Taylor Lewis
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Taylor Lewis has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
Joseph McMichael
3 shared publications- Charlotte Looby
RTI International 3040 East Cornwallis Road PO Box 12194 27709-2194 Research Triangle Park NC USA
2 shared publications - Daniel J. Schober
Department of Health Sciences, DePaul University, Chicago, Illinois, USA
2 shared publications - Matthew R. Williams
RTI International
2 shared publications Nik Prachand
Office of Epidemiology, Chicago Department of Public Health, Chicago, Illinois
2 shared publications- Allison Keller
Department of Health Sciences, DePaul University, Chicago, USA
1 shared publication
Latest Publications
- 5 May 2026
- Published by Wolters Kluwer Health in Journal of Public Health Management & Practice
- Vol. 32 (4) , 542-546
Giving and Receiving: A Study of Volunteering and Cardiometabolic Health Among Nonsmokers
Poor cardiometabolic health contributes to the leading causes of death, including heart disease, stroke, and diabetes. This study examined the relationship between volunteering and cardiometabolic health among nonsmoking adults through an analysis of the Chicago Department of Public Health's 2023 Healthy Chicago Survey (N = 4872). Cardiometabolic health was assessed through a 3-item summary score related to receiving a diagnosis of high blood pressure, high cholesterol, and diabetes. The analysis consisted of a Poisson regression and mediation models that incorporated demographic predictors and assessed mediation of physical activity, vegetable consumption, and belonging (feeling part of the neighborhood), 1 mediator at a time. Results show a significant relationship between volunteering in the past 12 months and cardiometabolic health and evidence that physical activity and belonging mediated this relationship. Urban health departments can promote cardiometabolic health as well as individual-level physical activity and a sense of belonging through assuring opportunities for volunteering.
- 5 May 2026
- Published by Wolters Kluwer Health in Journal of Public Health Management & Practice
- Vol. 32 (4) , 542-546
Giving and Receiving: A Study of Volunteering and Cardiometabolic Health Among Nonsmokers
Poor cardiometabolic health contributes to the leading causes of death, including heart disease, stroke, and diabetes. This study examined the relationship between volunteering and cardiometabolic health among nonsmoking adults through an analysis of the Chicago Department of Public Health's 2023 Healthy Chicago Survey (N = 4872). Cardiometabolic health was assessed through a 3-item summary score related to receiving a diagnosis of high blood pressure, high cholesterol, and diabetes. The analysis consisted of a Poisson regression and mediation models that incorporated demographic predictors and assessed mediation of physical activity, vegetable consumption, and belonging (feeling part of the neighborhood), 1 mediator at a time. Results show a significant relationship between volunteering in the past 12 months and cardiometabolic health and evidence that physical activity and belonging mediated this relationship. Urban health departments can promote cardiometabolic health as well as individual-level physical activity and a sense of belonging through assuring opportunities for volunteering.
- Open Access
- 1 January 2026
- Published by School of Statistics, Renmin University of China in Journal of Data Science
- p. 1-20
An Estimation Framework for Combining Probability and Non-probability Samples
Survey researchers are increasingly adopting hybrid sampling designs to address the limitations of traditional probability sampling, especially when studying rare or hard-to-reach populations. Challenges such as high screening costs, low statistical efficiency, and operational constraints make purely probability-based approaches impractical in many contexts. This article uses public data from the National Health and Nutrition Examination Survey to demonstrate how one can make population estimates from a hybrid sampling strategy that combines data from a stratified, multistage probability sample with data from a non-probability sample within the same primary sampling units as the probability sample. We outline a framework and discuss methods for analyzing data from a hybrid sample such as this, where covariates and survey outcomes are observed in both the probability and non-probability samples. We present a case study to illustrate the framework. We provide the case study R code in the supplementary material.
