average treatment effect
Recently Published Documents


TOTAL DOCUMENTS

393
(FIVE YEARS 223)

H-INDEX

21
(FIVE YEARS 6)

Author(s):  
OS Oduniyi ◽  
MA Antwi ◽  
AN Mukwevho

The participation of emerging farmers in high-value agricultural markets in South Africa cannot be over-emphasized. It is one of the objectives of the government to assist emerging farmers with the necessary resources and programmes to enable them to meet the requirements and participate in high-value markets. The study investigated the impact of participation in the high-value market on cattle production (cattle sold). A systematic random probabilistic sampling technique was used to obtain a sample of 55 emerging beef farmers. Interviews were undertaken using questionnaires to collect data. Descriptive statistics and econometric methods such as Tobit model and a treatment effect model using propensity score matching estimator were employed for the data analysis. The results of binary logit regression from the PSM revealed that participation in a high-value market was significantly affected by age, household size, years of farming and difficulty accessing a high-value market. The average treatment effect of the treated showed a negative impact and decreases the number of cattle sold by 58%. The recommendations informed by the findings from the study are that youth in the study area should be involved in beef farming, appropriate training should be given to the farmers and farmer's advisor should motivate farmers to sell more cattle and participate in a high-value market, and educate them about the requirements to participate in the high value markets. The DARD lease assistance should continue and include the lease of more land. Int. J. Agril. Res. Innov. Tech. 11(2): 27-36, Dec 2021


2022 ◽  
pp. 109821402092778
Author(s):  
Elizabeth Tipton

Practitioners and policymakers often want estimates of the effect of an intervention for their local community, e.g., region, state, county. In the ideal, these multiple population average treatment effect (ATE) estimates will be considered in the design of a single randomized trial. Methods for sample selection for generalizing the sample ATE to date, however, focus only on the case of a single target population. In this paper, I provide a framework for sample selection in the multiple population case, including three compromise allocations. I situate the methods in an example and conclude with a discussion of the implications for the design of randomized evaluations more generally.


2022 ◽  
Vol 22 (1) ◽  
Author(s):  
Edson Mwebesa ◽  
Joseph Kagaayi ◽  
Anthony Ssebagereka ◽  
Mary Nakafeero ◽  
John M. Ssenkusu ◽  
...  

Abstract Introduction Maternal mortality remains a global public health issue, more predominantly in developing countries, and is associated with poor maternal health services utilization. Antenatal care (ANC) visits are positively associated with facility delivery and postnatal care (PNC) utilization. However, ANC in itself may not lead to such association but due to differences that exist among users (women). The purpose of this study, therefore, is to examine the effect of four or more ANC visits on facility delivery and early PNC and also the effect of facility-based delivery on early PNC using Propensity Score Matched Analysis (PSMA). Methods The present study utilized the 2016 Uganda Demographic and Health Survey (UDHS) dataset. Women aged 15 – 49 years who had given birth three years preceding the survey were considered for this study. Propensity score-matched analysis was used to analyze the effect of four or more ANC visits on facility delivery and early PNC and also the effect of facility-based delivery on early PNC. Results The results revealed a significant and positive effect of four or more ANC visits on facility delivery [ATT (Average Treatment Effect of the Treated) = 0.118, 95% CI: 0.063 – 0.173] and early PNC [ATT = 0.099, 95% CI: 0.076 – 0.121]. It also found a positive and significant effect of facility-based delivery on early PNC [ATT = 0.518, 95% CI: 0.489 – 0.547]. Conclusion Policies geared towards the provision of four or more ANC visits are an effective intervention towards improved facility-based delivery and early PNC utilisation in Uganda.


2021 ◽  
Author(s):  
Larisa G Tereshchenko ◽  
Adam Bishop ◽  
Nora Fisher-Campbell ◽  
Jacqueline Levene ◽  
Craig Morris ◽  
...  

Objective: To determine absolute and relative risks of either symptomatic or asymptomatic SARS-CoV-2 infection for late cardiovascular events and all-cause mortality. Methods: We conducted a retrospective double-cohort study of patients with either symptomatic or asymptomatic SARS-CoV-2 infection [COVID-19(+) cohort] and its documented absence [COVID-19(-) cohort]. The study investigators drew a simple random sample of records from all Oregon Health & Science University (OHSU) Healthcare patients (N=65,585) with available COVID-19 test results, performed 03.01.2020 - 09.13.2020. Exclusion criteria were age < 18y and no established OHSU care. The primary outcome was a composite of cardiovascular morbidity and mortality. All-cause mortality was the secondary outcome. Results: The study population included 1355 patients (mean age 48.7 ± 20.5 y; 770(57%) female, 977(72%) white non-Hispanic; 1072(79%) insured; 563(42%) with cardiovascular disease (CVD) history). During a median 6 months at risk, the primary composite outcome was observed in 38/319 (12%) COVID-19(+) and 65/1036 (6%) COVID-19(-) patients (p=0.001). In Cox regression adjusted for demographics, health insurance, and reason for COVID-19 testing, SARS-CoV-2 infection was associated with the risk of the primary composite outcome (HR 1.71; 95%CI 1.06-2.78; p=0.029). Inverse-probability-weighted estimation, conditioned for 31 covariates, showed that for every COVID-19(+) patient, the average time to all-cause death was 65.5 days less than when all these patients were COVID-19(-): average treatment effect on the treated -65.5 (95%CI -125.4 to -5.61) days; p=0.032. Conclusions: Either symptomatic or asymptomatic SARS-CoV-2 infection is associated with increased risk of late cardiovascular outcomes and has a causal effect on all-cause mortality in a late post-COVID-19 period.


