Exam 2

Question 1

Why we use exploratory modeling

Answer 1

obtain the best fit model from all observations

Question 2

Why we use predictive modeling

Answer 2

split observations into a training set and a validation set

Question 3

What are training sets used for

Answer 3

create the model

Question 4

what are validation sets used for

Answer 4

evaluate accuracy of the model

Question 5

predictors

Answer 5

these are our variables

Question 6

target

Answer 6

what we are trying to estimate to test model

Question 7

regression

Answer 7

determining the relationship between a variable and one or more other variables

Question 8

linear regression

Answer 8

gives a set of observations, determine the equation of a line that can be used to describe the dataset

Question 9

types of error

Answer 9

error - estimated
mean error - average of errors
mean square error = same as mean but sum of errors are squared
root mean square error = same thing as MSE but taking the square root

Question 10

How do you know if r-square is accurate?

Answer 10

the closer to 1 it is the more accurate it is

Question 11

validation set

Answer 11

used to test a model

Question 12

why do we split validation and training sets

Answer 12

to learn about the data and test it

Question 13

class

Answer 13

category for data

Question 14

when would we want to use a class?

Answer 14

to identify a label for the data points

Question 15

what is the max of k

Answer 15

training size of dataset

Question 16

What is data normalization

Answer 16

organizing data to reduce redundancy. It is important with knn because the distance squares the difference in features

Question 17

regression model vs classification model

Answer 17

regression = numeric outcomes
classification = categorical outcomes

Question 18

what type of data can we use with KNN

Answer 18

numbers with categories, must prepare the data (like we did with car example in class)

Question 19

scatter plots are good to show change over time true or false

Answer 19

false

Question 20

how much data do you use to find K (max value of k?)

Answer 20

Set aside 80% of total data for K

Question 21

Knn and Bayes differences

Answer 21

Knn is based off euclidean distance and bayes is based on categorical data

Question 22

why do we use categorical for bayes

Answer 22

probability based

Question 23

why do we use numerical for knn

Answer 23

to measure the euclidean distance between the data

Question 24

what is the best chart for comparing 2 things

Answer 24

bar chart

Question 25

what is the best chart for finding proportions

Answer 25

pie chart

Question 26

shows the relationship between 2 variables

Answer 26

scatter plot

Question 27

what chart is used for change over time

Answer 27

line plot

Question 28

one hot encoding

Answer 28

001, etc

Question 29

euclidean distance equation

Question 30

what kind of data do we use for bayes classifiers

Answer 30

categorical but for features we must numeric it

Question 31

What affects the accuracy of a Bayes classifier?

Answer 31

assumption of features, the quality and size of the training data, feature relevance, distribution of features, class imbalance, parameter estimation, data preprocessing, outliers

Question 32

What is data imbalance, and why does that matter for Bayes classifiers?

Answer 32

biased predictions and unreliable probability estimates for minority classes