Quantile treatment effect and double robust estimators

2017 ◽  
Vol 44 (4) ◽  
pp. 585-604 ◽  
Author(s):  
Francesco Caracciolo ◽  
Marilena Furno
Keyword(s):  
Monte Carlo ◽  
Propensity Score ◽  
Treatment Effect ◽  
Average Treatment Effect ◽  
Short Term ◽  
Content Type ◽  
Double Robust ◽  
Monte Carlo Studies ◽  
And Control ◽  
The Impact

Purpose Several approaches have been proposed to evaluate treatment effect, relying on matching methods propensity score, quantile regression, influence function, bootstrap and various combinations of the above. This paper considers two of these approaches to define the quantile double robust (DR) estimator: the inverse propensity score weights, to compare potential output of treated and untreated groups; the Machado and Mata quantile decomposition approach to compute the unconditional quantiles within each group – treated and control. Two Monte Carlo studies and an empirical application for the Italian job labor market conclude the analysis. The paper aims to discuss these issue. Design/methodology/approach The DR estimator is extended to analyze the tails of the distribution comparing treated and untreated groups, thus defining the quantile based DR estimator. It allows us to measure the treatment effect along the entire outcome distribution. Such a detailed analysis uncovers the presence of heterogeneous impacts of the treatment along the outcome distribution. The computation of the treatment effect at the quantiles, points out variations in the impact of treatment along the outcome distributions. Indeed it is often the case that the impact in the tails sizably differs from the average treatment effect. Findings Two Monte Carlo studies show that away from average, the quantile DR estimator can be profitably implemented. In the real data example, the nationwide results are compared with the analysis at a regional level. While at the median and at the upper quartile the nationwide impact is similar to the regional impacts, at the first quartile – the lower incomes – the nationwide effect is close to the North-Center impact but undervalues the impact in the South. Originality/value The computation of the treatment effect at various quantiles allows to point out discrepancies between treatment and control along the entire outcome distributions. The discrepancy in the tails may differ from the divergence between the average values. Treatment can be more effective at the lower/higher quantiles. The simulations show the performance at the quartiles of quantile DR estimator. In a wage equation comparing long and short term contracts, this estimator shows the presence of an heterogeneous impact of short term contracts. Their impact changes depending on the income level, the outcome quantiles, and on the geographical region.

Propensity score specification for optimal estimation of average treatment effect with binary response

2020 ◽  
Vol 29 (12) ◽  
pp. 3623-3640
Author(s):  
John A Craycroft ◽  
Jiapeng Huang ◽  
Maiying Kong
Keyword(s):  
Propensity Score ◽  
Treatment Effect ◽  
Propensity Scores ◽  
Optimal Estimation ◽  
Theoretical Explanation ◽  
Average Treatment Effect ◽  
Adaptive Lasso ◽  
Confounding Bias ◽  
Average Treatment ◽  
The Impact

Propensity score methods are commonly used in statistical analyses of observational data to reduce the impact of confounding bias in estimations of average treatment effect. While the propensity score is defined as the conditional probability of a subject being in the treatment group given that subject’s covariates, the most precise estimation of average treatment effect results from specifying the propensity score as a function of true confounders and predictors only. This property has been demonstrated via simulation in multiple prior research articles. However, we have seen no theoretical explanation as to why this should be so. This paper provides that theoretical proof. Furthermore, this paper presents a method for performing the necessary variable selection by means of elastic net regression, and then estimating the propensity scores so as to obtain optimal estimates of average treatment effect. The proposed method is compared against two other recently introduced methods, outcome-adaptive lasso and covariate balancing propensity score. Extensive simulation analyses are employed to determine the circumstances under which each method appears most effective. We applied the proposed methods to examine the effect of pre-cardiac surgery coagulation indicator on mortality based on a linked dataset from a retrospective review of 1390 patient medical records at Jewish Hospital (Louisville, KY) with the Society of Thoracic Surgeons database.

