Proxy Means Test Research Articles

Predicting Poverty

Abstract Poverty prediction models are used to address missing data issues in a variety of contexts such as poverty profiling, targeting with proxy-means tests, cross-survey imputations such as poverty mapping, top and bottom income studies, or vulnerability analyses. Based on the models used by this literature, this paper conducts a study by artificially corrupting data clear of missing incomes with different patterns and shares of missing incomes. It then compares the capacity of classic econometric and machine-learning models to predict poverty under different scenarios with full information on observed and unobserved incomes, and the true counterfactual poverty rate. Random forest provides more consistent and accurate predictions under most but not all scenarios.

Shooting a moving target: Evaluating targeting tools for social programs when income fluctuates

A key challenge for policymakers in low- and middle-income countries is to design a method to select beneficiaries of social programs when income is unobservable and volatile. We use a unique panel dataset of a random sample of households in Colombia’s social registry that contains information before, during, and after the 2020 economic crisis to evaluate a traditional static proxy-means test (PMT) and three policy-relevant alternatives. We consider targeting metrics and social welfare under different curvatures of governments’ social welfare function, aggregate economic environments, and budgetary and political constraints. Updating the PMT data does not improve social welfare relative to the static PMT. Relaxing the eligibility threshold reduces the exclusion error, increases the inclusion error, and increases social welfare. A dynamic method that uses data on shocks to estimate a variable component of income reduces exclusion errors and limits the expansion in coverage, increasing social welfare during the economic crisis.

PER CAPITA CONSUMPTION ESTIMATION IN SURABAYA USING ENSEMBLE MODEL APPROACH

The categorization of the Low-Income Community category is based on the poverty indicators in the Multidimensional Poverty Index, including the dimensions of health, education, and living standards. The Proxy Means Test (PMT) can estimate household income or consumption by taking into account household conditions that are readily observable and cannot be manipulated. This method offers the advantage of being capable of determining both the poverty level of a household and the household's characteristics based on asset ownership and socio-demographic conditions. This study aims to estimate per capita consumption using OLS, Robust, Quantile, LASSO, and Ensemble methods. The application of these methods is intended to address various issues, including the presence of outlier data, multicollinearity, and uncertainties. The results indicate that none of the four methods used achieved the highest accuracy based on the MSE, MAE, and sMAPE criteria. Consequently, employing an ensemble model becomes essential to accommodate the element of uncertainty present in these four models. The application of the ensemble method is not only as a comparison between the models, but also as a means to capture the uncertainty contained in each model

Evaluation of a disability-inclusive ultra-poor graduation programme in Uganda: study protocol for a cluster-randomised controlled trial with process evaluation

BackgroundThere is little evidence on how to support ultra-poor people with disabilities to adopt sustainable livelihoods. The Disability-Inclusive Graduation (DIG) programme targets ultra-poor people with disabilities and/or women living in rural Uganda. The programme is an adaptation of an ultra-poor graduation model that has been shown to be effective in many contexts but not evaluated for people with disabilities.MethodsThe DIG programme works with project participants over a period of 18 months. Participants receive unconditional cash transfers for 6 months, training, access to savings-and-loans groups, and a capital asset that forms the basis of their new livelihood. The programme is also adapted to address specific barriers that people with disabilities face. Eligible households are clustered by geographical proximity in order to deliver the intervention. Eligibility is based on household screening to identify the ‘ultra-poor’ based on proxy means testing—both households with and without people with disabilities are included in the programme. Clusters are randomly selected prior to implementation, resulting in 96 intervention and 89 control clusters. The primary outcome of the trial is per-capita household consumption. Before the start of the intervention, a baseline household survey is conducted (November 2020) among project participants and those not offered the programme, a similar endline survey is conducted with participants with disabilities at the end of programme implementation in July 2022, and a second endline survey for all participants in October 2023. These activities are complemented by a process evaluation to understand DIG programme implementation, mechanisms, and context using complementary qualitative and quantitative methods. Ethical approval for the research has been received from Mildmay Uganda Research Ethics Committee and London School of Hygiene and Tropical Medicine.DiscussionDIG is a promising intervention to evaluate for people with disabilities, adapted to be disability inclusive across programme components through extensive consultations and collaboration, and has proven efficacy at reducing poverty in other marginalised groups. However, evaluating a well-evidenced intervention among a new target group poses ethical considerations.Trial registrationRegistry for International Development Impact Evaluations, RIDIE-STUDY-ID-626008898983a (20/04/22). ISRCTN registry, ISRCTN78592382. Retrospectively registered on 17/08/2023.