- 1 January 2026
- Published by School of Statistics, Renmin University of China in Journal of Data Science
- p. 1-20
Open AccessAn Estimation Framework for Combining Probability and Non-probability Samples
Survey researchers are increasingly adopting hybrid sampling designs to address the limitations of traditional probability sampling, especially when studying rare or hard-to-reach populations. Challenges such as high screening costs, low statistical efficiency, and operational constraints make purely probability-based approaches impractical in many contexts. This article uses public data from the National Health and Nutrition Examination Survey to demonstrate how one can make population estimates from a hybrid sampling strategy that combines data from a stratified, multistage probability sample with data from a non-probability sample within the same primary sampling units as the probability sample. We outline a framework and discuss methods for analyzing data from a hybrid sample such as this, where covariates and survey outcomes are observed in both the probability and non-probability samples. We present a case study to illustrate the framework. We provide the case study R code in the supplementary material.
- 6 November 2025
- Published by SAGE Publications in Statistical Journal of the IAOS
- Vol. 41 (4) , 1291-1299
A review of recent nowcasting methods compensating for vital statistics reporting lags
Producing timely, accurate, and granular estimates of public health outcomes is essential for effective public health surveillance and mitigation efforts. However, the production of these estimates is potentially delayed by reporting lags, which many times occur naturally in a data collection cycle. In this article, we review published nowcasting methods (i.e., predicting current events while accounting for reporting lags) with a focus on methods relevant for nowcasting vital statistics. Our aim is to classify the underlying modeling strategies and contexts, identify certain advantages and limitations, and present ideas for further research and development using promising statistical modeling techniques that, to the best of our knowledge, have not yet been utilized in any vital statistics nowcasting approaches.
- 6 November 2025
- Published by SAGE Publications in Statistical Journal of the IAOS
- Vol. 41 (4) , 1291-1299
A review of recent nowcasting methods compensating for vital statistics reporting lags
Producing timely, accurate, and granular estimates of public health outcomes is essential for effective public health surveillance and mitigation efforts. However, the production of these estimates is potentially delayed by reporting lags, which many times occur naturally in a data collection cycle. In this article, we review published nowcasting methods (i.e., predicting current events while accounting for reporting lags) with a focus on methods relevant for nowcasting vital statistics. Our aim is to classify the underlying modeling strategies and contexts, identify certain advantages and limitations, and present ideas for further research and development using promising statistical modeling techniques that, to the best of our knowledge, have not yet been utilized in any vital statistics nowcasting approaches.
- 16 May 2025
- Published by Springer Nature in Journal of Racial and Ethnic Health Disparities
- Vol. 13 (4) , 3088-3097
The Effects of Neighborhood Violence on Physical Activity Following the COVID-19 Stay-at-Home Order: A Multilevel Analysis
Objectives COVID-19 contributed to decreases in physical activity and residents from communities with more crime and fewer resources were less physically active during the pandemic. However, the direct effects of COVID-related increases in crime on leisure-time physical activity has not been studied, extensively. Therefore, we examined how individual perceptions of neighborhood violence, community-level perceptions of safety, and the prevalence of violent crime are associated with leisure-time physical activity across neighborhoods in Chicago, Illinois, following the COVID-19 stay-at-home order. Methods We used cross-sectional data to build a multilevel logistic regression model in which the individual represented level 1 and the Chicago community area represented level 2. We used a stepwise approach, testing variables, one at a time, as random intercepts and then as random coefficients. We estimated adjusted odds ratios and 95% confidence intervals. Results Respondents who reported violence occurring every day had significantly lower odds of leisure-time physical activity (OR = 0.65, 95% CI = 0.50—0.85). Compared to non-Hispanic Whites, Non-Hispanic Blacks (OR = 0.75, 95% CI = 0.57 – 0.99), non-Hispanic Asian American/Pacific Islanders (OR = 0.63, 95% CI = 0.45—0.89), and Hispanic/Latino respondents (OR = 0.69, 95% CI = 0.53—0.89) had lower odds of leisure-time physical activity. On the neighborhood level, the percent of adults who reported they feel safe in their neighborhood was significant (p < .001), but violence prevalence was not (p = 0.091). Conclusions These results can inform public health efforts to promote physical activity following the COVID-19 stay-at-home order.
