I am a Professor in the Department of Biostatistics and Medical Informatics and the Department of Population Health Sciences in the School of Medicine and Public Health at the University of Wisconsin-Madison. I have an affiliate appointment in the Department of Statistics.
I grew up in Duluth, Minnesota. I graduated from East High School in 1988. I received a BA in Mathematics and Economics in 1992 from the University of Minnesota-Duluth and an MS in Statistics in 1994 and a PhD in Statistics with emphasis in Biostatistics in 1998 from the University of Wisconsin-Madison. My PhD advisor was Murray Clayton.
I was a research scientist in the Statistical Data Analysis Center(SDAC) in the Department of Biostatistics and Medical Informatics at the University of Wisconsin-Madison, 1998-2005. I joined the faculty with a joint appointment in the Department of Biostatistics and Medical Informatics and the Department of Population Health Sciences in 2005.
I am an applied biostatistician focusing on problems in clinical and epidemiologic research. Current methodologic areas of interest include (1) multi-state models for incidence, progression and regression of ocular (and other) diseases, (2) small area estimation problems, particularly ranking, (3) spatial and spatio-temporal modeling, particularly cluster detection and high-dimensional variable selection and (4) age-period-cohort modeling.
Outside of the office, I’m an avid cyclist. You can check out my recent rides on Strava. I’m also a big movie fan. You’ll definitely see me at the Wisconsin Film Festival, one of my favorite events every year, and you can see lists of my favorite films and what I’ve been watching recently on Letterboxd.
PhD in Statistics (emphasis in Biostatistics), 1998
University of Wisconsin-Madison
MS in Statistics, 1994
University of Wisconsin-Madison
BA in Mathematics and Economics, 1992
University of Minnesota-Duluth
Introduction: There are significant disparities in the rates of maternal and infant morbidity and mortality in the United States – a discrepancy of particular importance in Wisconsin, where Non-Hispanic Black women experience the highest mortality rates in the country. The adverse effects of neighborhood socioeconomic status and geographical distance to obstetrical care outcomes have been demonstrated previously, with poor neighborhood socioeconomic status having been linked to higher rates of preterm births and low birth weight infants, which both increase the risk of neonatal morbidity and mortality. The objective of this study was to investigate the contributions of Area Deprivation Index and geographic location on age-matched birth weight z-scores. Methods: We conducted a retrospective cohort study of all singleton births >22 weeks’ gestation in Dane County, Wisconsin, from January 2016 through June 2018. Generalized additive models were adjusted for race/ethnicity, cigarette use, delivery route, pregnancy-related or chronic hypertension, pregestational and gestational diabetes, number of prenatal visits, maternal age, total weight gain, and pre-pregnancy body mass index. Results: There is evidence of an association between birth weight z-score and spatial location (median P value 0.006). With area deprivation, we found no evidence of an association with birth weight z-score (-0.01; 95% CI, -0.03 to 0.01; P = 0.109). Mean birth weight z-scores were lowest (-0.72) in the urban center of Madison, while mean birth weight z-score was highest (0.18) in rural areas near the northeast, southeast, and southwest county borders. We found an effect of race/ethnicity on birth weight. Conclusions: We identified geographic variations in birth weight at a granular level using census block groups and a holistic measure of deprivation, which can inform targeted public health interventions. The lack of evidence of area deprivation on birth outcomes but significant spatial trends demonstrated continued geographic disparities in our health care systems.