2021 ◽  
pp. 174077452110568
Author(s):  
Fan Li ◽  
Zizhong Tian ◽  
Jennifer Bobb ◽  
Georgia Papadogeorgou ◽  
Fan Li

Background In cluster randomized trials, patients are typically recruited after clusters are randomized, and the recruiters and patients may not be blinded to the assignment. This often leads to differential recruitment and consequently systematic differences in baseline characteristics of the recruited patients between intervention and control arms, inducing post-randomization selection bias. We aim to rigorously define causal estimands in the presence of selection bias. We elucidate the conditions under which standard covariate adjustment methods can validly estimate these estimands. We further discuss the additional data and assumptions necessary for estimating causal effects when such conditions are not met. Methods Adopting the principal stratification framework in causal inference, we clarify there are two average treatment effect (ATE) estimands in cluster randomized trials: one for the overall population and one for the recruited population. We derive analytical formula of the two estimands in terms of principal-stratum-specific causal effects. Furthermore, using simulation studies, we assess the empirical performance of the multivariable regression adjustment method under different data generating processes leading to selection bias. Results When treatment effects are heterogeneous across principal strata, the average treatment effect on the overall population generally differs from the average treatment effect on the recruited population. A naïve intention-to-treat analysis of the recruited sample leads to biased estimates of both average treatment effects. In the presence of post-randomization selection and without additional data on the non-recruited subjects, the average treatment effect on the recruited population is estimable only when the treatment effects are homogeneous between principal strata, and the average treatment effect on the overall population is generally not estimable. The extent to which covariate adjustment can remove selection bias depends on the degree of effect heterogeneity across principal strata. Conclusion There is a need and opportunity to improve the analysis of cluster randomized trials that are subject to post-randomization selection bias. For studies prone to selection bias, it is important to explicitly specify the target population that the causal estimands are defined on and adopt design and estimation strategies accordingly. To draw valid inferences about treatment effects, investigators should (1) assess the possibility of heterogeneous treatment effects, and (2) consider collecting data on covariates that are predictive of the recruitment process, and on the non-recruited population from external sources such as electronic health records.


2021 ◽  
Author(s):  
Ang Li ◽  
GUO Xiaohui ◽  
Lin Liu ◽  
Xiaoyong Yuan ◽  
Difei Lu ◽  
...  

Abstract Purpose: This study aimed to explore the influences of online support of an Internet plus Shared Care diabetes management model on metabolic indicators and the differences before and after the coronavirus disease 2019 (COVID-19) pandemic. Method: Type 2 diabetes patients who visited the Peking University First Hospital Internet plus Shared Care clinic from May 18, 2020 to June 20, 2020 (after the COVID-19 pandemic subsided) were enrolled in the study. The age, gender, usage of insulin, and duration of diabetes of the patients were collected. The glycosylated hemoglobin (HbA1c), interval between two consecutive visits, communication frequencies with online diabetes educators through an app, online self-monitoring of blood glucose (SMBG) and upload count and SMBG pairing count (before–after meal) were collected before (prior to January 20, 2020) and after (from May 18, 2020 to June 20, 2020) the COVID-19 pandemic for logistic regression analysis. The R-3.4.4 and TWANG programs were used for analysis. The group of patients whose HbA1c did not change during the pandemic was the control group, while the group of patients with improved HbA1c was the dependent variable. Independent variables included age, gender, duration of disease, insulin usage, online communication amount, SMBG count, and SMBG pairing count. Propensity score matching (PSM) was applied with age, duration, gender, body mass index (BMI), HbA1c, low density lipoprotein- cholesterol (LDL-C), and blood pressure (BP) at baseline as the concomitant variable. After the PSM weighting, the average treatment effect (ATE) of post-pandemic BMI, HbA1c, LDL-C, and BP was compared with the baseline. Results: A total of 387 patients were enrolled in the study including 184 female (47.5%). The baseline values were the following: age, 61.7±9.4 year;, duration of diabetes, 11.7±8.2 years; BMI, 25.9±3.8Kg/m2; HbA1c, 7.2±1.3%; LDL-C, 2.49±0.85mmol/L; systolic BP, 130.8±14.9 mmHg; and diastolic BP, 81.1±40.9 mmHg. Among variables, online communication amounted to a statistically significant contribution to the HbA1c improvement after the COVID-19 pandemic (OR=2.178, p=0.003). During the pandemic, each patient received 18 (3, 56) times online communication support per quarter. Patients were divided into four groups by quartiles: Q1 (more than 56 times/quarter, n=95), Q2 (18–56 times/quarter, n=97), Q3 (3–18 times/quarter, n=93), and Q4 (0–3 times/quarter, n=102). After PSM, post-pandemic data showed significant differences. Between-group variance was found in HbA1c (Q1 vs. Q3, -0.42±0.16%, p=0.009; Q1 vs. Q4, -0.53±0.15%, p=0.0009) and BMI (Q1 vs. Q3, -1.2±0.5, p=0.02; Q1 vs. Q4 -1.5±0.7, p=0.01) of patients.Conclusion: During the COVID-19 pandemic, high-quality online support of the Internet plus Shared Care diabetes management model can significantly improve the HbA1c and BMI of type 2 diabetes patients.


