Data Science Analytics

1. Suppose that the data for analysis includes the attribute age. The age values for the data tuples are: 37, 37, 38, 42, 15, 17, 22, 23, 24, 24, 27, 32, 35, 35, 37, 37, 47, 48, 54, 72, 27, 27, 18, 21, 22, 18, 27.

What is the mean of the data?

What is the median?

What is the mode of the data? Comment on the datas modality (i.e., bimodal, trimodal, ...).

What is the midrange of the data?

Give the five-number summary of the data.

What is the interquartile range (IQR) of the data?

What number(s) is(are) the outlier(s)?

2. Given two objects represented by the tuples (24, 3, 44, 12) and (22, 2, 38, 10):

Compute the Euclidean distance between the two objects.

Compute the Manhattan distance between the two objects.

Compute the Minkowski distance between the two objects, using h = 3.

Compute the supremum distance between the two objects.

3. Suppose that a patient record table (shown on the next page) contains the attributes name, gender, test-1, test-2, test-3, test-4, and test-5; where name is the object identifier, gender is a symmetric attribute, and all the tests (1 to 5) are asymmetric binary.

For asymmetric attribute values, let the values P (positive) be set to 1, and the value N (negative) be set to 0. Suppose that the distance between objects (patients) is computed based only on the asymmetric attributes.

Name Gender Test-1 Test-2 Test-3 Test-4 Test-5

Peter Male P N P N P

Paul Male P P N N N

Mary Female P P P N N

Compute d(Peter, Paul) and sim(Peter, Paul).

Compute d(Peter, Mary) and sim(Peter, Mary).

Compute d(Paul, Mary) and sim(Paul, Mary).

Based on the results, who are unlikely to have a similar disease? Who are likely to have a similar disease?