On a least squares adjustment of a sampled frequency table when the expected marginal totals are known.
Für eine Gesamtheit des Umfangs \(N\) kennt man die Randwerte einer \(m\times n\)-Tafel, nicht aber ihre Zellenwerte. Aus der Gesamtheit wird eine Stichprobe des Umfangs \(n\) entnommen, für die alle Zellenwerte vorliegen, die aber stark vom Zufall beeinflußt sind. Als beste Schätzungen für die wahren Randsummen werden nun die im Verhältnis \(n : N\) verkleinerten Randsummen der Gesamtheit angenommen. Nach der Methode der kleinsten Quadrate werden die beobachteten Zellenwerte so korrigiert, daß sie den neuen Randbedingungen gehorchen. Die verbesserten Zellenwerte werden nun im Verhältnis \(N : n\) vergrößert. Die Ergebnisse dieser Operation gelten als beste Schätzungen für die unbekannten Zellenwerte der Gesamtheit.
- Classical iterative proportional scaling of log-linear models with rational maximum likelihood estimator
- Survey estimates by calibration on complex auxiliary information
- Calibration estimation in survey sampling
- On calibrated inverse probability weighting and generalized boosting propensity score models for mean estimation with incomplete survey data
- Marginal indirect standardization using latent clustering on multiple hospitals
- Regression-based network-flow and inner-matrix reconstruction
- Estimating cell frequencies under inequality constraints based on the Kullback-Leibler information
- A calibrated BISG for inferring race from surname and geolocation
- Intercensal updating using structure-preserving methods and satellite imagery
- Approximation theory, computing, and deep learning on the Wasserstein space
- A multiple imputation method using population information
- Using saturated count models for user-friendly synthesis of large confidential administrative databases
- On the identity of two solution algorithms of the `improved normalized squared differences' matrix adjustment model
- A note on convergence of calibration weights to inverse probability weights
- Improving survey inference using administrative records without releasing individual-level continuous data
- Exponential convergence of general iterative proportional fitting procedures
- On the contraction properties of Sinkhorn semigroups
- An algorithm for reconciling indicators across multiple dimensions: weighted iterative proportional fitting
- Improving survey inference in two-phase designs using Bayesian machine learning
- Using the stylized U-shaped trend as an empirical selection criterion for homophily measures
This page was built for publication: On a least squares adjustment of a sampled frequency table when the expected marginal totals are known.
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2587677)
