Generalized Propensity Score Method Research Articles

Impact of post-disaster federal assistance on the national flood insurance program

This research tested the hypothesis that post-disaster federal relief program crowds out the demand for flood insurance in the U.S. To do that, this research has collected historical data between 2016 and 2020, and conducted propensity score-based analysis to understand the causality between post-disaster federal assistance and flood insurance enrollment in the flood affected counties in the U.S. In the first part, the treatment variable has been considered as binary to compare the effect of the availability of federal assistance to that of non-availability of federal assistance in a flood affected county by using propensity score matching method. It was found that the availability of the federal payout in a county in a year increased the number of flood insurance policies by 5.2 % and the total insured value of the policies by 4.6 % in the following year. Next, the treatment variable was considered continuous and was used in a generalized propensity score method to develop a dose response function, i.e., a function that depicts the changes in the outcome variables based on different levels of treatment. It was found that for each 1000 households in a county that received federal assistance, the percentage increase in the number of flood insurance policies was 3.41 %. On the other hand, for each million-dollar of federal assistance in a county, the total insured value of the flood insurance policies increased by 1.96 %. Therefore, this research has concluded that, contrary to the hypothesis, the availability of post-disaster federal assistance increased the flood insurance enrollment in the U.S.

Impact of postprocedural minimum lumen area on clinical outcome after femoropopliteal drug-eluting stent implantation.

Although favorable results of fluoropolymer-based drug-eluting stent (FP-DES) treatment for femoropopliteal lesions have been reported, it is unclear whether minimal lumen area (MLA) after FP-DES implantation affects clinical outcomes. This study aimed to reveal the association between intravascular ultrasound (IVUS)-evaluated MLA and the 1-year risk of restenosis and aneurysmal degeneration after FP-DES implantation for femoropopliteal lesions. A subanalysis of the CAPSICUM (Contemporary outcomes After Paclitaxel-eluting peripheral Stent implantation for symptomatic lower limb IsChemia with sUperficial feMoral or proximal popliteal lesion) study analyzed 718 limbs in 686 patients with available IVUS-evaluated MLA data. The association of MLA with the 1-year risk of restenosis and aneurysmal degeneration was analyzed using the generalized propensity score method. The 1-year incidence rate of restenosis was estimated to be 8.8% (95% CI, 6.1% to 12.5%) for the upper quartile of MLA (21.1 mm2) versus 14.3% (95% CI, 10.7% to 18.7%) for the lower quartile of MLA (15.2 mm2), with an odds ratio of 0.58 (95% CI, 0.36 to 0.93; p = 0.024), whereas the 1-year incidence rate of aneurysmal degeneration was 23.8% (95% CI, 19.5% to 28.8%) for the upper quartile versus 16.8% (95% CI, 12.6% to 22.0%) for the lower quartile, with an odds ratio of 1.55 (95% CI, 1.04 to 2.32; p = 0.031). A large MLA after FP-DES implantation for femoropopliteal lesions was associated with decreased restenosis risk but increased aneurysmal degeneration risk. These findings suggest that MLA is a valuable predictor of clinical outcomes.

Parental Son Preference and Depression in Later Life: The Moderating Role of Childhood Friendship Experience

We investigated the relationship between parental son preference experienced during childhood and depression symptoms experienced by Chinese men and women aged 45 years and over. Data were obtained from the China Health and Retirement Longitudinal Studies conducted in 2014 and 2018. Multiple regression analysis was the primary method of model assessment, and the generalized propensity score method was used for robustness checks. We found there was a positive correlation between parental son preference and depression symptoms in later life. The relationship between parental son preference and depression symptoms was also age accumulative and there was a gender heterogeneity effect. Childhood friendship experience mitigated the positive effect of parental son preference on depression symptoms in later life. Our findings emphasize the influence of parental son preference during childhood on depression symptoms in later life, and show that childhood friendship experience can reduce the strength of this link.