- 16 May 2025
- Published by Springer Nature in Journal of Racial and Ethnic Health Disparities
- Vol. 13 (4) , 3088-3097
The Effects of Neighborhood Violence on Physical Activity Following the COVID-19 Stay-at-Home Order: A Multilevel Analysis
Objectives COVID-19 contributed to decreases in physical activity and residents from communities with more crime and fewer resources were less physically active during the pandemic. However, the direct effects of COVID-related increases in crime on leisure-time physical activity has not been studied, extensively. Therefore, we examined how individual perceptions of neighborhood violence, community-level perceptions of safety, and the prevalence of violent crime are associated with leisure-time physical activity across neighborhoods in Chicago, Illinois, following the COVID-19 stay-at-home order. Methods We used cross-sectional data to build a multilevel logistic regression model in which the individual represented level 1 and the Chicago community area represented level 2. We used a stepwise approach, testing variables, one at a time, as random intercepts and then as random coefficients. We estimated adjusted odds ratios and 95% confidence intervals. Results Respondents who reported violence occurring every day had significantly lower odds of leisure-time physical activity (OR = 0.65, 95% CI = 0.50—0.85). Compared to non-Hispanic Whites, Non-Hispanic Blacks (OR = 0.75, 95% CI = 0.57 – 0.99), non-Hispanic Asian American/Pacific Islanders (OR = 0.63, 95% CI = 0.45—0.89), and Hispanic/Latino respondents (OR = 0.69, 95% CI = 0.53—0.89) had lower odds of leisure-time physical activity. On the neighborhood level, the percent of adults who reported they feel safe in their neighborhood was significant (p < .001), but violence prevalence was not (p = 0.091). Conclusions These results can inform public health efforts to promote physical activity following the COVID-19 stay-at-home order.
- Open Access
- 2 December 2024
- Published by RTI Press
Evaluating Three Ways to Handle Drop Points in Address-Based Sampling Frame Surveys
Address-based sampling frames are commonly created from lists derived from the United States Postal Service’s Computerized Delivery Sequence file (CDS), a comprehensive list of addresses in the United States. While most addresses in the CDS represent only one household, some addresses—known as drop points (DPs)—are delivery points for two or more households. The drop point units (DPUs) therein do not have secondary unit designators specified in the CDS, which is a challenge for self-administered surveys because they cannot be contacted specifically. An earlier paper by the authors examined differences between responses of DPUs and nearby non-DPU substitutes in the 2021 Healthy Chicago Survey of sociodemographic characteristics and key health outcomes. This paper is a follow-up analysis comparing the effects of including, excluding, or substituting DPUs on the entire sampling frame, and thus entire study area, to quantify the magnitude of point estimate differences between those methods. No statistically significant differences were found in the distributions of key health outcomes for the three methods. This is true even when focusing on the 11 community areas where more than 30 percent of the homes were DPUs.
- 2 December 2024
- Published by RTI Press
Open AccessEvaluating Three Ways to Handle Drop Points in Address-Based Sampling Frame Surveys
Address-based sampling frames are commonly created from lists derived from the United States Postal Service’s Computerized Delivery Sequence file (CDS), a comprehensive list of addresses in the United States. While most addresses in the CDS represent only one household, some addresses—known as drop points (DPs)—are delivery points for two or more households. The drop point units (DPUs) therein do not have secondary unit designators specified in the CDS, which is a challenge for self-administered surveys because they cannot be contacted specifically. An earlier paper by the authors examined differences between responses of DPUs and nearby non-DPU substitutes in the 2021 Healthy Chicago Survey of sociodemographic characteristics and key health outcomes. This paper is a follow-up analysis comparing the effects of including, excluding, or substituting DPUs on the entire sampling frame, and thus entire study area, to quantify the magnitude of point estimate differences between those methods. No statistically significant differences were found in the distributions of key health outcomes for the three methods. This is true even when focusing on the 11 community areas where more than 30 percent of the homes were DPUs.
