Question 1

Misclassifying an actual __________ observation as a(n) __________ observation is known as a false positive.

Accepted Answer

A false positive occurs when an actual Class 0 (negative) observation is incorrectly classified as a Class 1 (positive) observation.

Question 2

__________ is dividing the sample data into three sets for training, validation, and testing of the data mining algorithm performance.

Accepted Answer

Data partitioning involves dividing the sample data into three sets for training, validation, and testing of the data mining algorithm performance. Data sampling refers to the process of selecting a representative subset from the larger dataset. Data preparation involves cleaning, transforming, and pre-processing data. Model assessment refers to evaluating the predictive power and accuracy of the model.

Question 3

A(n) __________ is often displayed as a row of values in a spreadsheet or database in which the columns correspond to the variables.

Accepted Answer

A record is a complete set of information about a single entity, often displayed as a row of values in a spreadsheet or database in which the columns correspond to the variables. Each record contains a unique identifier and the values associated with that identifier for each variable.

Question 4

The percent of misclassified records out of the total records in the validation data is known as the

Accepted Answer

The overall error rate is calculated as the percent of misclassified records out of the total records in the validation data. This is a common metric used to evaluate the performance of a machine learning model. Option B, error, is too general and does not specify the type or scope of the error. Option C, accuracy, is the complement of the error rate, meaning it measures the percent of correctly classified records. Option D, class, is not relevant to this context.

Question 5

As we increase the cutoff value, _______ error will decrease and _________ error will rise.

Accepted Answer

As we increase the cutoff value, we will classify more instances as Class 0, which will decrease the Class 0 error. However, this will also increase the Class 1 error, as more instances that should have been classified as Class 1 will be misclassified as Class 0. Therefore, increasing the cutoff value will decrease one type of error (Class 0) and increase the other type of error (Class 1).

Question 6

__________ involves descriptive statistics, data visualization, and clustering.

Accepted Answer

Data exploration involves using descriptive statistics, data visualization, and clustering to gain a better understanding of the data and identify any patterns or relationships. Data partitioning involves dividing the data set into subsets for training and testing a model. Data preparation involves cleaning, transforming, and encoding the data for analysis. Model assessment involves testing the performance of a model on a new set of data.

Question 7

__________ is one minus the Class 0 error rate.

Accepted Answer

Specificity is one minus the Class 0 error rate, as it measures the proportion of actual negatives that are correctly identified.

Question 8

__________ is the manipulation of the data with the goal of putting it in a form suitable for formal modeling.

Accepted Answer

Data preparation involves cleaning, transforming, and structuring the data so that it can be used for analysis and modeling. This includes tasks such as removing missing values, encoding categorical variables, and scaling numerical variables. Data sampling and partitioning refer to the division of the data into subsets for training and testing purposes, while model assessment refers to the evaluation of the performance of a model on a given dataset.

Question 9

__________ is the step in data mining that includes addressing missing and erroneous data, reducing the number of variables, defining new variables, and data exploration.

Accepted Answer

Data preparation is the step in data mining that involves handling missing and erroneous data, reducing the number of variables, defining new variables, and exploring the data to check for any patterns or trends. The other options (A, B, D) are steps that come after data preparation in the data mining process.

Question 10

__________ is NOT a step of the data mining process.

Accepted Answer

Supervised learning is actually a type of machine learning algorithm that is used in the model construction step of the data mining process. Therefore, it is not a step of the data mining process itself. Data sampling, data partitioning, and model construction are all important steps of the data mining process.

Question 11

Determine a freshman's likely first-year grade point average from the student's Scholastic Aptitude Test (SAT) score, high school grade point average, and number of extra-curricular activities. This is an example of

Accepted Answer

The question is asking to determine a likely first-year grade point average, which is a continuous outcome. Therefore, the best choice is estimation of a continuous outcome (option B). Classification of a categorical outcome (option A) would be appropriate if the question was asking to predict whether a freshman would pass or fail a class based on their SAT score, high school GPA, and number of extra-curricular activities. Prediction of a categorical outcome (option C) would apply if the question was asking to predict which major a freshman would choose based on their SAT score, high school GPA, and number of extra-curricular activities. Unsupervised learning (option D) involves finding patterns in data without a specific outcome to predict, which is not relevant to this question.

Question 12

A characteristic or quantity of interest that can take on different values is a(n)

Accepted Answer

A variable is a characteristic or quantity of interest that can take on different values. Options B, C, and D do not accurately describe this concept.

Question 13

__________ is a category of data mining techniques in which an algorithm learns how to classify or estimate an outcome variable of interest.

Accepted Answer

In supervised learning, the algorithm is given labeled data with a known outcome variable, and learns how to predict or classify that variable based on the input variables. This is in contrast to unsupervised learning, which involves finding patterns or relationships in data without any predetermined outcome variable. Dimension reduction and data sampling are techniques used in both supervised and unsupervised learning.

Question 14

Applying descriptive statistics and data visualization to the training set to understand the data and assist in the selection of an appropriate technique is a part of

Accepted Answer

Applying descriptive statistics and data visualization is a part of data exploration, which helps in understanding the data better and selecting appropriate techniques for analysis. Data partitioning is dividing the data into training and testing sets, data preparation involves cleaning and transforming the data, and model assessment is evaluating the performance of the model on the test set.

Question 15

Data mining methods for classifying or estimating an outcome based on a set of input variables is referred to as

Accepted Answer

Supervised learning is the data mining method used for classifying or estimating an outcome based on a set of input variables. Unsupervised learning involves finding patterns or grouping data without a known outcome, dimension reduction is the process of reducing the number of variables in a dataset, and data sampling involves selecting a subset of data from a larger dataset.

Question 16

The set of recorded values of variables associated with a single entity is a(n)

Accepted Answer

An observation is a set of recorded values of variables associated with a single entity.

Question 17

Estimation methods are also referred to as

Accepted Answer

Estimation methods involve predicting or forecasting a value or outcome based on available data. Therefore, the best choice is A as it accurately describes the purpose of estimation methods. Clustering methods are used to group similar data points, association methods are used to identify relationships between variables, and supervised methods involve training algorithms with labeled data to predict outcomes for new data.

Question 18

Data used to build a data mining model is called

Accepted Answer

The data used to build a data mining model is called training data. This is the data used to teach the model to recognize patterns and make predictions. Validation data is used to evaluate the accuracy of the model during the training process, and test data is used to evaluate the accuracy of the final model after it has been built. Exploration data refers to the initial data exploration phase, where data is analyzed and cleaned before building a model.

Question 19

Classifying a record as belonging to one class when it belongs to another class is referred to as a(n)

Accepted Answer

Classifying a record as belonging to one class when it actually belongs to another class is an error.

Question 20

__________ is a method of extracting data relevant to the business problem under consideration. It is the first step in the data mining process.

Accepted Answer

Data sampling is the process of selecting a representative subset of data from a larger dataset. This is the first step in data mining as it helps to identify patterns and relationships within the data that are relevant to the business problem being solved. Other options like data partitioning, model construction, and model assessment come after this step.

Quiz 9: Predictive Data Mining

Misclassifying an actual observation as a(n) observation is known as a false positive.