Impact of mobile money access on internal remittances, consumption expenditure and household welfare in Ghana

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Priscilla Twumasi Baffour ◽  
Wassiuw Abdul Rahaman ◽  
Ibrahim Mohammed
Keyword(s):  
Propensity Score ◽  
Propensity Score Matching ◽  
Treatment Effect ◽  
Average Treatment Effect ◽  
Consumption Expenditure ◽  
Content Type ◽  
Mobile Money ◽  
Money Transfer ◽  
Per Capita ◽  
Transfer Services

PurposeThe purpose of this study is to examine the impact of mobile money access on internal remittances received, per capita consumption expenditure and welfare of household in Ghana.Design/methodology/approachThe study used data from the latest round of the Ghana Living Standards Survey (GLSS 7) and employed the propensity score matching technique to estimate average treatment effect between users and non-users of mobile money transfer services.FindingsThe study finds that using mobile money is welfare enhancing, particularly for poor households and the channel by which it impacts on welfare is through higher internal remittances received and per capita expenditure. The results from the average treatment effect indicate that mobile money users receive significantly higher remittances and consequently spend averagely higher on consumption than non-users.Research limitations/implicationsAlthough the data employed in this study is limited to one country, the findings support the financial inclusion role and developmental impact of mobile money transfer services. Hence, mobile money transfer services should be promoted and facilitated by the telecommunication and financial sector regulators.Originality/valueIn addition to making original contribution to the literature on the welfare impact of mobile money, the study's use of the propensity score matching is unique.

Impact of the production of underutilized vegetables on the livelihood of farmers in Southwestern Nigeria

2017 ◽  
Vol 44 (12) ◽  
pp. 1669-1682
Author(s):  
Oluwatosin Adejoke Oyedele ◽  
Kemisola O. Adenegan
Keyword(s):  
Treatment Effect ◽  
Nutritive Value ◽  
Average Treatment Effect ◽  
Current Status ◽  
Special Focus ◽  
Vegetable Production ◽  
Southwestern Nigeria ◽  
Content Type ◽  
Average Treatment ◽  
The Impact

Purpose African indigenous vegetables have high nutritive value which contains high levels of minerals. The current status of indigenous vegetable production in developing countries shows that these crops are “under-recognized” and “underutilized” with respect to nutritional value and opportunities for food security. The purpose of this paper is to examine the impact of the production of underutilized vegetables on the livelihood of farmers in South Western Nigeria. Design/methodology/approach The population for the study includes all the vegetable farmers in South Western Nigeria with a special focus on farmers’ groups formed by the NICANVEG project in Osun, Oyo, Ondo and Ekiti states. Descriptive statistics and propensity score matching (PSM) was used to analyze the objective. Findings Perceptions on individual household income reveal that the majority of participating respondents perceived higher production and harvesting density. This is due to the fact that harvesting is done by cutting the stems of the vegetables. The probability score shows that the dependent variables have an average effect of 44.6 percent on the probability of farmers participating in NICANVEG project. The PSM results reveal that average treatment effect on the treated is ₦269,254.87. Average treatment on the untreated is ₦11,990.63 while average treatment effect is ₦139,336.43. The total income of the participants from all the various livelihood strategies is increased by 29.73 percent because of their participation in the NICANVEG project. Originality/value This work has not been carried out by any other person before. This work will add to the existing knowledge on the impact of evaluation in agricultural economics.

scholarly journals Bootstrap bias correction for average treatment effects with inverse propensity weights

2019 ◽  
Vol 52 (2) ◽  
pp. 187-200
Author(s):  
GUBHINDER KUNDHI ◽  
MARCEL VOIA
Keyword(s):  
Propensity Score ◽  
Treatment Effect ◽  
Bias Correction ◽  
Treatment Effects ◽  
Potential Problem ◽  
Average Treatment Effect ◽  
Omitted Variables ◽  
Control Groups ◽  
Average Treatment ◽  
And Control

The estimated average treatment effect in observational studies is biased if the assumptions of ignorability and overlap are not satisfied. To deal with this potential problem when propensity score weights are used in the estimation of the treatment effects, in this paper we propose a bootstrap bias correction estimator for the average treatment effect (ATE) obtained with the inverse propensity score (BBC-IPS) estimator. We show in simulations that the BBC-IPC performs well when we have misspecifications of the propensity score (PS) due to: omitted variables (ignorability property may not be satisfied), overlap (imbalances in distribution between treatment and control groups) and confounding effects between observables and unobservables (endogeneity). Further refinements in bias reductions of the ATE estimates in smaller samples are attained by iterating the BBC-IPS estimator.