- 5 September 2024
- Published by Wolters Kluwer Health in Journal of Public Health Management & Practice
- Vol. 31 (2) , E80-E87
A Comparison of Los Angeles County Health Survey Outcomes After Transitioning From Telephone to a Primarily Web-Based, Self-Administration Data Collection Mode
Context: As response rates to health surveys conducted by telephone continue to fall while data collection costs rise, practitioners are increasingly transitioning to address-based sample (ABS) designs with a self-administered, mail contact data collection mode. Objective: To compare differences in key health indicators produced from both the Adult Survey and Child Survey of the Los Angeles County Health Survey (LACHS), which transitioned from a telephone to primarily self-administered mode in the 2022-2023 administration. Design: Weighted survey estimates from the 2015, 2018, and 2022-2023 LACHS administrations are compared to investigate differences that may be attributable to LACHS’ recent mode transition. Setting: All survey data were collected of residents of Los Angeles County between 2015 and 2023. Main Outcome Measures: Response rates and key health indicators produced from the Los Angeles County Health Survey. Results: Introducing the self-administration mode led to modest response rate increases of approximately 10% to 16% for the Adult Survey and from 10% to 14% in the Child Survey. Key health indicator differences are mixed, but generally larger in magnitude across the mode transition, and also generally larger for the Adult Survey relative to the Child Survey. Conclusions: Transitioning a population health survey from a telephone mode to a primarily self-administration mode using an ABS design comes with tradeoffs. Increased response rates and a greater ability to target lower-level geographies and other population domains of interest may be offset by mode effects that cannot be compensated for by weighting adjustments.
- 5 September 2024
- Published by Wolters Kluwer Health in Journal of Public Health Management & Practice
- Vol. 31 (2) , E80-E87
A Comparison of Los Angeles County Health Survey Outcomes After Transitioning From Telephone to a Primarily Web-Based, Self-Administration Data Collection Mode
Context: As response rates to health surveys conducted by telephone continue to fall while data collection costs rise, practitioners are increasingly transitioning to address-based sample (ABS) designs with a self-administered, mail contact data collection mode. Objective: To compare differences in key health indicators produced from both the Adult Survey and Child Survey of the Los Angeles County Health Survey (LACHS), which transitioned from a telephone to primarily self-administered mode in the 2022-2023 administration. Design: Weighted survey estimates from the 2015, 2018, and 2022-2023 LACHS administrations are compared to investigate differences that may be attributable to LACHS’ recent mode transition. Setting: All survey data were collected of residents of Los Angeles County between 2015 and 2023. Main Outcome Measures: Response rates and key health indicators produced from the Los Angeles County Health Survey. Results: Introducing the self-administration mode led to modest response rate increases of approximately 10% to 16% for the Adult Survey and from 10% to 14% in the Child Survey. Key health indicator differences are mixed, but generally larger in magnitude across the mode transition, and also generally larger for the Adult Survey relative to the Child Survey. Conclusions: Transitioning a population health survey from a telephone mode to a primarily self-administration mode using an ABS design comes with tradeoffs. Increased response rates and a greater ability to target lower-level geographies and other population domains of interest may be offset by mode effects that cannot be compensated for by weighting adjustments.
- 1 April 2024
- Published by Taylor & Francis in Journal of Occupational and Environmental Hygiene
- Vol. 21 (5) , 365-377
Work-related factors of mental health among Chicago residents two years into the COVID-19 pandemic
In March 2020, the COVID-19 pandemic brought about rapid shifts within the social, economic, and political contexts of almost every aspect of a person’s life, in particular their mental health (Bon...
