Logit

As explained in Grokking Statistics

The logit function maps a probability to the natural logarithm of its odds, log(p/(1-p)).

The logit turns a probability into the natural logarithm of its odds: first compute p/(1−p), then take ln of that result. Unlike probability, log-odds can range across the whole number line. section 8.4

Use the logit to connect probability, odds, and logistic regression:

• Probability describes how likely an event is; odds compare its likelihood with its non-occurrence. section 8.4
• The logit of a logistic-function output matches the model’s linear component, β0 + β1x. section 8.4
• An odds ratio describes how the odds change per unit of x, making model effects easier to compare. section 8.4

A toddler-meltdown risk

At four hours, a logistic model gives a meltdown probability of about 0.8532. Its odds are about 5.813 to 1; taking the natural logarithm of those odds produces the same value as β0 + β1x. section 8.4

Figure 8.6 Comparing the logistic function (the S-curve) with the log-odds function (the straight line). Note that when the log-odds line crosses y = 0, the sigmoid function has a value of y = 0.5.

Compare the logistic S-curve with the straight log-odds line; where the line crosses zero, the logistic function equals 0.5. section 8.4

How Grokking Statistics covers it

How deep it goes

Connects definition, worked numbers, Python verification, and curve behavior without developing a formal derivation.

Examples

Uses toddler-meltdown probabilities at four and six hours, coefficient calculations, Python listings, and a curve comparison.

What it assumes

Assumes familiarity with probability and odds while reviewing their conversion before applying the logit.

What you can do after

Evaluate logistic-regression outputs by converting probabilities to odds and checking their logit against β0 + β1x.

How it connects

Connects probability, odds, odds ratios, logistic regression, and the sigmoid function.

liveBookmanning.com

Read Grokking Statistics on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Statistics Slam DunkLog odds is the natural logarithm of the odds of an event, equal to the logarithm of its probability divided by its failure probability.
• 

  liveBookmanning.com
  Optimization Algorithms: AI techniques for design, planning, and control problemsA logit is an unnormalized output score produced by a model before conversion into class probabilities.
• 

  liveBookmanning.com
  Machine Learning for Tabular Data: XGBoost, Deep Learning, and AIThe logit function maps a probability in (0,1) to its log-odds and is the inverse of the logistic sigmoid.
• 

  liveBookmanning.com
  Natural Language Processing in Action, Second EditionA logit is an unconstrained real-valued score obtained by applying the inverse of the logistic or softmax probability transformation.
• 

  liveBookmanning.com
  LLMs in ProductionA logit is an unnormalized real-valued score assigned to a candidate token before probability normalization.
• 

  liveBookmanning.com
  Deep Learning with PyTorch, Second EditionUnnormalized model scores produced before applying a probability normalization such as softmax, used here as the direct input to cross-entropy loss.
• 

  liveBookmanning.com
  Learn Generative AI with PyTorchAn unnormalized model output score produced before conversion to probabilities for sampling or selection.
• 

  liveBookmanning.com
  Starting Data Analytics with Generative AI and PythonLog-odds are the natural logarithm of the odds of an event or ordered outcome category.
• 

  liveBookmanning.com
  Ensemble Methods for Machine LearningLog-odds are the natural logarithm of the odds of an event.
• 

  liveBookmanning.com
  Server-Side WebAssemblyA logit is an unnormalized score produced for a candidate class or token before conversion into probabilities.
• 

  liveBookmanning.com
  Build a Large Language Model (From Scratch)The model’s unnormalized output scores over the vocabulary before conversion to probabilities or token selections.
• 

  liveBookmanning.com
  Build a Text-to-Image Generator (from Scratch)A logit is an unnormalized real-valued score assigned to a class before conversion into probabilities.
• 

  liveBookmanning.com
  Math and Architectures of Deep LearningA vector of unnormalized class scores produced by a classifier before conversion to probabilities.
• 

  liveBookmanning.com
  Statistics Every Programmer NeedsLog odds are the natural logarithm of the odds of an event, calculated as the logarithm of its probability divided by the complement probability.
• 

  liveBookmanning.com
  Hugging Face in ActionA logit is an unnormalized model output representing evidence for a class before conversion into normalized probabilities.
• 

  liveBookmanning.com
  Financial AI in PracticeThe logarithm of the ratio of an event’s probability to the probability of its complement.

Compare how 17 books explain logit →

Related concepts

• temperatureused by · A temperature parameter adjusts the concentration of a probability distribution, affecting sampling randomness or the likelihood of accepting less favorable transitions.
• softmaxused by · Softmax is a function that exponentiates a vector of scores and normalizes the results into nonnegative values that sum to one.
• linear layerproduced by · A linear layer is a neural-network layer that maps input features to outputs by a learned affine transformation, typically connecting each output to every input feature.
• language modelproduced by · A language model is a computational model that represents patterns in linguistic tokens to estimate sequence probabilities and predict or generate language from context.
• regression coefficientmeasured by · A regression coefficient is a model parameter that quantifies a predictor’s contribution to a regression model’s output, conditional on other model terms.
• sigmoidequivalent to · A sigmoid is a smooth, bounded, S-shaped function that maps real-valued inputs between two limiting values, commonly zero and one.

This explainer was generated by Manning's knowledge graph from the text of Grokking Statistics. The section links point to the parts of the book it draws on.