Estimator
An estimator is a rule, procedure, or computational model that uses data or measurements to produce an estimate of an unknown quantity, parameter, prediction, or state.
Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI
A scikit-learn-compatible object that implements model fitting and typically prediction or transformation operations.
- How it is used
- Provides a common fit-based interface for tabular modeling, validation, and interchangeable algorithms.
- How deep it goes
- Defines fitting, learned attributes, prediction, transformation, scoring, and cross-validation use without detailing estimator internals.
- Examples
- Uses LogisticRegression with small feature rows and labels, plus BaggingClassifier configured with DecisionTreeClassifier.
- What you can do after
- Apply it via Scikit-learn by fitting models, predicting or transforming new data, and passing models to cross-validation.
Read how Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI explains estimator →
Causal AI
An estimator is a statistic or rule that produces an estimate of an unknown population quantity.
- How it is used
- Deploys estimators after causal identification to compute estimates for selected estimands from observed data.
- How deep it goes
- Explains the query-estimand-estimator distinction and validation workflow, but defers detailed statistical mechanics to a chosen estimator.
- Examples
- Uses Bostonian mean height, MNIST digit probabilities, and DoWhy linear regression for a backdoor estimand.
- What you can do after
- Apply it via DoWhy by selecting an estimator for an identified estimand and checking estimates against synthetic-data ground truth.
Machine Learning Algorithms in Depth
An estimator is a rule that computes an approximation to an unknown statistical quantity from observed data or samples.
- How it is used
- Uses weighted samples from a proposal distribution to estimate expectations and ratios of normalization constants.
- How deep it goes
- Derives importance-sampling estimators, unbiasedness, variance, and consistency, stopping short of broader estimator theory.
- Examples
- Uses truncated Gaussian samples, density-ratio weights, a sinusoidal function, pseudocode, and numerical integration.
- What you can do after
- Apply importance sampling to estimate expectations from normalized or unnormalized target and proposal distributions.
Read how Machine Learning Algorithms in Depth explains estimator →
Related concepts
- point estimateproduces · A point estimate is a single numerical value used to estimate an unknown quantity or parameter.
- double machine learningused by · Double machine learning is a causal-effect estimation method that uses machine-learning nuisance models with orthogonalized estimation to reduce bias from nuisance-function errors.
- Scikit-Learn pipelinepart of · A scikit-learn pipeline is a composite estimator that sequentially chains named data transformations with a final estimator for fitting and prediction.
- fit methoduses · A fit method is an operation that learns or estimates model parameters, structure, or transformation statistics from supplied data.
- front-door estimandmeasures · A front-door estimand is a causal-effect quantity identified from observational data through a mediator that satisfies the front-door identification conditions.
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.