2021 ◽  
Vol 23 (Supplement_G) ◽  
Author(s):  
Simone Zecchino ◽  
Vincenzo De Marzo ◽  
Roberto Licordari ◽  
Francesco Costa ◽  
Alessandro Caracciolo ◽  
...  

Abstract Aims Coronavirus disease 19 (COVID-19) pandemic has dramatically changed the management and the prognosis of patients experiencing acute coronary syndrome (ACS). Several scientific societies have highlighted the need for dedicated paths to deliver better and faster care to improve outcomes. Nevertheless, data depicting the impact of COVID-19 pandemic on ACS in Italy are still poor. To perform a propensity weighted analysis on a multicentre Italian registry involving patients with ACS managed before vs. during COVID-19 pandemic, taking into account baseline patients characteristics, clinical presentation, procedural aspects, and in-hospital outcomes (death, bleeding, stent thrombosis, myocardial infarction, stroke/transient ischaemic attack, mechanical complication, and arrhythmic complication). Methods and results We included all consecutive patients who have suffered from ACS during two periods before (March/April 2018, March/April 2019) vs. the period of COVID-19 pandemic (March/April 2020). A generalized boosted non-parsimonious regression was used to estimate the propensity scores of having an ACS in 2020 (year of COVID-19) vs. 2018/2019 using an average treatment effect and balancing for all baseline confounders. We included 2851 patients admitted to hospital with ACS in 17 Italian centres: 1079 (37.8%) during 2018, 1056 (37.0%) in 2019, and 716 (25.1%) during the first COVID-19 wave of 2020. Seventy (2.5%) patients had a positive swab for SARS-CoV-2 at admission. During 2020 there were higher time-to-emergency-call (P = 0.028) and less diagnosis of unstable angina (P = 0.029) and MINOCA (P = 0.004); none of the admission symptoms differ significantly across the years (P &gt; 0.05) except for fever that was more prevalent in 2020 (P &lt; 0.001). Patients suffering from ACS had lower admission EF (P = 0.006). After PS weighting, multivariate Cox regression analysis showed age (P &lt; 0.001), night admission (P = 0.017), cardiocirculatory arrest before cath-lab (P = 0.041), worst Killip class (P = 0.039), admission EF (P = 0.026), and need for left-ventricle mechanical support (P = 0.011) as independent predictors of in-hospital death. After propensity weighted analysis none of the in-hospital outcomes differed significantly across the years of investigation (all P &gt; 0.05). Conclusions During COVID-19 pandemic in Italy the characteristics and management of ACS was slightly different than the past. However, the rates of ‘hard’, in-hospital outcomes (e.g. deaths) are almost similar to the past, suggesting appropriate care and well-organized emergency-paths for ACS.


2021 ◽  
Vol 5 (Supplement_1) ◽  
pp. 840-840
Author(s):  
Peter Sun

Abstract This study examined the association between home- and community-based services (HCBS) and social, cognitive, and physical engagement among community-dwelling older adults in the U.S. Data were drawn from the 2012 Health and Retirement Study (HRS). The sample consisted of respondents ages 50 and over who answered questions on HCBS utilization and activity engagement (n = 567). Genetic matching and propensity score weighting were used to mimic randomized control and treatment groups, in order to estimate the population average treatment effect on the treated (PATT). HCBS utilization was found to be significantly associated with social engagement (PATT = 0.17, SE = 0.05, p &lt; 0.05) and physical (PATT = -0.20, SE = 0.07, p &lt; 0.05) engagement but not significantly associated with cognitive engagement (PATT = -0.04, SE = 0.12, p &gt; 0.05). Sensitivity analyses found that the results were robust to the estimation model. These findings suggest that HCBS utilization is a promising model for increased activity engagement, and future policies aimed at targeting these outcomes are warranted.


Sign in / Sign up

Export Citation Format

Share Document