Test 3

Question 1

What term is used to describe or specify a sequence of decisions and consequences?

a.      Decision tree

b.     A parametric algorithm

c.      Output variable

d.     Leaf nodes

Question 2

In our advanced analytical theory and methods readings, which of the following is not a â modelâ discussed in our textbook?

a.      Scotterpot model

b.     Autoregressive model

c.      ARIMA model

d.     ARMA model

Question 3

Per our readings, which of the following is not a step in text analysis?

a.      Text mining

b.     Parsing

c.      Retrieval

d.     Clustering

Question 4

What is Brewerâ s theorem also known as?

a.      Replication Theorem

b.     D4I Theorem

c.      Distributed Theorem

d.     CAP Theorem

Question 5

Which of the following does not represent what Hadoop is or what is used for?

a.      An open-source framework

b.     Used for large-scale storage

c.      Used for Data processing

d.     Not compatible with commodity hardware

Question 6

From the following what best describes â Beyond Bag-of-Wordsâ ?

a.      A technique to start with

b.     Gathering information to ascertain data points

c.      Excluding certain words or common language

d.     Non-text representation

Question 7

Sharding is often transparent to the client but is not necessarily a requirement.

True

False

Question 8

Using differencing, _______ models allow nonstationary series to change into stationary series where seasonable and unseasonal ________ models can be used.

a.      Kalman filtering, spectral analysis

b.     ARIMA, ARMA

c.      Multivariate time series analysis, ARMA

d.     ARMAX, Kalman filtering

Question 9

What is one reason to measure the significance of a split in a decision true?

a.      Abnormal amount

b.     Inconsistent variety values

c.      A small gain in information

d.     Scale and ratio abnormalities

Question 10

What is â Term Frequency-Inverse document frequency (TFIDF)â widely used for?

a.      Select non-descriptive words for retrieval

b.     Information retrieval and text analysis

c.      Retrieve non-frequently used words for analysis

d.     Retrieve inconsistently used words

Question 11

Unlike logistic regression, naïve Bayes classifiers can handle _____________.

a.      Missing values

b.     Variables and participants

c.      Removal of data

d.     Reasonable guesses

Question 12

Which of the following is not part of the acronym ACID?

a.      Constraints

b.     Isolation

c.      Durability

d.     Atomicity

Question 13

Which of the following does not represent what Box-Jenkins Methodology and analysis does?

a.      A systemic method to identify, fitting, and checking data

b.     An approach using integrated autoregressive

c.      Moving average (ARIMA) time series models

d.     Random data points placed in a cluster

Question 14

The ________ of a node is the minimum number of steps required to reach a node from the root.

a.      Layer

b.     Depth

c.      Density

d.     Leaf

Question 15

What best describes time series analysis?

a.      Recording data points randomly

b.     Focus on intermittently selected data points

c.      Analyzing data points over a period

d.     Record data from inconsistent intervals

Question 16

Which of the following is not an example of a decision tree algorithm in our textbook?

C4.5

ID3

CART

ID.8

Question 17

Which of the following is not what is meant in replication of data/information.

a.      Storing of multiple copies

b.     Provides scalability

c.      Not used for peer-to-peer methods

d.     Ease of availability

Question 18

In general, what is the function of classification algorithms?

a.      Data analytics

b.     Data categorization

c.      Data technique

d.     Data classification

Question 19

Big data is not used to parallel data in a distributed fashion where it is stored.

True

False

Question 20

What is another name used to refer to text analysis?

a.      Parsing

b.     Repetition analysis

c.      Text analytics

d.     Text mining