Final Module (11 & 12)

Question 1

Matrix

Answer 1

a rectangular array of numbers, symbols, expressions, functions etc. (called entries, or elements), arranged in rows and columns

Question 2

Vectors

Answer 2

matrices with only one row or column

Question 3

Element-by-element multiplication & division

Answer 3

multiplication: 𝐴 ∘ 𝐵
division: 𝐴 ⊘ 𝐵

Basically multiplying and dividing by using the same rules as adding & subtracting instead of the normal matrix rule.

Question 4

Matrix multiplication is not commutative (true or false)

Answer 4

TRUE

Question 5

Logistic regression

Answer 5

a statistical method that models the relationship between a binary response variable and one or more
continuous predictor variables

Question 6

Examples of Logistic regression

Answer 6

• Predicting whether or not a customer will default on a loan based on their credit score
• Predicting whether a basketball player will get drafted into the NBA based on average rebounds and points per game

Question 7

Logistic regression assumes

Answer 7

instead of the linear dependence between the response variable and predictor variables 𝑦 = 𝛽0 + 𝛽1𝑥1 + ⋯ + 𝛽𝑛𝑥𝑛 there is a linear dependence between the “logit” function of probability that the response variable takes the value of 1 and the predictor variables

Question 8

Parameter risk

Answer 8

the risk associated with underestimating or
overestimating the parameters of the model

Question 9

Process Risk

Answer 9

the risk associated with the variability of the
process itself

Question 10

Model Risk

Answer 10

the risk associated with choosing insufficiently
accurate model

Question 11

Modeling parameter risk using

Answer 11

LINEST output

Question 12

Total Risk =

Answer 12

Total Risk = parameter risk + process risk

Question 13

“Logit” function of the probability of response variable to be 1 is modeled as

Answer 13

a linear combination of predictors

Question 14

MLE

Answer 14

used to find the set of parameters that provides the best loglikelihood of the model