Advanced Analytical Theory and Methods: Regression, details in description below.

User Generated

Nah_Fun

Computer Science

Description

Reference: Chapter 6 of your textbook. Ebook Link: file:///Users/priyalgandhi/Downloads/Data%20Science%20&%20Big%20Data%20Analytics%20(%20PDFDrive.com%20).pdf
Please provide comprehensive responses to the following:

(a) In the use of a categorical variable with n possible values, explain the following:
1. Why only n – 1 binary variables are necessary
2. Why using n variables would be problematic

(b) Describe how logistic regression can be used as a classifier.

(c) Discuss how the ROC curve can be used to determine an appropriate threshold value for a classifier

(d) If the probability of an event occurring is 0.4, then

1. What is the odds ratio?
2. What is the log odds ratio?

Requirements:

- Typed in a word document.

- Please write in APA Style and include at least Five (5) reputable sources.

- The complete paper should be between 800-to-1000-words.

User generated content is uploaded by users for the purposes of learning and should be used following Studypool's honor code & terms of service.

Explanation & Answer

Attached.

Running head: ADVANCED ANALYTICAL THEORY AND METHODS

Advanced Analytical Theory and Methods
Name of student
Institutional affiliation
Course
Date

1

ADVANCED ANALYTICAL THEORY AND METHODS

2

Advanced Analytical Theory and Methods
Answers to questions
a. when using a categorical variable with n possible values,
1. The reason as to why on n-1 binary variables are necessary is because if we consider
the vast majority, dummy variables are always statistical and can accurately encode
information represented by the categorical variables. More so, the number of dummy
variables needed in describing a given categorical variable depends on the number of
values the categorical variable can assume. That is why the n-1 binary variable is
necessary to represent a categorical variable of n values.
2. Using the n variable will be problematic. This is because algorithms are dependent on
covariance calculations such as regression and also requires numerical operations
which mean that they must operate on numbers. More so, note that dummy variables
are used to transform categorical data to numeric therefore when they are excluded in
an analysis; a po...


Anonymous
Awesome! Perfect study aid.

Studypool
4.7
Trustpilot
4.5
Sitejabber
4.4

Related Tags