The study introduces backward baselines to distinguish past prediction from future prediction in machine learning models.
problem Differentiating between past and future prediction in machine learning models.
method Theoretical, empirical, and normative arguments support a family of simple and efficient statistical tests called backward baselines.
result The study provides a meaningful backward baseline for auditing black-box prediction systems.
Surveying machine learning methods for economic forecasting.
problem Improving accuracy of economic forecasts using machine learning.
method Nowcasting, textual data, panel and tensor data, high-dimensional Granger causality tests, time series cross-validation, classification with economic losses.
result Recent advances in machine learning methods enhance economic forecasting accuracy.
R package xtdml uses DML for panel data models with fixed effects.
problem Estimating structural parameters in panel data models with fixed effects.
method Combines machine learning with statistical estimation for inference.
result Demonstrates improved performance in learning nuisance functions.
Develops privacy-preserving methods for longitudinal linear regression.
problem Protecting individual information in longitudinal data with privacy-preserving statistics.
method Proposes a user-level private regression estimator and a privatized covariance estimator for longitudinal linear regression under user-level differential privacy.
result Establishes theoretical guarantees for practical user-level differential privacy estimation and inference in longitudinal linear regression.
Simple method for estimating missing panel data entries with confidence intervals.
problem Estimating missing values in panel data with staggered adoption.
method Simple matrix algebra and singular value decomposition for estimation, with data-driven confidence intervals.
result Confidence intervals match non-asymptotic lower bounds, proving instance optimality.
GANs improve longitudinal data imputation but face challenges in missing data and class imbalance.
problem Missing data and class imbalance in longitudinal data.
method GANs applied to longitudinal data imputation (LDI).
result GANs show potential but need more versatile approaches.
Over the years, several studies have demonstrated that there exist significant disparities in health indicators in the United States population across various groups. Healthcare expense is used as a proxy for health in algorithms that drive healthcare systems and this exacerbates the existing bias. In this work, we foc…
We analyze three sets of income data: the US Panel Study of Income Dynamics PSID), the British Household Panel Survey (BHPS), and the German Socio-Economic Panel (GSOEP). It is shown that the empirical income distribution is consistent with a two-parameter lognormal function for the low-middle income group (97%-99% of …
Proposes a robust EM algorithm for analyzing incomplete panel count data.
problem Missing reports in panel count data.
method Functional EM algorithm for non-parametric counting process mean function estimation.
result Robust to misspecification of Poisson process assumption and missing completely at random.
Study uses 1D-CNNs to forecast mortality in ELSA survey.
problem Forecasting mortality in the middle-aged and older population.
method 1D-CNNs applied to longitudinal data with various over/undersampling and activation functions.
result Swish nonlinearity outperforms other functions in forecasting mortality.
Missing data is a common problem in real-world settings and particularly relevant in healthcare applications where researchers use Electronic Health Records (EHR) and results of observational studies to apply analytics methods. This issue becomes even more prominent for longitudinal data sets, where multiple instances …
Survey on factor models and their applications in econometrics.
problem Estimating low-rank structures in high-dimensional models.
method Low-rank recovery techniques for factor model estimation.
result New insights into factor model applications in econometrics.
Digital personas improve survey results for stable attributes but fail for subjective responses.
problem When can digital personas reliably approximate human survey findings?
method Using LISS panel, constructed personas from background variables and survey histories, tested against held-out post-cutoff answers.
result Digital personas improve alignment with human response distributions for stable attributes but fail for subjective responses.
Study uses ML to predict non-participation in ELSA COVID-19 follow-up studies.
problem Predicting non-participation in follow-up surveys due to various factors.
method Used machine learning algorithms including KNN, RF, AdaBoost, logistic regression, NN, and SVC.
result Random Forest (RF) outperforms other models in balanced accuracy.
The paper introduces tests for missing data models based on graph assumptions.
problem Verification of assumptions in missing data models is insufficiently addressed.
method The paper explores three classes of missing data models and designs goodness-of-fit tests.
result The paper provides new insights and tests for missing data graphical models.
Proposes a machine learning predictor for survey data.
problem Limited integration of machine learning in traditional surveys.
method Predictor supported by machine learning algorithms, analyzing departures from model assumptions.
result Machine learning predictors are a good alternative, even under small departures from model assumptions.
Financial planners helped preserve and increase household net financial assets during the Great Recession.
problem Impact of financial planners on household net financial assets during the Great Recession.
method Utilized 2007-2009 Survey of Consumer Finances (SCF) panel dataset, analyzed 3,862 respondents.
result Starting to use a financial planner during the Great Recession had a positive impact on preserving and increasing household net financial assets.