Alternative targeting methods for social assistance programs: Evidence from Tunisia

AbstractSocial assistance programmes are crucial in alleviating poverty, reducing inequality, and addressing social exclusion. The efficacy of these programmes hinges on the precision and efficiency of their targeting methods. Governments, especially in developing countries, can enhance the impact of social assistance programmes and ensure equitable resource distribution by accurately identifying the right individuals or households. This paper proposes two approaches to targeting beneficiaries of social benefits in Tunisia, including cash transfers and healthcare programmes. The first approach, a Mixed Means Test, extends the Proxy Means Test model by integrating individual/household assessments with explicit geographical targeting methods. The second is a multidimensional targeting strategy that explicitly considers the various deprivations faced by the households. Utilising data from the 2015 National Survey on Household Budget, Consumption, and Standard of Living, our results indicate that the targeting performance of the Mixed Means Test surpasses existing programmes both nationally and regionally, notably minimising inclusion and exclusion errors in the poorest regions of Tunisia. However, the multidimensional targeting approach identifies a higher number of potential beneficiaries compared to the current selection process in Tunisia. Including these households in social programmes may be hindered by limited monetary resources and the country's financial constraints. To address this, the multidimensional targeting approach enables the categorisation of potential beneficiaries into three mutually exclusive and collectively exhaustive groups based on their degree of deprivation.

Targeting Social Safety Nets: Evidence from Nine Programs in the Sahel

This paper analyzes household data from nine programs in the Sahel region using a harmonized approach to compare Proxy-Means Testing (PMT) and Community-Based Targeting (CBT) as conducted in practice, once geographical targeting has been applied. Results show that the targeting performance measured depends critically on the definition of the targeting objectives, share of beneficiaries selected, and indices used to evaluate targeting. While PMT performs better in reaching the poorest households based on per capita consumption, it differs little from CBT, random or universal selection when distribution-sensitive measures are employed, or when food security is used as the welfare metric. Administrative costs associated with targeting represent only a small share of budgets. Results emphasize the importance of studying programs as implemented in practice instead of relying on simulations of targeting performance. They also suggest that PMT and CBT contribute little to poverty or food insecurity reduction efforts in poor and homogeneous settings.

Predicting social assistance beneficiaries: On the social welfare damage of data biases

Abstract Cash transfer programs are the most common anti-poverty tool in low- and middle-income countries, reaching more than one billion people globally. Benefits are typically targeted using prediction models. In this paper, we develop an extended targeting assessment framework for proxy means testing that accounts for societal sensitivity to targeting errors. Using a social welfare framework, we weight targeting errors based on their position in the welfare distribution and adjust for different levels of societal inequality aversion. While this approach provides a more comprehensive assessment of targeting performance, our two case studies show that bias in the data, particularly in the form of label bias and unstable proxy means testing weights, leads to a substantial underestimation of welfare losses, disadvantaging some groups more than others.

