Armin Schwartzman

The paper introduces a decomposed FVE estimation framework to improve heritability estimates by accounting for heavy-tailed SNP effects and violations of the bounded-kurtosis condition.

The paper introduces a conditional SNP-heritability method to estimate heritability across subpopulations with different ancestral and environmental factors, showing how heritability of intelligence scores varies by socio-economic group.

This paper introduces a method to quantify uncertainty in drift diffusion models of decision making, accounting for temporal dependence and parameter variability, and applies it to rat behavior in a visual task.

This study compares models to estimate how much variance in crystallized intelligence is explained by cortical surface area in adolescents using ABCD data.

This study argues that fixing the intercept in LDSC improves SNP heritability estimation by reducing bias and variance, but LDSC remains biased under population stratification.

This paper introduces two methods to estimate timescales in resting-state fMRI, showing the time-domain method is more accurate and provides valid statistical inference with Python implementations.

The paper develops a method to construct simultaneous confidence regions for fMRI data across all activation thresholds and validates it using simulations and real data.

The paper evaluates resampling methods for neuroimage topological features, finding that wild bootstrap and permutation perform well in larger samples, while GRF-based methods have inflated error rates.

The paper applies a Bayesian multivariate growth mixture model to identify cognitive decline patterns in Alzheimer's Disease Neuroimaging Initiative data.

This paper introduces spatial Confidence Sets for effect size images in fMRI to address limitations in statistical inference and improve activation localization.

The paper develops spatial confidence sets for raw effect size images in fMRI to address limitations of traditional hypothesis testing by providing confidence intervals for effect sizes.

The paper introduces a method to calculate p-values and control FDR in neuroimaging without requiring a pre-threshold, using a signal-plus-noise model and exact peak height distribution.

The paper introduces a consistent estimator for heritability in GWAS using summary statistics, accounting for linkage disequilibrium and enabling analytical precision.