Predictive Analytics

Question 1

Marital status and eye color are examples of what sort of data?

Answer 1

Nominal scales - categorical data divided into distinct categories

Question 2

Survey responses (e.g. strong agree, agree, neutral…) are examples of what sort of data?

Answer 2

Ordinal scales - categorical data that aims to rank data in a specific order

Question 3

What are the three patterns of missing data?

Answer 3

MCAR - Missing completely at random
MAR - Missing at random
MNAR - Missing not at random

Question 4

Data missing due to test sensors losing connectivity is an example of which missing data pattern?

Answer 4

MCAR - Missing completely at random

Question 5

Assuming more women than men will answer a survey regarding skin routine would create an example of which missing data pattern?

Answer 5

MAR - Missing at random

Question 6

When there is a pattern to the missing data however it is not on the primary dependent variable is a trait of which missing data pattern?

Answer 6

MAR - Missing at random

Question 7

Data missing due to patients refusing to disclose info on sensitive topics is an example of which missing data pattern?

Answer 7

MNAR - Missing not at random

Question 8

A __________ is a supposition or observation regarding the results of sampling data.

Answer 8

Hypothesis

Question 9

The null hypothesis being rejected in error when it is actually true is which type of error?

Answer 9

Type I error

Question 10

The null hypothesis is not rejected in error when it is actually false is which type of error?

Answer 10

Type II error

Question 11

This statistic is used for normally distributed data and a known population standard deviation.

Answer 11

z-statistic

Question 12

This statistic is used for normally distributed data and an unknown population standard deviation.

Answer 12

t-statistic

Question 13

T/F: P-values measure the probability that the null hypothesis is true.

Answer 13

False

Question 14

Which statistical summary value provides the measure of location, or central tendency?

Answer 14

Arithmetic mean

Question 15

The _______ is the middle number in a set of observations that are in order.

Answer 15

Median

Question 16

The _______ is the number in a set of observations that occurs most often.

Answer 16

Mode

Question 17

The _______ measure the spread of the distribution of a set of observations.

Answer 17

Standard deviation

Question 18

Most often in predictive modeling, _______ is considered in the context of normal distributions and provides a measure of statistical dispersion.

Answer 18

Standard deviation

Question 19

Which statistical summary measurement measures the balance of a distribution?

Answer 19

Skewness

Question 20

_______ measures the shape (how fat or thin compared to a normal distribution) of the distribution.

Answer 20

Kurtosis

Question 21

_______ is a measure of the numerical relationship of one variable to another.

Answer 21

Correlation

Question 22

What does PCA stand for?

Answer 22

Principal component analysis

Question 23

From chapter 3, what are the three key measures of central tendency?

Answer 23

Mean, median, mode

Question 24

From chapter 3, what are the five key measures of variability?

Answer 24

Standard deviation, variance, range, kurtosis, and skewness

Question 25

As a measure of central tendency the _______ is not influenced by outliers.

Answer 25

Median

Question 26

What is the average of the squared deviations of each observation from the mean?

Answer 26

Variance

Question 27

What is the square root of the variance?

Answer 27

Standard deviation

Question 28

The _______ is the most widely used transformation method to deal with skewed data.

Answer 28

Logarithmic function

Question 29

By _______ data there is a loss of information and power and, if not necessary, it should be avoided.

Answer 29

Binning

Question 30

An r-squared value of 0.25 indicates what?

Answer 30

That 25% of the variation in target variable (y) is explained by the input variable (x)

Question 31

_______ identifies the correlations and covariances between the input variables and creates groups or clusters of similar variables.

Answer 31

Variable clustering

Question 32

When using variable clustering, the clusters are determined by calculating the _______ distance.

Answer 32

Euclidean distance

Question 33

When using variable clustering, the _______ is the average of the points in the cluster; a representative point that lies at the center.

Answer 33

Centroid

Question 34

The _______ for a given cluster measures the variance in all the variables.

Answer 34

Eigenvalue

Question 35

_______ is a variable reduction strategy that is used when there are several redundant variables or variables that are correlated with one another and may be measuring the same construct.

Answer 35

Principal component analysis (PCA)

Question 36

The _______ defines the condition that the researchers need to discredit before suggesting an effect exists.

Answer 36

Null hypothesis

Question 37

Regression analysis is _______; meaning it comes from a population that follows a probability distribution based on a fixed set of parameters.

Answer 37

Parametric

Question 38

What are the five common assumptions that must be validated for a model to generate good results?

Answer 38

1. Linearity 2. Independence : No multicollinearity 3. Constant variance : Homoskedasticity 4. Autocorrelation 5. Normality

Question 39

Which assumption states there should be a linear relationship between the target and input variables?

Answer 39

Linearity

Question 40

Which assumption states the input variables should not be correlated?

Answer 40

Independence : No multicollinearity

Question 41

_______ assumes that the variance of a variable is constant across all values of another variable.

Answer 41

Homoskedasticity (constant variance)

Question 42

_______ occurs when one data point in a variable is dependent on another data point within the same variable.

Answer 42

Autocorrelation

Question 43

Which assumption assumes the error terms are normally distributed for any given value of the input variables with a mean of zero?

Answer 43

Normality

Question 44

According to chapter 4, what are the three common metrics to evaluate the strength of a regression line?

Answer 44

1. R-squared 2. Adjusted r-squared 3. P-value

Question 45

Which regression evaluation metric provides the percentage variation in the target variable explained by the input variables?

Answer 45

R-squared (coefficient of determination)

Question 46

Which regression evaluation metric integrates the model's degrees of freedom as a means of adjustment?

Answer 46

Adjusted r-squared

Question 47

T/F When using multiple linear regression, the adjusted r-squared should always be used over the r-squared value.

Answer 47

TRUE

Question 48

Generally, a p-value less-than-or-equal-to _______ indicates strong evidence against the null hypothesis.

Answer 48

0.05