The paper improves machine learning for heavy-tailed panel data.
problem Improving estimates for financial and economic data with fat tails.
method Sparse-group LASSO regularization and Fuk-Nagaev concentration inequality.
result Oracle inequalities for panel data estimators.
New method tests Granger non-causality in panel data with cross-sectional dependencies.
problem Testing Granger non-causality in panel data with cross-sectional dependencies.
method Proposes a new approach to aggregate p-values from panel members to test Granger non-causality, showing lower FDR.
result Our approach discovers true causal relations in panel data, unlike state-of-the-art methods.
Survey of de Casteljau's algorithm's applications in geometric data analysis.
problem No specific problem stated; focuses on algorithm applications.
method Constructive approach to generalize parametric smooth curves to manifolds.
result Algorithm provides principled way to analyze geometric data.
A tutorial on various methods for clustering longitudinal data.
problem Identifying groups with different trends in longitudinal data.
method Group-based trajectory modeling, growth mixture modeling, longitudinal k-means.
result Strengths, limitations, and model extensions of the methods are discussed.
Paper develops a new estimator for panel data with endogenous treatments, improving causal inference.
problem Challenges in causal inference for static panel data with endogenous treatments and confounding variables.
method Develops Double Machine Learning (DML) estimator for static panel models with endogenous treatments (panel IV DML). Introduces weak-identification diagnostics.
result Panel IV DML estimator improves estimation accuracy and delivers more reliable inference under weak identification.
LPCI provides valid prediction intervals for longitudinal data.
problem Current conformal prediction methods for time series data lack cross-sectional coverage when applied to longitudinal datasets.
method Modeling residual data as a quantile fixed-effects regression problem, constructing prediction intervals with a trained quantile regressor.
result LPCI achieves valid cross-sectional coverage and outperforms existing benchmarks in terms of longitudinal coverage rates.
New method for estimating heterogeneous treatment effects in panel data.
problem Estimating heterogeneous treatment effects in non-stationary, temporally dependent panel data.
method Proposes H1SL and H2SL, synthetic learners for panel data, based on existing non-panel data estimators.
result Established convergence rates for proposed estimators and demonstrated superior performance.
Motivated by applications in architecture and design, we present a novel method for increasing the developability of a B-spline surface. We use the property that the Gauss image of a developable surface is 1-dimensional and can be locally well approximated by circles. This is cast into an algorithm for thinning the Gau…
A new method for online prediction uncertainty quantification in non-exchangeable panel data.
problem Challenges in quantifying predictive uncertainty for non-exchangeable panel data.
method Online conformal prediction framework for non-exchangeable panel data, using similarity weights and adaptive miscoverage levels.
result Improves coverage on worst-covered target units through adaptive interval-width allocation.
Estimates mean and covariance for large, unbalanced stock returns panels.
problem Estimating mean and covariance in large, unbalanced panel data.
method Nonparametric, kernel-based joint estimator for conditional mean and covariance matrices.
result The idiosyncratic risk explains more than 75% of cross-sectional variance.
Proposes CoDEAL for estimating heterogeneous treatment effects in panel data models.
problem Estimating heterogeneous treatment effects in causal panel data models with covariate effects.
method Covariate-Adjusted Deep Causal Learning (CoDEAL) integrating neural networks and autoencoders.
result Establishes theoretical guarantees and demonstrates compelling performance in simulations and real data.
Paper uses machine learning for nowcasting corporate earnings from mixed-frequency data.
problem Predicting corporate earnings for a large cross-section of firms with different frequency data.
method Structured machine learning regressions with sparse-group LASSO regularization for panel data.
result Machine learning models outperform traditional methods in nowcasting corporate earnings.
The 2007 Midwest Geometry Conference included a panel discussion devoted to open problems and the general direction of future research in fields related to the main themes of the conference. This paper summarizes the comments made during the panel discussion.
Estimates heterogeneous treatment effects in panel data with a new method.
problem Estimating heterogeneous treatment effects in panel data with general treatment patterns.
method Partition observations into clusters with similar treatment effects using a regression tree, then estimate average treatment effects for each cluster.
result Our method achieves superior accuracy compared to alternative approaches.
Improved causal inference with panel data using deep learning.
problem Causal inference challenges in social science with panel data.
method Adapted N-BEATS deep neural architecture for time series forecasting.
result SyNBEATS estimator outperforms existing methods in panel data settings.
