Binary outcome
A binary outcome is a result or response restricted to exactly two possible values or categories.
Statistics Every Programmer Needs
A binary outcome is a response variable with exactly two possible categories, conventionally represented by 0 and 1.
- How it is used
- Frames two-category decisions as prediction problems, including raisin classification and fourth-down conversion.
- How deep it goes
- Works through outcome encoding, sigmoid probabilities, thresholded predictions, and checks of fit and classification performance.
- Examples
- Uses encoded raisin varieties, observed-versus-predicted raisin records, and professional football fourth-down conversions.
- What you can do after
- Apply it via pandas and logistic regression to encode two classes, interpret predicted probabilities, and evaluate classification errors.
Read how Statistics Every Programmer Needs explains binary outcome →
Grokking Statistics
A binary outcome is an outcome restricted to two possible categories, such as yes and no.
- How it is used
- Frames yes-or-no observations for probability modeling and classification.
- How deep it goes
- Explains binary values and their modeling with logistic curves, while deferring the underlying mathematics.
- Examples
- Uses toddler meltdowns, hours without a nap, 0-or-1 observations, and a fitted probability curve.
- What you can do after
- Apply logistic regression to estimate a binary outcome's probability and classify it using a threshold.
Math and Architectures of Deep Learning
A trial result with exactly two possible states, here interpreted as success versus failure.
- How it is used
- Frames binary outcomes as the elementary events used to construct binomial probabilities.
- How deep it goes
- Defines two-state trials, calculates sequence probabilities, enumerates three trials, and connects the idea to PyTorch distribution code.
- Examples
- Uses celebrity-photo classification, success–failure sequences, and a three-trial probability table.
- What you can do after
- Apply it via PyTorch's Binomial distribution to evaluate log probabilities and compare sampled means and variances.
Read how Math and Architectures of Deep Learning explains binary outcome →
Statistics Slam Dunk
A binary target variable is an outcome variable restricted to exactly two possible values or categories.
- How it is used
- Frames yes-or-no analytical questions, such as whether a team qualifies for postseason play.
- How deep it goes
- Defines 0/1 coding and places binary outcomes in logistic regression, without detailing model mechanics.
- Examples
- Uses postseason qualification, regular-season wins, offense measures, and defense measures as modeling examples.
- What you can do after
- Apply it via logistic regression by coding group membership as 0 or 1 and relating it to predictors.
Related concepts
- filter contextproduced by · Filter context is a query-execution mode in which documents are tested for matching without calculating relevance scores.
- logistic regressionused by · Logistic regression is a statistical classification model that estimates categorical outcome probabilities by applying a logistic or softmax function to a linear combination of input features.
- binomial distributionused by · A binomial distribution is the probability distribution of the number of successes in a fixed number of independent trials, each with the same probability of success.
- thresholdproduced by · A threshold is a boundary value against which a quantity is compared to determine whether a condition is met or an action or decision is triggered.
- decision treeused by · A decision tree is a branching structure that represents sequential tests or choices, with paths leading to outcomes, predictions, or actions.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.