- 1 April 2024
- Published by Taylor & Francis in Journal of Occupational and Environmental Hygiene
- Vol. 21 (5) , 365-377
Work-related factors of mental health among Chicago residents two years into the COVID-19 pandemic
In March 2020, the COVID-19 pandemic brought about rapid shifts within the social, economic, and political contexts of almost every aspect of a person’s life, in particular their mental health (Bon...
- Open Access
- 18 May 2023
- Published by Survey Practice in Survey Practice
- Vol. 16 (1) , 1-9
Mail to One or Mail to All? An Experiment (Sub)Sampling Drop Point Units in a Self-Administered Address-Based Sampling Frame Survey
Practitioners utilizing an address-based sampling frame for a self-administered, mail contact survey must decide on how to handle drop points, which are single delivery points or receptacles that service multiple households. A variety of strategies have been adopted, including sampling all units at the drop point or subsampling just one (or a portion) of them. This paper reports results from an experiment fielded during the 2021 Healthy Chicago Survey aimed at providing insight into whether there are any substantive differences between these approaches. We find that a subsampling strategy in which a single mailing is sent produces a roughly 3 percentage point higher response rate relative to a strategy sending multiple mailings concurrently to the drop point. While base-weighted distributions of gender and age differed enough to be statistically significant, there were no noteworthy differences across other demographics or across the base-weighted distributions of select key health outcomes measured by the survey. Taken together, these results provide some evidence that a "mail to one" drop point strategy is more efficient than a "mail to all" drop point strategy.
- 18 May 2023
- Published by Survey Practice in Survey Practice
- Vol. 16 (1) , 1-9
Open AccessMail to One or Mail to All? An Experiment (Sub)Sampling Drop Point Units in a Self-Administered Address-Based Sampling Frame Survey
Practitioners utilizing an address-based sampling frame for a self-administered, mail contact survey must decide on how to handle drop points, which are single delivery points or receptacles that service multiple households. A variety of strategies have been adopted, including sampling all units at the drop point or subsampling just one (or a portion) of them. This paper reports results from an experiment fielded during the 2021 Healthy Chicago Survey aimed at providing insight into whether there are any substantive differences between these approaches. We find that a subsampling strategy in which a single mailing is sent produces a roughly 3 percentage point higher response rate relative to a strategy sending multiple mailings concurrently to the drop point. While base-weighted distributions of gender and age differed enough to be statistically significant, there were no noteworthy differences across other demographics or across the base-weighted distributions of select key health outcomes measured by the survey. Taken together, these results provide some evidence that a "mail to one" drop point strategy is more efficient than a "mail to all" drop point strategy.
- 13 January 2023
- Published by SAGE Publications in Sociological Methodology
- Vol. 53 (1) , 158-175
Evaluating Substitution as a Strategy for Handling U.S. Postal Service Drop Points in Self-Administered Address-Based Sampling Frame Surveys
Most addresses on modern address-based sampling frames derived from the U.S. Postal Service’s Computerized Delivery Sequence file have a one-to-one relationship with a household. Some addresses, however, are associated with multiple households. These addresses are referred to as drop points, and the households therein are referred to as drop point units (DPUs). DPUs pose a challenge for self-administered surveys because no apartment number or unit designation is available, making it impossible to send targeted correspondence. The authors evaluate a method for substituting sampled DPUs with similar non-DPUs, which was implemented in the 2021 Healthy Chicago Survey alongside a concurrent survey of the originally sampled DPUs. Comparing aggregate distributions of DPUs and the non-DPU substitutes, the authors observe certain differences with respect to age, employment status, marital status, and housing tenure but no substantive differences in key health outcomes measured by the survey.