Context: Population health rankings can be a catalyst for the improvement of health by drawing attention to areas in need of relative improvement and summarizing complex information in a manner understood by almost everyone. However, ranks also have unintended consequences, such as being interpreted as “hard truths”, where variations may not be significant. There is a need to improve communication about uncertainty in ranks, with accurate interpretation. The most common solutions discussed in the literature have included modeling approaches to minimize statistical noise or borrow strength from covariates. However, the use of complex models can limit communication and implementation, especially for broad audiences. Objectives: Explore data-informed grouping (cluster analysis) as an easier-to-understand, empirical technique to account for rank imprecision that can be effectively communicated both numerically and visually. Design: Cluster analysis, specifically k-means clustering with Wasserstein (earth mover’s) distance, was explored as an approach to identify natural and meaningful groupings and gaps in the data distribution for the County Health Rankings’ (CHR) health outcomes ranks. Setting: County-level health outcomes from the 2022 CHR Participants: 3,082 counties that were ranked in the 2022 CHR Main Outcome Measure: Data-informed health groups Results: Cluster analysis identified 30 health groupings among counties nationwide, with cluster size ranging from nine to 184 counties. On average, states had 16 identified clusters, ranging from 3 in Delaware and Hawaii to 27 in Virginia. Number of clusters per state was associated with number of counties per state and population of the state. The method helped address many of the issues that arise from providing rank estimates alone. Conclusions: Public health practitioners can use this information to understand uncertainty in ranks, visualize distances between county ranks, have context around which counties are not meaningfully different from one another, and compare county performance to peer counties.
Prior research has shown that cancer risk varies by geography, but scan statistic methods for identifying cancer clusters in case-control studies have been limited in their ability to identify multiple clusters and adjust for participant-level risk factors. We develop a method to identify geographic patterns of breast cancer odds using the Wisconsin Women’s Health Study, a series of 5 population-based case-control studies of female Wisconsin residents aged 20-79 enrolled in 1988-2004 (cases=16,076, controls=16,795). We create sets of potential clusters by overlaying a 1 km grid over each county-neighborhood and enumerating a series of overlapping circles. Using a two-step approach, we fi=t a penalized binomial regression model to the number of cases and trials in each grid cell, penalizing all potential clusters by the least absolute shrinkage and selection operator (Lasso). We use BIC to select the number of clusters, which are included in a participant-level logistic regression model. We identify 15 geographic clusters, resulting in 23 areas of unique geographic odds ratios. After adjustment for known risk factors, confidence intervals narrowed but breast cancer odds ratios did not meaningfully change; one additional hotspot was identified. By considering multiple overlapping spatial clusters simultaneously, we discern gradients of spatial odds across Wisconsin.
Spatial and spatio-temporal cluster detection are important tools in public health and many other areas of application. Cluster detection can be approached as a multiple testing problem, typically using a space and time scan statistic. We recast the spatial and spatio-temporal cluster detection problem in a high-dimensional data analytical framework with Poisson or quasi-Poisson regression with the Lasso penalty. We adopt a fast and computationally-efficient method using a novel sparse matrix representation of the effects of potential clusters. The number of clusters and tuning parameters are selected based on (quasi-)information criteria. We evaluate the performance of our proposed method including the false positive detection rate and power using a simulation study. Application of the method is illustrated using breast cancer incidence data from three prefectures in Japan.
Background: Recent reports suggest that racial differences in breast cancer incidence rates have decreased. We examined whether these findings apply to breast cancer mortality while considering age, period, and cohort influences on both absolute and relative measures of breast cancer mortality. Methods: Using publicly available datasets (CDC Wonder, Human Mortality Database), we developed an age-period-cohort model of breast cancer mortality and breast cancer deaths as a proportion of all deaths during 1968-2019 among all women and by five race/ethnicity groups with sufficient numbers for estimation: Hispanic (all races), American Indian/Alaska Native and Asian/Pacific Islanders (regardless of ethnicity), non-Hispanic Black, and non-Hispanic White. Results: Initially increasing after 1968, age-adjusted breast cancer mortality rates have decreased among all racial/ethnic groups since 1988. The age-adjusted percent of all deaths due to breast cancer also has been declining for non-Hispanic White women since about 1990 while increasing or holding steady for other race/ethnic groups. In 2019, the age-adjusted percent of deaths due to breast cancer for women was highest for Asian/Pacific Islanders (5.6%) followed by non-Hispanic Black (4.5%), Hispanic (4.4%), non-Hispanic White (4.1%), and American Indian/Alaska Native women (2.6%). Conclusions: Breast cancer mortality disparities are now greater on both relative and absolute scales for non-Hispanic Black women, and using the relative scale for Asian/Pacific Islanders and Hispanic women, compared with non-Hispanic White women for the first time in 50 years.
