Multicity Investigation of the Effect of Holidays on Bikeshare System Ridership

Bikeshare provides important first mile–last mile, commuting, circulation, and sightseeing options in many cities. Bikeshare can also be healthy and convenient for users. Throughout the year, holidays occur that change typical bikeshare activity patterns. Existing literature shows mixed results relating to the ridership impacts of holidays: some research shows that these days may result in higher ridership, whereas others show no effect. Because of variations in system locations and modeling methods, it is difficult to determine the reasons for these mixed results. To control for these aspects, this project consisted of a multicity study of the effect of holidays on system-level ridership using a loglinear regression model with robust standard errors. The results showed the impacts of holidays on bikeshare system ridership for different user types among systems in the Washington D.C., Chicago, Boston, Los Angeles, and Minneapolis metro areas. Several hypotheses were developed and tested to examine the effects of holidays on bikeshare usage. A major finding from this study was that federal holidays negatively affected member ridership and positively affected nonmember ridership. It was also found that different federal holidays had dissimilar effects on total ridership. These findings could be useful for bikeshare agencies to plan, reposition fleet, and improve system operation.

The association between WASH, nutrition, and early childhood growth faltering in rural Cambodia: a cross-sectional risk factor analysis

Background Inadequate nutrition in early life and exposure to sanitation-related enteric pathogens have been linked to poor growth outcomes in children. Despite rapid development in Cambodia, high prevalence of growth faltering and stunting persist among children. This study aimed to assess nutrition and WASH variables and their association with nutritional status of children under 24 months in rural Cambodia. Methods We conducted surveys in 491 villages across 55 rural communes in Cambodia in September 2016 to measure associations between child, household, and community-level risk factors for stunting and length-for-age z-score (LAZ). A primary survey measured child-level variables, including anthropometric measures and risk factors for growth faltering and stunting, for 4,036 children under 24 months of age from 3,877 households (approximately 8 households per village). A secondary survey of 5,341 households, including the same households from the primary survey and an additional 1,464 households (approximately 3 additional household per village) from the same villages, assessed village-level WASH variables to understand community water, sanitation, and hygiene (WASH) conditions that may influence child growth outcomes. For LAZ, we calculated bivariate and adjusted associations (as mean differences) with 95% confidence intervals using generalized estimating equations (GEEs) to fit linear regression models with robust standard errors. For stunting, we calculated unadjusted and adjusted prevalence ratios (PRs) with 95% confidence intervals using GEEs to fit Poisson regression models with robust standard errors. For all models assessing effects of household-level variables, we used GEEs to account for clustering at the village level. Findings After adjustment for potential confounders, presence of water and soap at a household's handwashing station was found to be significantly associated (p<0.05) with increased LAZ (adjusted mean difference in LAZ +0.10, 95% CI 0.03 to 0.16), and household use of an improved drinking water source was associated with less stunting in children compared to households that did not use an improved source of drinking water (aPR 0.81, 95% CI 0.66 to 0.98); breastfeeding and community-level access to an improved drinking water source were associated with a lower LAZ score (-0.16, 95% CI -0.27 to -0.05; -0.13, 95% CI -0.26 to 0.00). No other nutrition (i.e., dietary diversity, meal frequency) or sanitation variables (i.e., household's safe disposal of child stools, household-level sanitation, community-level sanitation) were measured to be associated with LAZ scores or stunting in children under 24 months of age.

COVID-19 vaccine hesitancy January-March 2021 among 18-64 year old US adults by employment and occupation

IntroductionCOVID-19 vaccine hesitancy increased among US adults April-December, 2020, and threatens efforts to end the pandemic. Among US adults 18-64 years, we report prevalence of and reasons for vaccine hesitancy, overall and by employment and occupation, during the COVID-19 vaccine rollout.MethodsThe Delphi Group at Carnegie Mellon University conducted a COVID-19 survey administered by Facebook. In January, February and March, 2021, 791,716, 710,529, and 732,308 Facebook users, respectively, reported age 18-64 years and answered a vaccine acceptance question. Weights matched the sample to the age, gender, and state profile of the US population. Percentages and risk ratios (RR) for vaccine hesitancy were estimated using a weighted Poisson regression; 95% confidence intervals (CI) were calculated using robust standard errors.ResultsVaccine hesitancy decreased among adults 18-64 years from January (27.5% [95%CI, 27.3-27.6]) to March (22.1% [95%CI, 21.9-22.2]). Vaccine hesitancy varied widely by occupational category: 9.6%, (95%CI, 8.5-10.7) in life/physical/social sciences to 46.4% (95%CI, 45.1-47.7) in construction/extraction. Almost half (47.9%, 95%, 47.6-48.3) of hesitant participants indicated concern about side effects, and over a third didn’t believe they needed the vaccine, didn’t trust the government, were waiting to see if it was safe, and didn’t trust COVID-19 vaccines (versus 14.5% [95%CI, 14.3-14.8] who didn’t like vaccines in general).ConclusionsIn this nationally representative survey of adults 18-64 years, vaccine hesitancy decreased to 22.1% by March, 2021. Still, hesitancy, which varies widely by occupation, remains a barrier to pandemic control. Reasons for hesitancy indicate messaging about safety and addressing trust are paramount.