scholarly journals Inference on mean quality-adjusted lifetime using joint models for continuous quality of life process and time to event

2020 ◽  
Vol 53 (2) ◽  
pp. 165-189
Author(s):  
XIAOTIAN GAO ◽  
XINXIN DONG ◽  
CHAERYON KANG KANG ◽  
ABDUS S. WAHED
Keyword(s):  
Propensity Score ◽  
Treatment Effect ◽  
Average Treatment Effect ◽  
Omitted Variables ◽  
Time To Event ◽  
Joint Models ◽  
Average Treatment ◽  
Continuous Quality ◽  
And Control

The estimated average treatment effect in observational studies is biased if the assumptions of ignorability and overlap are not satisfied. To deal with this potential problem when propensity score weights are used in the estimation of the treatment effects, in this paper we propose a bootstrap bias correction estimator for the average treatment effect (ATE) obtained with the inverse propensity score (BBC-IPS) estimator. We show in simulations that the BBC-IPC performs well when we have misspecifications of the propensity score (PS) due to: omitted variables (ignorability property may not be satisfied), overlap (imbalances in distribution between treatment and control groups) and confounding effects between observables and unobservables (endogeneity). Further refinements in bias reductions of the ATE estimates in smaller samples are attained by iterating the BBC-IPS estimator.

Non-governmental Organisations and Democracy: An Empirical Analysis

2015 ◽  
Vol 21 (4) ◽  
pp. 489-496 ◽  
Author(s):  
Tania Masi
Keyword(s):  
Developing Countries ◽  
Propensity Score ◽  
United Nations ◽  
Propensity Score Matching ◽  
Empirical Analysis ◽  
Treatment Effect ◽  
Average Treatment Effect ◽  
Government Accountability ◽  
The United Nations ◽  
The Impact

AbstractThe United Nations established in 2005 the United Nations Democracy Fund (UNDEF), whose objective is to support projects submitted by national NGOs aimed at increasing government accountability. The purpose of this paper is to investigate the impact of NGOs activity on democracy exploiting the UNDEF database. An empirical analysis based on a propensity score matching (PSM) method is implemented on a sample of 102 developing countries. The findings indicate that the average treatment effect on the treated (ATT) is positive and significant only when countries receive UNDEF-funded NGOs projects for three rounds or more. In this case the Polity IV indicator improves by an average of 1.08 points with respect to the level of 2005.

Child labor and family structure: the role of divorce

2018 ◽  
Vol 45 (10) ◽  
pp. 1453-1468
Author(s):  
Shirley Pereira de Mesquita ◽  
Wallace Patrick Santos de Farias Souza
Keyword(s):  
Family Structure ◽  
Child Labor ◽  
Treatment Effect ◽  
Single Mother ◽  
Average Treatment Effect ◽  
Empirical Approach ◽  
Content Type ◽  
The Impact ◽  
Single Mother Families

Purpose The purpose of this paper is to investigate the role of family structure on child labor by comparing children of nuclear families headed by the father with children of single-mother families headed by the divorced mother. Design/methodology/approach This paper uses data from Brazilian urban areas provided by the Brazilian Demographic Census of 2010. The empirical approach consists of the estimation of three treatment effect models: the Average Treatment Effect, IV Treatment Effect and Two-Stage Estimator proposed by Lewbel (2012). Findings The main findings show that children of single-mother families headed by divorced mothers are more likely to work, compared to children living with both parents. This paper found evidence of a direct effect of family structure parents’ determinant on child participation in labor. The main hypothesis is that the absence of the father paired with exposure to family stress arising from marital dissolution is an indicator toward child labor. Practical implications This study implies that in order to combat child labor effectively, it is important to understand deeply its several causes and consider ruptures in family structure, such as divorce, as one of these factors. In addition, location and family’s characteristics also play a role on the decision of child labor. For instance, boys living at metropolis areas have less chance to work. Family’s head education and non-work income affects positively the child well-being by reducing the probability of child labor. On the other hand, the number of siblings increases the chance of child labor. Finally, the results of this study suggest policies to raise awareness among parents about the negative effects of child labor on children during both childhood and adulthood, and that social policies need to act beyond legislation and enforcement, but including family mobilization. Originality/value This paper estimates the impact of family structure on child labor using an empirical approach to deal with the endogeneity problem of the treatment.