Is The Wealth Index Better than The Proxy Means Test in Poverty Targeting? A Study in Brebes and East Jakarta

The ranking of household welfare status in targeting recipients of social protection programs is important and needs attention. Appropriate welfare status ranking is one of the keys for making the various types of programs designed by the government right on target. The Proxy Means Test method is popular in Indonesia in the 2015 Integrated Database Updating. Based on another popular statistical approach to ranking welfare status, the Wealth Index method is also known. Global surveys, such as Demographic and Health Surveys, Multiple Indicator Cluster Surveys, and World Food Program Surveys, have always used the Wealth Index to rank household welfare. Using Susenas data from March 2017 to March 2022, this study found that the Proxy Means Test method is better than the Wealth Index method in both Brebes Regency and East Jakarta City. The value of the classification error rate in Brebes Regency and East Jakarta City using the Proxy Means Test method is 13.94 percent and 10.37 percent, respectively. In comparison, the Wealth Index method is 25.12 percent and 14.74 percent. This research emphasizes that the results of the ranking of household welfare status are not only influenced by the method used but also by the socioeconomic conditions and characteristics of households data in the areas targeted by the program.

Machine learning and data augmentation in the proxy means test for poverty targeting

Recent years have seen increased interest in the use of alternative data sources in the definition and production of official statistics and indicators for the UN Sustainable Development Goals. In this paper, we consider the application of data science to the production of official statistics, illustrating our perspective through the use of poverty targeting as an application. We show that machine learning can play a central role in the generation of official statistics, combining a variety of types of data (survey, administrative and alternative). We focus on the problem of poverty targeting using the Proxy Means Test in Indonesia, comparing a number of existing statistical and machine learning methods, then introducing new approaches in the spirit of small area estimation that utilize area-level features and data augmentation at the subdistrict level to develop more refined models at the district level, evaluating the methods on three districts in Indonesia on the problem of estimating 2020 per capita household expenditure using data from 2016–2019. The best performing method, XGBoost, is able to reduce inclusion/exclusion errors on the problem of identifying the poorest 40% of the population in comparison to the commonly used Ridge Regression method by between 4.5% and 13.9% in the districts studied.

Which Fantasy Sports Players Will Bet on Sports? A Trait-Based Predictive Model of Fantasy Sport Players Engaging in Sports Betting

Abstract: Fantasy sports is a favorite form of sports consumption, and sports betting is becoming increasingly more popular and accessible. Following the recent Supreme Court decision concerning legalization, many fantasy sports operators are now incorporating sports betting into their platforms to capitalize on this opportunity. However, little research examines the motivations behind why some fantasy players bet on sports while others do not. Using a trait-based model, we investigate the likelihood that fantasy sports players would also engage in sports betting, revealing that traits are predictive of sports betting behavior. Given that traits are not readily observable or easily accessible, a proxy model incorporating commonly available demographic variables is also specified and estimated. Support for our proxy model is found in the widely used proxy means test devised to identify and target those eligible for social programs. As a result, this research is both theoretically driven and actionable.

Does social assistance disincentivise employment, job formality, and mobility?

How do cash transfers affect employment, job formality, and mobility, especially in times of crises and economic recovery? I examine this question in the context of Indonesia’s major unconditional cash transfer (UCT) programmes, rolled out in a targeted manner in response to adverse economic shocks. Identification is based on a generalised difference-in-differences with propensity score matching approach exploiting three waves of nationally representative longitudinal data on household transfer receipts and labour market outcomes. Annual retrospective data in each survey wave allows me to look at immediate effects, potentially important due to the transient nature of the transfers. Consistent with the income and substitution effects, when cash transfers are distributed using a more precise proxy-means test and current, dynamic welfare information, beneficiaries are more likely to adjust their labour supply in order to qualify for or maintain their benefits. Individuals with lower skill levels show a more pronounced response, with a significant decrease in both employment and job formality. The larger effect on job formality highlights the importance of the adjustment margin through the substitution effect associated with the targeting design.

Government social protection programme spending and household welfare in Lesotho

AbstractLesotho has notably high levels of poverty and inequality despite a high level of government spending on social protection programmes. We assess the performance of this spending in reducing consumption poverty and inequality, applying benefit incidence and microsimulation methods to 2017/2018 household survey data. We investigate the distributional effects of actual spending as well as those of a hypothetical alternative in which the spending is targeted through a proxy means test (PMT) formula used by the government for some programmes. We find that government spending on social protection programmes in Lesotho substantially reduces poverty and inequality. For most programmes, the hypothetical alternative of targeting spending to poorer households through the government's PMT formula would have no better distributional effects than current programme spending. The exception is postsecondary education bursaries, which are costly and regressive. Retaining bursaries only for poorer students, and reallocating the outlay this saves to a transfer targeted to poorer households through the government's PMT formula, could reduce poverty and inequality significantly.