Bilingualism and intelligence in children exposed to poverty environments: A Raven's error pattern analysis using a generalized propensity score method

The main objective of this study is to compare the quantitative (correct answers) and qualitative (error types) performance of children belonging to different linguistic groups on a non-verbal reasoning test, Raven's Colored Progressive Matrices Test, after being matched based on level of exposure to poverty, certain individual characteristics and test performance. The sample is representative for Mexico at a population level and consists of children aged 5 to 12 (n = 4644), of which 671 are bilingual in Spanish and an indigenous language, 3970 are monolingual in Spanish and 78 are monolingual in an indigenous language. The results show significant quantitative differences with a lower overall performance in the Raven's test by bilingual children as compared to their monolingual (Spanish only) peers, but no qualitative differences when analyzing their error types. When considering each linguistic group individually, the relative frequency of three error types (Repetition, Wrong Principle, and Incomplete Correlate) is similar in children aged 5 to 8 and in those aged 9 to 12. However, considering the two age cohorts, the results reveal how the intragroup differences in each linguistic group, are only statistically significant in the case of Difference errors, in the group of monolingual children in Spanish.In addition to practical use that may be potentially derived from this empirical evidence, these results may also be encouraging from a methodological point of view. They demonstrate how the method used, in addition to permitting greater comparison between the experimental groups of a representative sample at a population level, does not present high sensitivity, either for the model used to estimate the Generalized Propensity Score method, or for the specific estimator used.

Institutions and economic development: new measurements and evidence

We propose a new set of indices to capture the multidimensionality of a country’s institutional setting. Our indices are obtained by employing a dimension reduction approach on the institutional variables provided by the Fraser Institute (2018). We estimate the impact that institutions have on the level and the growth rate of per capita GDP, using a large sample of countries over the period 1980–2015. To identify the causal effect of our institutional indices on a country’s GDP we employ the Generalized Propensity Score method. Institutions matter especially in low- and middle-income countries, and not all institutions are alike for economic development. We also document non-linearities in the causal effects that different institutions have on growth and the presence of threshold effects.

우리나라 초등학생의 그릿(Grit)수준이 인지, 정서, 사회 발달에 미치는 영향

The purposes of this study were to identify the effect of Grit on cognitive, emotional, and social development and to investigate the differencial effect accroding to the type of student's life-long goal, and the level of household income. To do this, 9th to 11th waves of the Panel Study of Korean Children(PSKC 2018) were utilized, and generalized propensity score method applied. The results of this study were as follows. First, happiness, self-esteem, concentration, positive parenting attitude significantly influenced on students’ grit score(perseverance of efforts). The frequency of conversation with parents, the smart phone and PC utilization, and the sense of alienation affect students' grit score(consistency of interest). Second, Grit had a positive effect on students' happiness, self-esteem, life satisfaction, and peer relationships. Third, Grit showed differential effects on emotional, and social development according to the type of student's life-long goal, and the level of household income. Based on these results, the implications of this study and suggestions for future study were discussed.

Investigating the Differential Effects of Early Child Care and Education in Reducing Gender and Racial Academic Achievement Gaps From Kindergarten to 8th Grade

We used the generalized propensity score method to estimate the differential effects of five Early Child Care and Education (ECCE) experiences (Prekindergarten, Head Start, Center-based Child Care, Home-based Child Care, and Parental Care) in reducing math and reading achievement gaps between boys versus girls, Latinx versus Whites, and Blacks versus Whites. Findings revealed differential effects of ECCE in reducing gender and racial achievement gaps. However, results indicated that significant gender and racial gaps still exist despite ECCE experiences and that these gaps widen throughout the elementary and middle school years.

Identifying and Estimating Causal Moderation for Treated and Targeted Subgroups

Extant literature on moderation effects narrowly focuses on the average moderated treatment effect across the entire sample (AMTE). Missing is the average moderated treatment effect on the treated (AMTT) and other targeted subgroups (AMTS). Much like the average treatment effect on the treated (ATT) for main effects, the AMTS changes the target of inferences from the entire sample to targeted subgroups. Relative to the AMTE, the AMTS is identified under weaker assumptions and often captures more policy-relevant effects. We present a theoretical framework that introduces the AMTS under the potential outcomes framework and delineates the assumptions for causal identification. We then propose a generalized propensity score method as a tool to estimate the AMTS using weights derived with Bayes Theorem. We illustrate the results and differences among the estimands using data from the Early Childhood Longitudinal Study. We conclude with suggestions for future research.

