Cluster Analysis

Question 1

What is Cluster Analysis?

Answer 1

is a multivariate statistical technique that groups observations on the basis some of their features or variables they are described by

observations in a dataset can be divided into different groups

example: clustering by geographic proximity
or language
or Market Segmentation

Question 2

What is the goal of Cluster Analysis?

Answer 2

To maximize the similarity of observations within a cluster and maximize the dissimilarity between clusters

Question 3

When is clustering most often used?

Answer 3

is often used as a preliminary step in all types of analysis

it is a useful technique for exploring and identifying patterns in the data

Data Scientists often turn to it when they have no idea where to start or what to expect

Question 4

What is a key distinguishing trait of supervised leanering?

Answer 4

We are dealing with labeled data

Question 5

What is the Euclidean distance?

Question 6

What is a Centroid?

Answer 6

the mean position of a group of points

aka - center of mass

Question 7

What does K in K-means clustering stand for?

Answer 7

The number of clusters

Question 8

What is the proper way of selecting the number of clusters?

Answer 8

The elbow method

Question 9

What is Clustering about?

Answer 9

1. Minimizing the distance between points in a cluster
2. Maximizing the distance between clusters

Question 10

What does WCSS stand for?

Answer 10

Within-cluster sum of squares

if we minimize WCSS we have reached the perfect clustering solution

Question 11

What are pros of K-Means Clustering?

Answer 11

1. Simple to understand
2. Fast to cluster
3. Widely available
4. Easy to implement

Question 12

What are some cons of K-means Clustering?

Answer 12

1. We need to pick K
2. Sensitive to initialization
3. Sensitive to outliers
4. Produces spherical solutions
5. Standardization

Question 13

What are the 3 Types of Analysis?

Answer 13

1. Exploratory
2. Confirmatory
3. Explanatory

Question 14

What are characteristics of Exploratory Analysis?

Answer 14

• Getting acquainted with the data
• Search for patterns
• Plan - determining what methods may be useful to investigate further
  ie. Data Visualization, Descriptive Stats ( pd.describe() ), Clustering

Question 15

What are characteristics of Confirmatory and Explanatory Analysis?

Answer 15

• Explain a phenomenon
• Confirm a hypothesis
• Validate previous research

using hypothesis testing and regression analysis

Question 16

What are the two broad types of clustering?

Answer 16

1. Flat ie K-Means
2. Hierarchical

Question 17

What are the two types of Hierarchical Clustering?

Answer 17

1. Agglomerative (bottom-up)
2. Divisive (top-down)