Do Board Quality and Promoters’ Holdings Affect Firm Performance? Evidence from Small and Medium-sized Enterprises

Unlike large businesses, small and medium-sized enterprises (SMEs), being a key growth driver in accomplishing immeasurable socio-economic objectives, possess different governance structures and face unique governance issues. Through the agency perspective, this research endeavours to pore over how the quality of their board affects the performance of SMEs in India. A regression model was run applying heteroscedasticity robust standard errors (RSE) on a sample of 68 BSE-listed SMEs for the period from 2013–2014 to 2017–2018. The results of the regression of the performance of the SMEs against their board attributes showed the prominent contribution of high promoters’ shareholding, signifying that SMEs with a highly concentrated ownership structure demonstrate better performance. Firm leverage and firm performance were shown to have a positive and significant relationship with each other, suggesting that levered firms display substantially better performance. On the other hand, it was found that increasing the number of independent directors and female directors does not necessarily result in improved firm performance. This finding suggests that tokenism, that is, appointing independent directors and female directors merely to comply with norms but not in true spirit, can reduce a firm’s performance. This research effort contributes to the literature constructively through explaining the linkage between board quality and the performance of SMEs, particularly in the Indian context, and has implications for the escalation of governance standards through bringing more clarity to and streamline policy and disclosure.

Understanding, Choosing, and Unifying Multilevel and Fixed Effect Approaches

When working with grouped data, investigators may choose between “fixed effects” models (FE) with specialized (e.g., cluster-robust) standard errors, or “multilevel models” (MLMs) employing “random effects.” We review the claims given in published works regarding this choice, then clarify how these approaches work and compare by showing that: (i) random effects employed in MLMs are simply “regularized” fixed effects; (ii) unmodified MLMs are consequently susceptible to bias—but there is a longstanding remedy; and (iii) the “default” MLM standard errors rely on narrow assumptions that can lead to undercoverage in many settings. Our review of over 100 papers using MLM in political science, education, and sociology show that these “known” concerns have been widely ignored in practice. We describe how to debias MLM’s coefficient estimates, and provide an option to more flexibly estimate their standard errors. Most illuminating, once MLMs are adjusted in these two ways the point estimate and standard error for the target coefficient are exactly equal to those of the analogous FE model with cluster-robust standard errors. For investigators working with observational data and who are interested only in inference on the target coefficient, either approach is equally appropriate and preferable to uncorrected MLM.

Reflections on modern methods: demystifying robust standard errors for epidemiologists

All statistical estimates from data have uncertainty due to sampling variability. A standard error is one measure of uncertainty of a sample estimate (such as the mean of a set of observations or a regression coefficient). Standard errors are usually calculated based on assumptions underpinning the statistical model used in the estimation. However, there are situations in which some assumptions of the statistical model including the variance or covariance of the outcome across observations are violated, which leads to biased standard errors. One simple remedy is to userobust standard errors, which are robust to violations of certain assumptions of the statistical model. Robust standard errors are frequently used in clinical papers (e.g. to account for clustering of observations), although the underlying concepts behind robust standard errors and when to use them are often not well understood. In this paper, we demystify robust standard errors using several worked examples in simple situations in which model assumptions involving the variance or covariance of the outcome are misspecified. These are: (i) when the observed variances are different, (ii) when the variance specified in the model is wrong and (iii) when the assumption of independence is wrong.

The Nastiest Question: Does Population Mobility Vary by State Political Ideology during the Novel Coronavirus (COVID-19) Pandemic?

We consider the association between state political ideology and population mobility during the coronavirus (COVID-19) pandemic. We use first-party geo-behavioral data to estimate the average distance traveled by approximately 15,000,000 devices over 10 weeks (February 24, 2020 to April 27, 2020). Regression models with state clustered robust standard errors show lower shelter-in-place rates and higher mobility scores in states with larger percentages of voters who supported Trump in the 2016 presidential election. We also find that shelter-in-place rates increased and mobility scores declined at slower rates in states with greater Trump support. Shelter-in-place rates and average mobility scores were comparable in states governed by Republicans and Democrats. There was some evidence that shelter-in-place rates increased and average mobility scores declined at slower rates in states governed by Republicans. Overall, states with more Trump voters are more resistant to public health recommendations and state stay-at-home orders during the coronavirus pandemic.

Barriers in profiting from external knowledge: the role of organizational design

This article analyzes as to how organizational design impacts firms’ innovation success in integrating knowledge that they have obtained from external partners. Responding to the call for more quantitative empirical analyses on limits and boundary conditions of external knowledge, I provide findings of a study of 97 firms with multi-informants from the Western-European automotive industry. Based on multiple hierarchical regression analyses with robust standard errors, the study shows that organizational design (in particular specialization, formalization, communication/connectedness [non-] monetary rewards) acts as barrier for firms who strive to profit from integrating external knowledge.

Modelling the Influences of Economic, Demographic, and Institutional Factors on Fiscal Pressure Using OLS, PCSE, and FD-GMM Approaches

The purpose of our article is to assess the effect of diverse factors, such as economic, demographic, and institutional factors, on global and social fiscal pressure. The study is based on a panel analysis of 38 states during 2000–2017. We used ordinary least squares (OLS) as a base model for our estimations, and a linear regression with panel-corrected standard errors and a first difference generalized method of moments (GMM) with robust standard errors and orthogonal deviations. The results of our study indicate that the demographic and institutional factors involved in the analysis contribute to the identification of some variables that affect the global or social fiscal pressure.