Liver Transplantation: A Right or a Privilege? Sustainable Liver Transplant Financing With an Innovative Model for the Developing World

Living donor liver transplant in addition to its lifesaving therapy is a cost-effective alternate to long-term disease management in patients with chronic liver disease. Financial constraint is the biggest hurdle faced by patients in developing countries in availing the liver transplantation. So, we conducted this study to report a government-funded financial support system for liver transplant services. A total of 198 patients who underwent living donor liver transplant with at least 90 days follow-up were included in the study. According to proxy means test score, 52.2% patients were from low and middle socioeconomic groups and 64.6% of patients underwent liver transplantation through government support. Out of 198 patients who underwent liver transplantation 29.6% had monthly income below 25,000 Pakistani rupees ($114). In recipients, 90-day mortality was 7.1% and morbidity was 67.1%. Donor morbidity was 23.2% without any mortality. This financial model can serve as a valuable source for middle and low income group countries to overcome the financial challenge and make liver transplant an accessible, affordable, and economically viable option.

The dynamics of poverty targeting

Several recent papers have compared the ability of proxy-means testing (PMT) and community-based targeting (CBT) to identify consumption-poor households. Motivated by the facts that targeted benefits typically reach beneficiaries with a substantial time lag and that transitions into and out of poverty are frequent, we assess PMT’s and CBT’s performance during the years following the targeting exercise. With original data from Burkina Faso, we replicate the finding that PMT outperforms CBT at baseline. But this pattern disappears for households’ poverty status 12 and 30 months later where both methods perform equally well. For real-world welfare programs where benefits typically accrue with a substantial time lag, our results suggest that CBT’s targeting performance is better than commonly thought.

A hybrid approach to targeting social assistance

Proxy means testing (PMT) and community-based targeting (CBT) are two of the leading methods for targeting social assistance in developing countries. We present a hybrid targeting method that incorporates CBT’s emphasis on local information and preferences with PMT’s reliance on verifiable indicators. Specifically, we outline a Bayesian framework for targeting that resembles PMT in that beneficiary selection is based on a weighted sum of sociodemographic characteristics, but we instead propose calibrating the weights to preference rankings from community targeting exercises. We discuss several practical extensions to the model, including a generalization to multiple rankings per community, an adjustment for elite capture, a method for incorporating auxiliary information on potential beneficiaries, and a dynamic updating procedure. We further provide an empirical illustration using data from Burkina Faso and Indonesia, which shows that our method achieves error rates lower than what PMT achieves when targeting household expenditures.

Estimating poverty for refugees in data-scarce contexts: an application of cross-survey imputation

The increasing growth of forced displacement worldwide has brought more attention to measuring poverty among refugee populations. However, refugee data remain scarce, particularly regarding income or consumption. We offer a first attempt to measure poverty among refugees using cross-survey imputation and administrative and survey data collected by the United Nations High Commissioner for Refugees (UNHCR). Employing a small number of predictors currently available in the UNHCR registration system, the proposed methodology offers out-of-sample predicted poverty rates that are not statistically different from actual poverty rates. These estimates are robust to different poverty lines, perform well according to targeting indicators, and are more accurate than those based on asset indexes or proxy means tests. They can also be obtained with relatively small samples. We additionally show that it is feasible to provide poverty estimates for one geographical region based on existing data from another similar region.

