Description
Please answer each of the following questions. Expectation is 1 page (at least) per question:
1. State the difference between clustering and associations in data mining. Provide an example within healthcare data analysis when clustering can/should be used and when associations can/should be used.
2. Research various healthcare academic journals. Find one article that interests you and utilizes data mining techniques (e.g. clustering, associations, outliers). Summarize the article by stating the issue, the data mining technique used in the study, and the outcome of the study. This provides you the chance to better understand data mining techniques and how they are applied to healthcare situations.
EXTRA CREDIT (Regression review):
Worth 2 points, but assignment point total will not go over 50. Graph the following data and write down the best regression line formula and R2 value:
X: 2,4,6,12,24,36
Y: 5,17,37,145,577,1297
Unformatted Attachment Preview
Purchase answer to see full attachment
Explanation & Answer
Attached.
Data Mining
Your name
Instructor’s name
Course
Date of submission
Question 1
Data mining comprises two main independent techniques that treat distinct analysis
functions. Clustering is an unsupervised learning function using an algorithm to group objects by
similarity. The objective is to maximize the homogeneity of clusters by forming membership
between the points where the objects in the same clusters are more similar than those in different
clusters. The method is best applied in exploratory data analysis when data sets are so unknown
that the analyst needs to uncover intrinsic categories (Rodriguez et al., 2019).
Distinct from traditional clustering techniques, the association rules ascertain meaningful
patterns from the inter-variable relationships concealed in large datasets. Under association rule
mining, analysts can identify the relationships recurring between data points, which mention some
usual combinations of attributes. Clustering is often used in real life for market basket analysis
since it can help discover the types of products consumers purchase in combination. The efficacy
of clustering is well-exemplified when the patient segmentation task is taken within...
