Research map / Probabilistic and scientific modeling / Variational and generative sampling
Estimation and Imputation in Probabilistic Principal Component Analysis with Missing Not At Random Data
Aude Sportisse, Claire Boyer, Julie Josse
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use the proposed MNAR-aware PPCA estimator instead of competing methods | PPCA with MNAR data · Synthetic data | imputation prediction error | Improved |
| Use the proposed MNAR-aware PPCA estimator instead of competing methods | PPCA with MNAR data · Synthetic data | loading-matrix RV coefficient | Improved |
| Use the proposed MNAR-aware PPCA estimator instead of competing methods | PPCA with MNAR data · Synthetic data | bias of mean, variance, and covariance estimates | Improved |
| Use the proposed MNAR-aware PPCA imputation instead of competing methods | PPCA with MNAR data · TraumaBase | imputation prediction error | Improved |
| Use the MAR-adapted estimator rather than the proposed MNAR estimator | PPCA with MNAR data · Synthetic data, low-dimensional example | imputation prediction error | Hurt |
| Use the MAR-adapted estimator rather than the proposed MNAR estimator | PPCA with MNAR data · Synthetic data, higher dimension | imputation prediction error | Hurt |
| Increase the percentage of missing values | Compared methods · Synthetic data | imputation performance | Mixed |
| Increase the noise level | Proposed MNAR estimator · Synthetic data | mean and variance estimation | No clear effect |
| Increase the noise level | Proposed MNAR estimator · Synthetic data | covariance estimation | Hurt |
| Misspecify the number of latent variables | Proposed MNAR estimator · Synthetic data | estimation and imputation performance | No clear effect |
| Generate data from a fixed-effect low-rank model instead of the assumed PPCA model | Proposed MNAR estimator · Synthetic data | estimation and imputation performance | No clear effect |
Closest papers by meaning
- Identification and Estimation for Nonignorable Missing Data: A Data Fusion Approach (ICML 2024 · similarity 0.88)
- Identifiable Generative models for Missing Not at Random Data Imputation (NeurIPS 2021 · similarity 0.87)
- From Predictive Methods to Missing Data Imputation: An Optimization Approach (JMLR 2018 · similarity 0.86)
- Random features models: a way to study the success of naive imputation (ICML 2024 · similarity 0.86)
- Distribution Shift in Missing Data Imputation: A Risk-Based Perspective and Importance-Weighted Correction under MAR (NeurIPS 2026 · similarity 0.85)
- DiffPuter: Empowering Diffusion Models for Missing Data Imputation (ICLR 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
