page 2: Assignment 4](https://reader036.vdocuments.mx/reader036/viewer/2022082714/5695cf831a28ab9b028e6a7b/html5/thumbnails/2.jpg)
5. Basing on the lift ratio of 1.09525 is slightly higher than 1, suggesting that the association is rule is not effective because although there is some degree of association between the Introduction and SW course, the relation is not much higher than would be expected if the two are independent.