Background Many older adults rely on private vehicles for their mobility and may continue to drive when they are advised to stop. Walking and public transit can fulfill mobility needs in some contexts, but in the U.S. these options may not adequately substitute for driving when older adults reduce or stop driving. We examined whether baseline walking or taking public transit was associated with reductions in older adults’ driving after a three-year period in the United States. Methods We analyzed National Health and Aging Trends Study data from community-dwelling older drivers in 2015 (n = 4574). We used weighted logistic regression to estimate associations between older drivers’ walking and use of public transit in 2015 and changes in their driving behavior three years later—avoiding more driving conditions, driving less often, or not driving at all. We also examined associations between neighborhood walkability and driving behavior change three years later. Results There were no statistically significant associations between walking or taking public transit in 2015 and the adjusted odds of driving behavior change three years later. However, older drivers living in the most walkable neighborhoods in 2015 had greater adjusted odds of avoiding more driving conditions compared to those in the least walkable neighborhoods (adjusted Odds Ratio (aOR) = 1.66; 95 % Confidence Interval (95 % CI): 1.23-2.25). Living in the most walkable neighborhoods compared to the least walkable neighborhoods was also associated with an increased odds of no longer driving in 2018 (aOR = 1.56; 95 % CI: 1.04–2.36). Discussion The walkability of one’s neighborhood area—shorter distances between blocks, diverse land uses, and proximity to transit stops—is associated with driving behavior changes over time for older drivers. This work can inform programs and policies designed to connect older adults with alternative transportation options to driving.
Colorectal cancer (CRC) is highly preventable with timely screening, but screening modalities are widely underused, especially among those of low individual-level socioeconomic status (SES). In addition to individual-level SES, neighborhood-level SES may also play a role in CRC screening completion through less geographic access to health care, transportation, and community knowledge of and support for screenings. We investigated the associations between neighborhood SES using a census tract-level measure of social and economic conditions with the uptake of colonoscopy and stool-based testing. We utilized data from the Southern Community Cohort Study, a large, prospective study of English-speaking adults aged 40-79 from the southeastern United States with 65% of participants identifying as non-Hispanic Black and 53% having annual household income <$15,000. Neighborhood SES was measured via a Neighborhood Deprivation Index compiled from principal component analysis of 11 census tract variables in the domains of education, employment, occupation, and poverty; screening was self-reported at the baseline interview (2002-2009) and follow-up interview (2008-2012). We found that participants residing in the lowest SES areas had lower odds of ever undergoing colonoscopy (ORQ5vsQ1=0.75; 95%CI=[0.68, 0.82]) or stool-based CRC testing (ORQ5vsQ1=0.71; 95%CI=[0.63, 0.80]), while adjusting for individual-level SES factors. Associations were consistent between neighborhood SES and screening in subgroups defined by race, sex, household income, insurance, or education (p>0.20 for all interaction tests). Our findings suggest that barriers to screening exist at the neighborhood level and that residents of lower SES neighborhoods may experience more barriers to screening using colonoscopy and stool-based modalities.
