DePaul University

About: DePaul University is a education organization based out in Chicago, Illinois, United States. It is known for research contribution in the topics: Population & Context (language use). The organization has 5658 authors who have published 11562 publications receiving 295257 citations.

Banded and Tapered Estimates for Autocovariance Matrices and the Linear Process Bootstrap

Abstract: We address the problem of estimating the autocovariance matrix of a stationary process. Under short range dependence assumptions, convergence rates are established for a gradually tapered version of the sample autocovariance matrix and for its inverse. The proposed estimator is formed by leaving the main diagonals of the sample autocovariance matrix intact while gradually down-weighting o�-diagonal entries towards zero. In addition we show the same convergence rates hold for a positive de�nite version of the estimator, and we introduce a new approach for selecting the banding parameter. The new matrix estimator is shown to perform well theoretically and in simulation studies. As an application we introduce a new resampling scheme for stationary processes termed the linear process bootstrap (LPB). The LPB is shown to be asymptotically valid for the sample mean and related statistics. The e�ectiveness of the proposed methods are demonstrated in a simulation study.

Oscillation in ergodic theory: Higher dimensional results

Abstract: In this paper we continue our investigations of square function inequalities. The results in [9] are primarily one dimensional, and here we extend all the results to multi-dimensional averages. Our basic tool is still a comparison of the ergodic averages with various dyadic (reversed) martingales, but the Fourier transform arguments are replaced by more geometric almost orthogonality arguments.

The Connection Between Popularity Bias, Calibration, and Fairness in Recommendation

Abstract: Recently there has been a growing interest in fairness-aware recommender systems including fairness in providing consistent performance across different users or groups of users. A recommender system could be considered unfair if the recommendations do not fairly represent the tastes of a certain group of users while other groups receive recommendations that are consistent with their preferences. In this paper, we use a metric called miscalibration for measuring how a recommendation algorithm is responsive to users’ true preferences and we consider how various algorithms may result in different degrees of miscalibration for different users. In particular, we conjecture that popularity bias which is a well-known phenomenon in recommendation is one important factor leading to miscalibration in recommendation. Our experimental results using two real-world datasets show that there is a connection between how different user groups are affected by algorithmic popularity bias and their level of interest in popular items. Moreover, we show that the more a group is affected by the algorithmic popularity bias, the more their recommendations are miscalibrated.

Ten simple rules for building an antiracist lab.

Abstract: Demographics of the science, technology, engineering, and mathematics (STEM) workforce and student body in the US and Europe continue to show severe underrepresentation of Black, Indigenous, and people of color (BIPOC). Among the documented causes of the persistent lack of diversity in STEM are bias, discrimination, and harassment of members of underrepresented minority groups (URMs). These issues persist due to continued marginalization, power imbalances, and lack of adequate policies against misconduct in academic and other scientific institutions. All scientists can play important roles in reversing this trend by shifting the culture of academic workplaces to intentionally implement equitable and inclusive policies, set norms for acceptable workplace conduct, and provide opportunities for mentorship and networking. As scientists are increasingly acknowledging the lack of racial and ethnic diversity in science, there is a need for clear direction on how to take antiracist action. Here we present 10 rules to help labs develop antiracists policies and action in an effort to promote racial and ethnic diversity, equity, and inclusion in science.

The clinical application of interphase FISH in prenatal diagnosis.

Abstract: Fluorescence in situ hybridization (FISH) for five chromosomes (13, 18, 21, X and Y) detected 87 of 107 (81%) of the chromosome aberrations identified by conventional chromosome analysis applied to fetal interphase cells obtained by chorionic villus sampling or amniocentesis. The choice of FISH was solely determined by prospective parents after formal genetic counselling concerning the advantages and disadvantages of FISH analysis. Excluding known familial chromosome aberrations, if FISH analysis revealed normal signals, there was an overall residual risk of 1 in 149 for an undetectable chromosome aberration. This risk varied according to the indication for prenatal diagnosis: 1 in 177 for women of advanced maternal age; 1 in 60 for women at increased risk for Down syndrome based on maternal serum screening; and, 1 in 43 for women whose ultrasound examination revealed fetal anomalies. There were 20 cases of discordance between the FISH results and standard karyotype analysis: four were the outcome of a failure to apply the appropriate FISH probe; 16 were not detectable by the available FISH probes. Of these 16, nine were chromosome abnormalities with clinical significance and seven were familial. If FISH is to become a standard part of prenatal genetic diagnosis, genetic counselling that is sensitive to patient health needs must be based on accurate information about the biological and obstetrical implications of the results of FISH analysis.