The sociocultural mechanism of obesity: The influence of gender role attitudes on obesity and the gender gap

Worldwide, women are more likely to be obese than men, but research on the mechanism of the gender gap in obesity is relatively lacking. This article uses five rounds of Chinese General Social Survey (CGSS) data from 2010 to 2017 to empirically test the impact of gender role attitudes on obesity and the gender gap and to explore the mechanism. The main results show that the traditional gender role attitude will improve the probability of obesity in women, but it will not positively impact obesity in men. Using the proportion of “March 8th red flag bearer” at the provincial level as an instrumental variable to alleviate the possible estimation errors caused by omitted variables, the results show that the lower the proportion of red flag bearers, the higher the probability of obesity of women, and still will not improve the probability of obesity of men. The robustness test based on the generalized propensity score method (GPSM) supports the above results. The mechanism analysis shows that economic status and market participation are two essential mechanisms of gender role attitudes and female obesity. Traditional gender role attitudes increase the risk of women's obesity by reducing their economic status and labour market participation.

The Effect of Community Socioeconomic Context on High School Attendance in China: A Generalized Propensity Score Approach

Many developing countries have experienced increasing spatial inequality, but little is known about the effect of community disadvantages on educational attainment in these societies. Using data from the China Family Panel Studies (2010–2016), I examine the effect of community socioeconomic status (SES) on the transition into high school in urban and rural China, and I explore several mechanisms explaining the community effects. I adopt the generalized propensity score method to estimate the potential probability of high school entrance at different levels of community SES. Results show that community SES is positively associated with high school attendance in both urban and rural China, and the relationship is stronger in more disadvantaged communities in both contexts. In urban areas, the effect of community SES is partly attributable to collective socialization and children’s academic performance. In rural areas, spatial accessibility to high schools and children’s academic performance are the salient mechanisms.

Vulnerability and impact of climate variability on Peruvian artisanal fisheries

ABSTRACT The aim of this study is to analyse the effects of climate variability on the poverty of artisanal fishers in Peru. First, an index of vulnerability of artisanal fishers in the face of climate variability along the Peruvian coast was calculated. This index consists of three components (exposure, sensitivity, and adaptability) and classifies the vulnerability of a study area in a range from 0 to 1. Second, using the generalized propensity score method, the effect of climate variability that occurred in 2015 on the poverty of artisanal fishers in three areas of the Peruvian coast was estimated. This effect is calculated through the variation of the probability of poverty among the artisanal fishers from high to low according to the degree of economic impact. The results confirmed a positive relationship between the calculated vulnerability index and poverty levels; the North was the most vulnerable area (0.67), followed by the Centre (0.61) and the South (0.43). Likewise, the areas with stronger effects of climate variability exhibited greater variation in the probability of poverty (North: 12%, Centre: 11% and South: 4%). Finally, the results show the importance of the adaptive capacity of artisanal fishers in the face of changes in climatic conditions.

Alleviating multi-dimensional poverty through land transfer: Evidence from poverty-stricken villages in China

This study constructs a Ramsey–Cass–Koopmans growth model of the agricultural sector, which includes land transfer characteristics, to investigate the theoretical basis of the land transfer impact on multi-dimensional poverty, under a steady equilibrium. Using 2010, 2012, and 2014 panel data from the Mutual Aid Fund for Poverty-Stricken Villages in China, we obtained results indicating the impact of land transfer on multi-dimensional poverty, based on the generalized propensity score method. The research results are as follows: (1) The intensity of rural households' land transfer in poverty-stricken villages remains low, at only 14.54%; however, it demonstrates an increasing trend. (2) When the intensity of land transfer is continuously enhanced, the multi-dimensional poverty of rural households in poverty-stricken villages decreases. (3) Rural households' land transfer in poverty-stricken villages can reduce multi-dimensional poverty by improving their savings behavior. “Precautionary savings motivation” is an important land transfer mechanism affecting rural households' multi-dimensional poverty in poverty-stricken villages.