When Poverty Reduction Meets Democracy: An Investigation into the Use of Different Evaluation Methods for Assessing the Effectiveness of a Social Program

Abstract This paper evaluates the minimum living standard guarantee program (Dibao) in rural China using several methods including the income approach, the multidimensional poverty approach, and a proxy means test approach. We find that the targeting accuracy of the program appears greater the more comprehensive the evaluation method used—but all these methods find low levels of targeting accuracy. Because Dibao fund allocation is largely decided by the villagers, who take a more holistic view in selecting “poor” households than the various evaluation methods, we argue that the low targeting efficacy may be due to the lack of comprehensive evaluation method, as opposed to the low targeting of the program itself. This paper argues that the community-based targeting used by the Dibao program may be a better way to combat poverty in many developing countries, as it requires less administrative capacity and overcomes the difficulties of identifying poor households that qualify for assistance.

Targeting social safety net programs on human capabilities

• We develop an alternative method for targeting social safety net programs that uses the capabilities approach as a normative framework. • We adapt Bayesian additive regression trees for the estimation of human capabilities and use the resulting estimates as a basis for targeting. • We examine the implications of our method through a variety of simulation exercises and with real data from a field experiment in Indonesia. • Relative to traditional approaches, our method identifies a fundamentally different and arguably more disadvantaged group of beneficiaries. Conventional approaches to targeting social safety net programs select beneficiaries on the basis of income or expenditure levels. We argue that these approaches neglect human diversity and agency, which can lead to counterintuitive targeting outcomes and thus a misallocation of benefits. In light of these issues, we develop an alternative method for targeting that is based on the capabilities approach, which we claim provides a more rigorous normative framework for targeting that respects both human diversity and agency. In particular, we adapt Bayesian additive regression trees for the estimation of human capabilities and demonstrate how the resulting estimates can be used to target social safety net programs. We examine the targeting implications of our method through a variety of simulation exercises and also with real data from a field experiment conducted in Indonesia. Relative to more traditional approaches – including not only the full and proxy means test, but also community-based targeting – we find that our method identifies a fundamentally different and arguably more disadvantaged group of beneficiaries.

Targeting Cash Transfers on the “Poorest of the Poor” in the Slums: How Well Did the Kenya’s Older Persons Cash Transfer Programme Perform?

ABSTRACT In resource poor environments, identifying those most in need of limited available resources is challenging. Kenya’s older persons cash transfer programme (OPCT) targeted at the most poor used a 2-stage targeting process to identify beneficiaries, combining community-based selection with a proxy means-test. This paper investigates whether the process “correctly” identified targeted vulnerable older people in Nairobi’s informal settlements and whether receipt of the OPCT resulted in an improvement in perceived financial wellbeing. Regression results show that individuals with greater need were covered under the OPCT. Using propensity score matching, the paper evidences that the OPCT improved subjective financial wellbeing among beneficiaries.

Performance of a novel machine learning-based proxy means test in comparison to other methods for targeting pro-poor water subsidies in Ghana

Access to safe drinking water is still very low among the poorest households in sub-Saharan Africa, and economic shocks can make water access even more difficult for poor consumers. Water subsidies can be a solution to enhance access to safe water services, but they are often ineffective as they regularly fail to reach the very poor. In this study, we developed a new Machine Learning-based proxy means test (ML-based PMT) to identify the poorest households and field-tested it in comparison to four other methods (the Demographic and Health Survey (DHS) wealth index, the Poverty Probability Index (PPI), Community Based Targeting (CBT) and the Ghana Government's Livelihood Empowerment Against Poverty (LEAP) program). We first developed our new ML-based PMT by applying machine learning techniques to the nationally-representative 2016–2017 Ghana Living Standards Survey and compared its performance with an existing PMT (the PPI). We then compared the strengths and weaknesses of this new method in three rural towns of southwestern Ghana against the four other methods, with respect to the characteristics of households they identified, their ease of implementation, their cost, and their acceptability among local stakeholders. In our field assessment we found that our new ML-based PMT performed better than most other approaches at screening out households having assets associated with wealth, but it had higher implementation costs than CBT and LEAP. Local government officials considered CBT to be more transparent than the PMTs, while community members perceived the PMTs to be fairer.By highlighting the strengths and weaknesses of five different targeting methods, this study provides guidance to practitioners in choosing the most appropriate methods to target poor households eligible for water subsidies in rural Ghana.