- 13 January 2023
- Published by SAGE Publications in Sociological Methodology
- Vol. 53 (1) , 158-175
Evaluating Substitution as a Strategy for Handling U.S. Postal Service Drop Points in Self-Administered Address-Based Sampling Frame Surveys
Most addresses on modern address-based sampling frames derived from the U.S. Postal Service’s Computerized Delivery Sequence file have a one-to-one relationship with a household. Some addresses, however, are associated with multiple households. These addresses are referred to as drop points, and the households therein are referred to as drop point units (DPUs). DPUs pose a challenge for self-administered surveys because no apartment number or unit designation is available, making it impossible to send targeted correspondence. The authors evaluate a method for substituting sampled DPUs with similar non-DPUs, which was implemented in the 2021 Healthy Chicago Survey alongside a concurrent survey of the originally sampled DPUs. Comparing aggregate distributions of DPUs and the non-DPU substitutes, the authors observe certain differences with respect to age, employment status, marital status, and housing tenure but no substantive differences in key health outcomes measured by the survey.
- 1 May 2022
- Published by Wolters Kluwer Health in Journal of Public Health Management & Practice
- Vol. 28 (3) , 309-316
Transitioning the Healthy Chicago Survey From a Telephone Mode to Self-administered by Mail Mode
Context: As response rates to health surveys conducted by telephone continue to decline and costs continue to increase, practitioners are increasingly considering a transition to self-administered mail contact modes. Objective: To compare empirical differences observed across adjacent administrations of the Healthy Chicago Survey (HCS) conducted by telephone versus self-administered via mail contact. Design: Data from the 2016, 2018, and 2020 administrations of the HCS are contrasted, and demographic distributions are benchmarked against the American Community Survey to investigate differences that may be linked to the HCS' transition from a telephone to self-administered mail mode between 2018 and 2020. Setting: All survey data were collected from adult residents of Chicago, Illinois, between 2016 and 2020. Main Outcome Measures: Costs, response rates, key health statistics, demographic distributions, and measures of precision generated from the HCS. Results: The mail mode led to a response rate increase of 6.8% to 38.2% at half the cost per complete. Mail respondents are more likely to be nonminority, female, and hold a college degree. Key health statistic differences are mixed, but design effects are larger in the mail mode, which we attribute to more detailed geographic stratification and weighting employed in 2020. Conclusions: The mail mode is a less costly data collection strategy for the HCS, but it comes with trade-offs. The quasi-random selection of an individual in the household exacerbates sociodemographic distribution disparities.
- 1 May 2022
- Published by Wolters Kluwer Health in Journal of Public Health Management & Practice
- Vol. 28 (3) , 309-316
Transitioning the Healthy Chicago Survey From a Telephone Mode to Self-administered by Mail Mode
Context: As response rates to health surveys conducted by telephone continue to decline and costs continue to increase, practitioners are increasingly considering a transition to self-administered mail contact modes. Objective: To compare empirical differences observed across adjacent administrations of the Healthy Chicago Survey (HCS) conducted by telephone versus self-administered via mail contact. Design: Data from the 2016, 2018, and 2020 administrations of the HCS are contrasted, and demographic distributions are benchmarked against the American Community Survey to investigate differences that may be linked to the HCS' transition from a telephone to self-administered mail mode between 2018 and 2020. Setting: All survey data were collected from adult residents of Chicago, Illinois, between 2016 and 2020. Main Outcome Measures: Costs, response rates, key health statistics, demographic distributions, and measures of precision generated from the HCS. Results: The mail mode led to a response rate increase of 6.8% to 38.2% at half the cost per complete. Mail respondents are more likely to be nonminority, female, and hold a college degree. Key health statistic differences are mixed, but design effects are larger in the mail mode, which we attribute to more detailed geographic stratification and weighting employed in 2020. Conclusions: The mail mode is a less costly data collection strategy for the HCS, but it comes with trade-offs. The quasi-random selection of an individual in the household exacerbates sociodemographic distribution disparities.