The paper develops coresets for panel data regression problems.
problem Efficiently summarize panel data regression problems.
method Introduced coreset construction for panel data regression problems using the Feldman-Langberg framework.
result Constructs coresets of size polynomial in 1/ε and number of parameters, independent of panel data size. Improved forecasting of investment dynamics across heterogeneous panels using a two-stage model.
problem Forecasting investment dynamics in heterogeneous panels with varying dynamics.
method Two-stage architecture: global pooled AR(1) for shared persistence, local models for residual dynamics.
result Significant improvement in out-of-sample R2 from 0.630 to 0.677, with a gain of 0.047. Method for factor analysis in short panels without assuming sphericity or Gaussianity.
problem Factor analysis in short panels without assuming sphericity or Gaussianity.
method Pseudo maximum likelihood method and asymptotically uniformly most powerful invariant test.
result Systematic risk explains a large part of cross-sectional total variance in bear markets but is not spanned by observed factors.
Paper develops a new estimator for high-dimensional panel data with common shocks.
problem Cross-sectionally dependent errors driven by common shocks in high-dimensional panel data.
method Factor-augmented sparse-group LASSO estimator combining MIDAS aggregation with latent factors.
result The estimator outperforms standard LASSO for prediction and estimation in settings with cross-sectional dependence.
Gradient boosting algorithm for spatial panel models improves estimation in high-dimensional settings.
problem Estimation failure in high-dimensional spatial panel models.
method Model-based gradient boosting algorithm for spatial panel models with random and fixed effects.
result Feasibility and interpretability in both low- and high-dimensional settings.
Study compares resampling methods for rare event prediction in longitudinal studies.
problem Predicting rare events in longitudinal follow-up studies.
method Comparison of resampling methods to improve standard regression models.
result Effect of sampling rate on model predictive performance.
Flexible variable selection handles missing data for better biomarker panels.
problem Identifying relevant features from incomplete data sets.
method Nonparametric variable selection combined with multiple imputation.
result Improved biomarker panels with higher classification and variable selection performance.
The paper tackles temporal coverage bias in financial panel data, proposing a structuring framework to correct for incomplete histories.
problem Incomplete histories of financial instruments lead to biased panel data.
method Formalizes the problem and proposes a coverage-aware structuring framework using structured metadata and an availability matrix.
result The framework reveals substantial distortions in return dynamics and volatility when naive temporal alignment is used.
latrend simplifies longitudinal clustering for numeric measurements.
problem Clustering of longitudinal data to identify common trends over time.
method Unified framework for applying various clustering methods.
result Facilitates comparison and rapid prototyping of new methods.
New method models longitudinal data using variational inference and normalizing flows.
problem Handling high-dimensional longitudinal data with time dependency.
method Variational inference with normalizing flows for latent variables.
result The method achieves better likelihood estimates and more reliable missing data imputation.
Causalfe estimates treatment effects in panel data with fixed effects.
problem Spurious heterogeneity in treatment effect estimates due to fixed effects in panel data.
method CFFE approach with node-level residualization during tree construction.
result Validates the estimator's performance through simulation studies.
We analyze linear factor models for asset pricing panels.
problem Characterizing cross-sectional and inter-temporal properties of returns and factors.
method Conditional means and covariances, review of Kozak and Nagel (2024) conditions.
result Low-dimensional factor portfolios can span efficient portfolios in unbalanced panels.
Micro-panel data are collected and analysed in many research and industry areas. Cluster analysis of micro-panel data is an unsupervised learning exploratory method identifying subgroup clusters in a data set which include homogeneous objects in terms of the development dynamics of monitored variables. The supply of cl…
Deep neural networks are a family of computational models that have led to a dramatical improvement of the state of the art in several domains such as image, voice or text analysis. These methods provide a framework to model complex, non-linear interactions in large datasets, and are naturally suited to the analysis of…
We present the first framework for Gaussian-process-modulated Poisson processes when the temporal data appear in the form of panel counts. Panel count data frequently arise when experimental subjects are observed only at discrete time points and only the numbers of occurrences of the events between subsequent observati…
Optimal tensor PCA for estimating factors and loadings in high-dimensional panel data.
problem Estimating factors and loadings in high-dimensional panel data with non-negligible correlations.
method Tensor Principal Component Analysis (TPCA) for estimating factors and loadings in a tensor factor model.
result Simple TPCA is optimal for strong factors and can be improved for weak factors with alternating least-squares iterations.