Institutions and Economic Development: New Measurements and Evidence

We propose a new set of indices to capture the multidimensionality of a country’s institutional quality. Our indices are obtained by employing a dimension reduction approach on the institutional variables provided by the Frazer Institute (2018). We estimate the impact that our measures of institutional quality have on the level and the growth rate of per capita GDP, using a large sample of countries over the period 1980-2015. To identify the causal effect of our measures of institutional quality on a country’s GDP dynamics we employ the Generalized Propensity Score method. Institutions matter especially in low- and middle-income countries, and not all institutions are alike for economic development. For this group of countries, we find: i) a positive correlation between our main institutional index and the GDP growth and ii) that improvement in the reliability and fairness of the legal system leads to a higher long-run per capita GDP level. We also document non-linearities in the causal effects that different institutions have on growth, and the presence of threshold effects.

Job qualification programs for young apprentices: an analysis in the Brazilian Midwest

PurposeThe aim of this study is to evaluate five job qualification programs for young apprentices, in Goiás, a Brazilian State. We expect to contribute to the improvement and strengthening of the job training programs in developing countries.Design/methodology/approachWe applied propensity score matching and extensions such as the generalized propensity score method (dose–response effect).FindingsWe found evidence of the heterogenous effects of the five job qualification programs on employability. We found that the duration of the programs influences employability in up to two years after the program.Research limitations/implicationsThis research is based on secondary data provided by the responsible institutions. The evidence is obtained through a nonexperimental method.Practical implicationsThe research has implications for public or private institutions dedicated to the professional qualification of young apprentices.Social implicationsThe findings of the study provide some ways of comparing training programs, for young workers, that can be applied in different types of institutions.Originality/valueThis study provides new insight about the professional qualification of young apprentices, by comparing fives programs in Midwest Brazil.

Impact of power outages on households in developing countries: Evidence from Ethiopia

Abstract In developing countries, access to electricity has received much attention. However, the reliability of its supply has been given less focus, though power outages happen frequently and are expected to limit gains from electricity connection. In this paper, I go beyond electricity connection and provide an average estimate of monthly defensive expenditures at different monthly hours of power outages for urban households in Ethiopia, using the generalized propensity score method. I also elicit households' willingness to pay for improved electricity supply, using a stated preference method, to account for non-monetary costs of outages. Based on the average estimated results, a back-of-the-envelope calculation for urban households of Ethiopia with electricity connection provides a monthly defensive expenditure of US$14.8 million and a monthly willingness to pay of US$6.2 million for improved electricity supply, on top of the regular electricity bill. The study underscores that connection to electricity is not enough; the reliability of its supply is also important.

Impacts of woody invasive alien plant species on rural livelihood: Generalized propensity score evidence from Prosopis spp. invasion in Afar Region in Ethiopia

This study applied a generalized propensity score method to evaluate the impact of Prosopis invasion on Afar pastoralist and agro-pastoralist households’ annual per capita consumption expenditure, as a proxy of rural livelihoods. The analysis was based on cross-sectional survey data collected in mid-2016 from 250 households in the Afar National Regional State in Ethiopia. The method was applied to match households with similar covariates with different Prosopis invasion levels. The method was effective in teasing out non-linear causal relationships between Prosopis invasion dose and household per capita consumption expenditure. Average dose-response or impact function was obtained by estimating average annual household per capita consumption expenditure at different levels of Prosopis invasion. Initially, the plants’ impact was positive, but turned negative after an optimum invasion dose. The optimal invasion dose of Prosopis was found to be 22.23%. The corresponding optimum level of annual household per capita consumption expenditure was found to be 4,500.50 Ethiopian Birr (USD 198). The results suggest that to maximize the benefits of Prosopis and minimize its adverse effects on the livelihoods of the pastoral and agro-pastoral communities, diverse management strategies that take into account not only the intensity of invasion, but also patterns of dryland economy should be implemented.