Correlates and impact of crop insurance in India: evidence from a nationally representative survey

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
A.G. Adeeth Cariappa ◽  
Darshnaben P. Mahida ◽  
Priyanka Lal ◽  
B.S. Chandel
Keyword(s):  
Propensity Score ◽  
Crop Insurance ◽  
Average Treatment Effect ◽  
Policy Implications ◽  
Sample Survey ◽  
Representative Survey ◽  
Content Type ◽  
Nationally Representative ◽  
The Impact ◽  
Matching Techniques

PurposeThe purpose of this paper is to identify the correlates of crop insurance adoption and estimate the impact on debt and farm income.Design/methodology/approachThe authors used nationally representative data from National Sample Survey Office (NSSO), which consisted of 35,200 farming households. Logit and propensity score matching (PSM) (nearest neighbor, caliper and kernel matching) techniques were used.FindingsWith only around 5% of households insuring their crops and 87% of them not receiving claims, crop insurance in India has failed. Logit model estimates of correlates of adoption indicated that households with larger family size, lower social group, less education, lower standard of living and poor were more likely to be left out of the ambit of crop insurance. Further, propensity score estimates suggested that households with access to crop insurance had significantly lesser outstanding debt with positive effect on input costs and crop income. The authors’ results were in contrast to the risk balancing theory.Practical implicationsResults of our work encourage us to rethink and restructure the crop insurance policy design in India. With credit and insurance markets interlinked by design and as the risk balancing in the farm business found absent, policies to strengthen both the markets are the need of the hour. To encourage more farmers to take up crop insurance, revenue-based indemnity calculation could be tried in India.Originality/valueImpact estimates from three different algorithms of matching were compared and tested for robustness. Consistent average treatment effect on treated (ATT) was considered for interpretation and policy implications. Since the data are from a nationally representative survey, results are believed to be of extreme value to policy makers and insurance providers as it can be generalized.

scholarly journals A Monte Carlo Determination of Dose and Range Uncertainties for Preclinical Studies with a Proton Beam

Cancers ◽  
2021 ◽  
Vol 13 (8) ◽  
pp. 1889
Author(s):  
Arthur Bongrand ◽  
Charbel Koumeir ◽  
Daphnée Villoing ◽  
Arnaud Guertin ◽  
Ferid Haddad ◽  
...  
Keyword(s):  
Monte Carlo ◽  
Monte Carlo Simulations ◽  
Proton Beam ◽  
Dose Response ◽  
Small Animal ◽  
Absorbed Dose ◽  
Normal Tissue Damage ◽  
Dose Homogeneity ◽  
And Control ◽  
The Impact

Proton therapy (PRT) is an irradiation technique that aims at limiting normal tissue damage while maintaining the tumor response. To study its specificities, the ARRONAX cyclotron is currently developing a preclinical structure compatible with biological experiments. A prerequisite is to identify and control uncertainties on the ARRONAX beamline, which can lead to significant biases in the observed biological results and dose–response relationships, as for any facility. This paper summarizes and quantifies the impact of uncertainty on proton range, absorbed dose, and dose homogeneity in a preclinical context of cell or small animal irradiation on the Bragg curve, using Monte Carlo simulations. All possible sources of uncertainty were investigated and discussed independently. Those with a significant impact were identified, and protocols were established to reduce their consequences. Overall, the uncertainties evaluated were similar to those from clinical practice and are considered compatible with the performance of radiobiological experiments, as well as the study of dose–response relationships on this proton beam. Another conclusion of this study is that Monte Carlo simulations can be used to help build preclinical lines in other setups.

Sign in / Sign up

Export Citation Format

Share Document