China
Africa
Explore chapters and articles related to this topic
Strong Social Distancing Measures in the United States Reduced the COVID-19 Growth Rate
Published in William C. Cockerham, Geoffrey B. Cockerham, The COVID-19 Reader, 2020
Charles Courtemanche, Joseph Garuccio, Anh Le, Joshua Pinkston, Aaron Yelowitz
We estimated the relationship between social distancing policies and the exponential growth rate of confirmed COVID-19 cases using an event-study regression with multiple treatments. Statistical analysis was conducted using Stata MP (version 15). This approach is akin to difference-in-differences but more flexible, as it interacts the treatment variables with multiple indicators of time since implementation, thereby tracing out the evolution of the treatment effects over time.20
All Things Being Equal – But How? (Designing the Study)
Published in Mitchell G. Maltenfort, Camilo Restrepo, Antonia F. Chen, Statistical Reasoning for Surgeons, 2020
Mitchell G. Maltenfort, Camilo Restrepo, Antonia F. Chen
There is a body of work on the topic of causal inference, which is concerned with the question of potential outcomes. In the real world, the patient either gets operated on or doesn’t. We can observe the outcome for patients who received a treatment but can only estimate what it would have been for the same patients if they did not get the treatment, and similarly we can observe the outcome for patients who were not treated but can only estimate what it would have been if they were treated. Estimates of the unobserved outcomes are plugged in to create estimates of the casual effect of treatment. Tools used include difference-in-difference methods, which use interaction terms in a regression to estimate before-and-after effects given that the patient did receive treatment, and propensity scores to balance treated and untreated groups.
Sensory Analysis Applied to Cosmetic Products
Published in Heather A.E. Benson, Michael S. Roberts, Vânia Rodrigues Leite-Silva, Kenneth A. Walters, Cosmetic Formulation, 2019
Regina Lúcia F. de Noronha, Heather A.E. Benson, Vânia Rodrigues Leite-Silva
This chapter provides an overview of the tests most widely used in cosmetic product sensory analysis to screen for differences between two samples (paired comparison, duo-trio and triangle tests), and three or more samples (ranking test). For detecting and quantifying the degree of difference, the difference from control test is recommended (Meilgaard et al., 2007). The reader is referred to the text by Meilgaard et al. (2007) for detailed information to assist with designing study protocols and data analysis.
Can a quality improvement intervention improve person-centred maternity care in Kenya?
Published in Sexual and Reproductive Health Matters, 2023
May Sudhinaraset, Katie M. Giessler, Michelle Kao Nakphong, Meghan M. Munson, Ginger M. Golub, Nadia G. Diamond-Smith, James Opot, Cathy E. Green
We conducted bivariate analyses to compare intervention and control groups pre- and post-intervention on socio-demographic factors, pregnancy factors, facility, and provider characteristics. We evaluated differences across groups by performing cross-tabulations, chi-square tests, and t-tests. To investigate the impact of the intervention on the various outcomes, we conducted a difference-in-differences analysis using models that included main effects of both treatment group and survey round, as well as a two-way interaction term. Ordinary least squares regression was conducted to examine the impact of the QIC on PCMC scores, sub-domains of PCMC, and clinical quality. We tested for homogeneity of variance of residuals using White’s test and used robust standard errors (Eicker-Huber-White) to correct for heteroscedasticity in our models. Logistic regression was employed to assess the effect of the intervention on secondary outcomes. Robust standard errors were used to correct for clustering of participants at the facility level. In addition, all multivariate models were adjusted for age, marital status, parity, employment, education, facility type, type of delivery provider, pregnancy complications, and baseline clinical quality. Analyses were performed using Stata SE 15.1 and an alpha level of 0.05 was established for statistical significance.
Impact of Medicaid expansion on mental health and substance use related emergency department visits
Published in Substance Abuse, 2022
In order to test for parallel trend assumption for using difference-in-differences approach in the analyses, we conducted event studies using Medicaid expansion dates and estimated treatment effects for 12 quarters before and after the Medicaid expansion date. We normalized the Medicaid expansion effect to 2 quarters prior to the policy implementation for both expansion (treatment) and non-expansion (control) states. Although parallel trend assumption cannot be tested directly, event study graphs of treatment effect coefficients can provide suggested evidence for parallel trend assumption. If the coefficients of the treatment effects before the Medicaid expansion are not statistically significant, then it would indicate that there are no apparent differences between treatment and control states suggesting that parallel trend assumption holds.
Effects of the COVID-19 pandemic on routine pediatric vaccination in Brazil
Published in Expert Review of Vaccines, 2021
Victor Santana Santos, Sarah Cristina Fontes Vieira, Ikaro Daniel de Carvalho Barreto, Vanessa Tavares de Gois-Santos, Ariel Oliveira Celestino, Carla Domingues, Luis Eduardo Cuevas, Ricardo Queiroz Gurgel
The percentage differences of vaccine doses administered during the pre-pandemic, stay-at-home and reopening periods were calculated by comparing them to the same months in 2019. To control for period changes, we conducted difference-in-difference (DiD) analyses and estimated adjusted percentage differences and 95% confidence intervals (CIs) during the stay-at-home and reopening periods using Poisson regression models, adjusting for the percentage difference in vaccine doses administered during the pre-pandemic period in 2020. The difference-in-differences approach uses repeated cross-sectional data collected before and after an event. The difference-in-differences estimator corresponds to the difference in two before-after differences observed in an exposed and non-exposed group. In our analyses, the exposed condition was represented by the months from January to December of the pandemic year 2020, while January to December 2019 were our non-exposed condition. We used the software R Core Team 2021 (Version 4.0.4) and adopted 5% significant level in all analysis.