Purpose Physical activity may greatly benefit adults living with advanced cancer; however, barriers to physical activity and preferences for supportive care interventions are not well understood. This study investigates barriers to physical activity and differences in intervention preferences by demographic and clinical characteristics among adults with advanced cancer. Methods Data came from a cross-sectional study of 247 adults with advanced cancer who visited the University of Wisconsin Carbone Cancer Centre from January 2021 to January 2023. The Godin–Shepard Leisure Score Index (insufficiently active, moderately active and active) was used to assess physical activity. Physical activity barriers were reported as mean scores (1–5: ‘not at all’ to ‘a great deal’). Differences in intervention preferences were assessed using X2 tests. Results Adults living with advanced cancer were insufficiently active (53%), moderately active (21%) or active (26%). Respondents identified several barriers to physical activity spanning tiredness (x̄=3.2), winter weather concerns (x̄=3.2) and lack of motivation (x̄=2.7). Respondents were most interested in a supportive care intervention designed to increase energy (88%) and improve physical health (86%) with physical therapy (73%), walking (72%) and resistance exercises (72%). Differences in preferences emerged by demographic characteristics and to a lesser extent by clinical characteristics. Conclusions Adults with advanced cancer reported several barriers to physical activity. Future interventions should emphasise increasing energy and physical health and include strategies to manage tiredness and winter weather concerns.
Introduction: The postpartum visit is an important opportunity to prevent pregnancy-related morbidity and mortality; however, about 1 in 10 birthing people fail to attend this visit. Intrapartum care experiences are an understudied factor that may contribute to postpartum healthcare engagement. Materials and Methods: We analyze data from a novel survey supplement on intrapartum care experiences administered to a probability-based population sample of people who have recently given birth through the Wisconsin Pregnancy Risk Assessment Monitoring System. Results: In regression models adjusting for a robust set of individual characteristics and birth hospital clustering, we find that lower provider responsiveness during intrapartum care is associated with increased odds of forgoing the postpartum visit (aOR 1.4, 95% CI 1.0-2.0). Discussion: The quality of care received during the birth hospitalization may shape how birthing people feel about health care providers and their willingness to attend future visits. Experiences of care during the intrapartum period may contribute to postpartum mental health outcomes and future health care utilization. Improving these experiences is an opportunity to promote long-term health.
Importance Prior literature has explored the prevalence of motor impairments in autistic individuals, but estimates come from clinical, convenience, or small samples, limiting generalizability. Better understanding of the frequency of motor milestone delays in autistic individuals could improve early identification and subsequently lead to earlier intervention and better developmental outcomes. Objective To determine the prevalence of motor milestone delays in a population-based sample of 8-year-old autistic children and to evaluate if having motor milestone delays is associated with an earlier age at autism evaluation or diagnosis. Design, Setting, and Participants This cross-sectional study of autistic 8-year-old children was conducted using Autism and Developmental Disabilities Monitoring (ADDM) Network data between surveillance years 2000 and 2016. ADDM Network data are population based and are drawn from 17 sites across the US. Data were analyzed from October 2023 to August 2024. Exposure Binary indicator of motor milestone delays documented in health or educational records. Main Outcomes and Measures The primary outcome was the prevalence of motor milestone delays among autistic 8-year-old children. Associations between motor milestone delays and age at autism evaluation or diagnosis were evaluated using linear regression. Covariates included study site, surveillance year, the number of autism discriminators, intellectual disability, child sex, and child race and ethnicity. Results Among 32 850 children aged 8 years identified with autism by active surveillance, 23 481 children (71.5%) met criteria for motor milestone delays. A total of 5973 children (18.2%) were female. In linear regression models, children with motor milestone delays were evaluated for autism significantly earlier (mean age, 43.65 months; 95% CI, 43.38-43.91) than children without motor milestone delays (mean age, 51.64 months; 95% CI, 51.22-52.06). After stratifying by the co-occurrence of intellectual disability (ID), children with motor milestone delays were evaluated for autism earlier than those without motor milestone delays, regardless of ID. Conclusions and Relevance This cross-sectional study estimates the prevalence of motor milestone delays among autistic 8-year-old children and highlights the association between these delays and an earlier autism evaluation, even in children without co-occurring ID. Early identification of autism is a public health priority, and assessing motor milestone delays, particularly in children with an increased likelihood of being autistic, may facilitate an earlier autism evaluation, leading to more timely interventions and better developmental outcomes.