06.b Logistic Regression

Question 1

What is Logistic Regression

Answer 1

The logistic regression is a supervised predictive analysis. Logistic regression is used to describe data and to explain the relationship between one dependent categorical variable and one or more nominal, ordinal, interval or ratio-level independent variables by estimating probabilities using a logistic function.

Question 2

What type of output variable comes from Logistic Regression

Answer 2

When the outcome variable is categorical in nature, logistic regression can be used to predict the likelihood of an outcome based on the input variables.

Question 3

Name four use cases for Logistic Regression

Answer 3

Medical
Finance
Marketing
Engineering

Question 4

What shape is the common Logistic Curve

Answer 4

An S Shape curve. Bottom left is zero, top right is One, with an S Shape joining the two corners

Question 5

What is the Logistic Function (equation)

Answer 5

f(y) = e^y / (1+e^y) for -infinity < y < +infinity

Question 6

What is MLE in terms of Logistic Regression

Answer 6

MLE stands for Maximum Likelihood Estimation

Question 7

What does churn mean

Answer 7

Churn refers to the likelihood of a customer will switch to another company

Question 8

Which function should you use for Logistic Regression in R

Answer 8

The Generalised Linear Model function glm()

OutputDF = glm (Churned ~ Age + Married + Cust_Years+Churned_Contacts, data=churn_input, family=bionomial(link=”logit”))

Question 9

Describe Odds

Answer 9

The Odds of something happening are the chances of A happening divided by the chances of B happening.

Question 10

Describe Probability

Answer 10

The Probablity of something happening are the chances of A happening divided by the chances of all possible results.

Question 11

Once you have calculated the Generalised Linear Model for y which equation should you use to calculate the probability

Answer 11

p = e^y / (1-e^y)

Question 12

What is the Akaike Information Criteria (AIC)

Answer 12

You can look at AIC as counterpart of adjusted r square in multiple linear regression. It’s an important indicator of model fit. It follows the rule: Smaller the better. AIC penalises increasing number of coefficients in the model. It helps to avoid over-fitting.

Question 13

In Logistic Regression what is the Null Deviance

Answer 13

The Null Deviance is the value where the likelihood function is based only on the intercept term

Question 14

In Logistic Regression what is the Residual Deviance

Answer 14

The Residual Deviance is the value where the likelihood function is based on the parameters in the specified logistic model

Question 15

In Logistic Regression how do you calculate a Pseudo - R squared

Answer 15

Pseudo R Squared = 1 - (residual dev. / null dev.)

Question 16

The Deviance of an observation is calculated how

Answer 16

-2 * log (likelihood of that observation)

Question 17

What is a confusion matrix

Answer 17

A table of Actual Class (AC) against Predicted Class (PC) showing false and true
PC
Positives (1) Negatives (0)
Positives (1) True Pos False Neg
AC Negatives (0) False Pos True Neg

A good classifer should have high True (Pos&Neg) and low False (Pos & Neg)

Question 18

What is the true positive rate (TPR)

Answer 18

TPR = TP / (TP +FN)

All the TP divided by all the actual Positives

Question 19

What is the false positive rate (FPR)

Answer 19

FPR = FP / ( FP + TN)

All the FP divided by all the actual Negatives

Question 20

What is the true negative rate (TNR)

Answer 20

TNR = TN / (FP + TN)

All the TN divided by all the actual Negatives

Question 21

What is the false negative rate (FNR)

Answer 21

FNR = FN / (TP + FN)

All of the FN divided by all the actual Positives

Question 22

What is Accuracy of a Confusion Matrix

Answer 22

Accuracy = TP + TN / (TP + TN + FP + FN)

So the correct ones / everything

Question 23

What is Precision of a Confusion Matrix

Answer 23

Precision = TP / ( TP + FP)

P for Precsion all of the P’s! TP / all of the positives

Question 24

What is Recall of a Confusion Matrix

Answer 24

Recall = TP / ( TP + FN )

Which is the same as the TPR

Question 25

How do you calculate the F Score of a Confusion Matrix

Answer 25

FScore = 2 x ((Precision x Recall)/ (Precision + Recall

Question 26

When would you consider using Ridge Regression or Lasso Regression

Answer 26

In the case of multicollinearity you could consider using Ridge or Lasso regression because they apply penalties based on the size of the coefficients in an effort to reduce the impact of the multicollinearity

Question 27

What is a ROC curve

Answer 27

It is a receiver operator curve
It is a plot of the TPR against the FPR
A 45 deg line represents as many correct as wrong
A straight line up the y axis and flat line across the top represents a 100% accuracy

ROC Curve is looking at the Positives!

Question 28

In logistic regression what is the default threshold

Answer 28

50%

Question 29

What is another name for a leaf node

Answer 29

A class label