The effects of nutrients on stream invertebrates: a regional estimation by generalized propensity score

IntroductionThe effects of nutrients on stream conditions within individual streams or small areas have been studied extensively, but the same effects over a large region have rarely been examined due to the difficulty of applying large-scale manipulative experiments. In this study, we estimated the causal effects of nutrients within the Western United States on invertebrate richness, an important biological indicator of stream conditions, by using observational data.MethodsWe used the generalized propensity score method to avoid the common problem of statistical inference using observational data, i.e., correlation established based on observational data does not imply a causal relationship because the effects of confounding factors are not properly separated.ResultsOur analysis showed a subsidy-stress relationship between nutrients and invertebrate taxon richness in the whole Western United States and in its sub-ecoregions. The magnitude of the relationship varies among these sub-ecoregions, suggesting a varying nitrogen effect on macroinvertebrates due, in large part, to the varying natural and anthropogenic conditions from ecoregion to ecoregion. Furthermore, our analysis confirmed that causal estimation results using regression can be sensitive to the imbalance of confounding factors.ConclusionsStratifying data into ecoregions with relatively homogeneous environmental conditions or adjusting data by generalized propensity score can improve the balance of confounding factors, thereby allowing more reliable causal inference of nutrient effects. Invertebrates respond to the same nutrient levels differently across different site conditions.

Embracing the Generalized Propensity Score Method: Measuring the Effect of Library Usage on First-Time-In-College Student Academic Success

Abstract
 
 Objective – This research focuses on First-Time-in-College (FTIC) student library usage during the first academic year as number of visits (frequency) and length of stay (duration) and how that might affect first-term grade point average (GPA) and first-year retention using the generalized propensity score (GPS). We also want to demonstrate that GPS is a proper tool that researchers in libraries can use to make causal inferences about the effects of library usage on student academic success outcomes in observation studies. 
 
 Methods – The sample for this study includes 6,380 FTIC students who matriculated in the fall 2014 and fall 2015 semesters at a large southeastern university. Students’ library usage (frequency and duration), background characteristics, and academic records were collected. The Generalized Propensity Score method was used to estimate the effects of frequency and duration of FTIC library visits. This method minimizes self-selection bias and allows researchers to control for 
 
 demographic, pre-college, and collegiate variables. Four dose-response functions were estimated for each treatment (frequency and duration) and outcome variable (GPA and retention).
 
 Results – The estimated dose-response function plots for first-term GPA and first-year retention rate have similar shapes, which initially decrease to the minimum values then gradually increase as the treatment level increases. Specifically, the estimated average first-term GPA is minimized when the FTIC student only visits the library three times or spends one hour in the library during his/her first semester. The threshold for first-year retention occurs when students visit the library 15 times or spend 21 hours in the library during their first semester. After those thresholds, an increase in students’ library usage is related to an increase in their academic success.
 
 Conclusions – The generalized propensity score method gives the library researcher a scientifically rigorous methodological means to make causal inferences in an observational study (Imai & van Dyk, 2004). Using this methodological approach demonstrates that increasing library usage is likely to increase FTIC students’ first-term GPA and first-year retention rates past a certain threshold of frequency and duration.

Measuring the effects of preservation on farm profits in a continuous treatment setting

ABSTRACTDespite billions of dollars of public appropriations to state purchase of development rights (PDR) programmes, there has been limited evaluation of the effects of these investments on the economic performance of preserved farms. This article estimates dose-response functions to evaluate the effects of enrolment in New Jersey’s PDR programme on farm profitability. The generalized propensity score method in a continuous treatment setting is used to address selection bias arising from voluntary programme participation. Treatment effects are measured across treatment levels to determine whether farm profitability is affected differently across levels of programme participation. Our findings reveal that, relative to unpreserved farms, profit per acre tends to increase along lower treatment levels. The profit per acre of preserved farms in the 1–40% treatment range is, on average, $407 higher than that of unpreserved farms in the full sample. Positive profit differentials averaging between $317 and $472 per acre are also observed in the 1–20%, 1–40% and 1–60% treatment quintiles in the farming occupation sample. We do not observe statistically significant profitability differentials when treatment effects are averaged across all positive treatment values.

Generalized propensity scores for multiple continuous treatment variables

This paper illustrates that the generalized propensity score method can easily be applied with multiple continuous endogenous treatment variables. Consistency proofs carry over straightforwardly to this general case, and the approach is shown to work well in finite samples with various data-generating processes and up to five continuous endogenous treatment variables.