Chapter 7 Data Analysis and Presentation

exploratory data analysis

An approach to examining data that seeks to explore the data without testing formal models or hypotheses.

outlier

A data point, or a few data points, that lie an abnormal distance from other values in the data.

visualization

Any visual representation of data, such as a graph, diagram, or animation; called a viz for short.

confirmatory data analysis

Testing a hypothesis and providing statistical evidence of the likelihood that the evidence refutes or supports a hypothesis.

null hypothesis

A proposed explanation worded in the form of an equality, meaning that one of the two concepts, ideas, or groups will be no different than the other concept, idea, or group.

alternative hypothesis

A proposed explanation worded in the form of an inequality, meaning that one of the two concepts, ideas, or groups will be greater or less than the other concept, idea, or group.

type I error

The incorrect rejection of a true null hypothesis.

type II error

The failure to reject a false null hypothesis.

effect size

A quantitative measure of the magnitude of the effect.

categorical data

Data items that take on a limited number of assigned values to represent different groups.

training dataset

A subset of data used to train a model for future prediction.

test dataset

A subset of data not used for the development of a model but used to test how well the model predicts the target outcome.

data overfitting

When a model is designed to fit training data very well but does not predict well when applied to other datasets.

classification analyses

Techniques that identify various groups and then try to classify new observations into one of those groups.

machine learning

An application of artificial intelligence that allows computer systems to improve and update prediction models without explicit programming.

supervised machine learning

A type of machine learning algorithm that uses labeled datasets to train, classify, and predict outcomes accurately.

unsupervised machine learning

A type of machine learning algorithm that uses unlabeled datasets to analyze datasets.

reinforcement machine learning

A type of machine learning algorithm that is trained to achieve specific outcomes by only rewarding or punishing the algorithm as it strives to achieve a desired outcome.

extrapolation beyond the range

A process of estimating a value beyond the range of the data used to create the model.

simplification

In design, making a visualization easy to interpret and understand.

emphasis

In design, assuring the most important message is easily identifiable.

ethical data presentation

Avoiding the intentional or unintentional use of deceptive practices that can alter the user's understanding of the data being presented.

visual weight

In design, the amount of attention an element attracts.

data ordering

The intentional arranging of visualization items in a way to produce emphasis.

data deception

A graphical depiction of information, designed with or without an intent to deceive, that may create a belief about the message and/or its components, which varies from the actual message.