Instrumental Variable Estimation Strategy Research Articles

College Gap Time and Academic Outcomes for Women: Evidence from Missionaries

Abstract This study leverages a policy change in the missionary program of The Church of Jesus Christ of Latter-day Saints that exogenously influenced the likelihood that a woman took gap time during college to understand how gap time influences women's subsequent choice of major and academic outcomes. If structured gap time shapes educational outcomes, increasing the uptake of gap time by women may be a mechanism to ameliorate later wage gaps. Using administrative data from Brigham Young University (N = 17,402) and an instrumental variables estimation strategy, we find that women who take gap time for missionary service shift into majors with higher expected salaries and are more likely to be in limited-enrollment majors and majors with a higher concentration of men. However, gap time decreases the likelihood of graduating within eight years of entering college, creating tension between the costs and benefits. On average, net benefits of expected wages are close to zero. Gap time most clearly benefits women with relatively low ACT scores who are more likely to be accepted into limited enrollment programs following gap time. This research informs university administrators and students alike seeking to understand the academic implications of taking planned time off during postsecondary education.

Competition and Competitors: Evidence from the Retail Fuel Market

Policy makers and antitrust authorities are concerned about the lack of competition in the fuel retail market and its impact on consumer prices. The aim of this article is to empirically evaluate the role of the intensity of competition and competitors’ brand affiliation on retail fuel prices. To this end, we use a panel data set with detailed daily on nearly 8,500 gas stations and 2 million price observations; we estimate a reduced-form fuel price equation that accounts for supply (input costs and local competition) and demand shifters (income, traffic intensity, and location) as well as for brand and time fixed effects. We use an instrumental variable estimation strategy, to account for the endogeneity of the intensity of competition. Our results show that premium brands and low-cost brands affect the prices of rival firms in an opposite way. On the one hand, premium brands soften competition in the local markets where they operate and thereby allow their rivals to set higher prices. Besides, price setting by premium-brand stations react differently depending on whether the nearest rival sells the same brand (a friendly competitor) or some other brand. By contrast, low-cost brands contribute to reducing prices through their own prices (direct effect), thereby encouraging competitors to lower their prices (indirect effect). Our results suggest that regulation limiting the entry of premium operators whilst promoting the entry of low cost gas stations will enhance competition at the retail level.

Issue Responsiveness in Canadian Politics: Are Parties Responsive to the Public Salience of Climate Change in the Question Period?

This paper explores how politicians respond to the public salience of policy issues when determining which topics to publicly address. Using new data and state-of-the-art methodology, our study provides a fresh perspective on this fundamental question. We focus on a multi-party parliamentary system, specifically the Canadian House of Commons, with a specific emphasis on the issue of climate change. To assess the attention given by political parties to various policy issues, we analyze transcripts from the Question Period spanning from April 2006 to June 2021. To gauge the public’s level of concern for these issues, we incorporate data obtained from Google Trends. Employing an instrumental variable estimation strategy, our study causally estimates the extent to which the public salience of climate change influences elite attention. Our findings reveal that the public salience of climate change significantly influences the attention given to this issue by parties, albeit with noticeable partisan variations. Moreover, our research highlights the effectiveness of the Question Period in compelling the government to address challenging or potentially embarrassing issues. Lastly, we uncover evidence suggesting that the Liberal Party of Canada successfully increased the public salience of climate change during its tenure in government.

An Empirical Study of the Pathway Model Link Between Cognitive Distortions and Gambling Problems.

This research empirically tests the relationship between gambling-related cognitive distortions and the development of gambling problems. In two separate studies using methodologies designed to support non-experimental causal inference, we demonstrate that holding false beliefs about gambling experiences is related to current and future risk of developing problems with gambling. In our first study, we use an instrumental variable estimation strategy on an internet sample (n = 184) and observe a statistically significant relationship between Gamblers' Belief Questionnaire scores and measures of loss chasing, overspending, and gambling problems. These findings were robust to linear and ordinal estimation strategies and multiple model specifications. In our second study, we examine five-year prospective longitudinal data (n = 1,431) to validate our initial findings and test whether irrational thoughts are also related to future problems with gambling. While controlling for current fallacies, we find that past Gambling Fallacies Measure scores are related to present gambling problems across two survey waves. The effect size of each of the past fallacy levels is roughly half of the effect size of present levels, suggesting meaningful impacts. Our findings support the Pathways Model of Problem and Pathological Gambling.

The Economic Impact of Public Capital: Evidence from Chinese Prefectures and Firms

This study estimates the economic impact of public capital by constructing the public capital stock of 214 prefectures in China from 1999 to 2006 and combining the data of both prefectural economies and manufacturing firms. Using an instrumental variable estimation strategy, the empirical results show that public capital increases aggregate output in the economy, specifically in the secondary and tertiary sectors. Such growth mainly comes from the increased labor supply and reduced labor costs and, hence, more firms emerge.

Returns to grid electricity on firewood and kerosene: Mechanism

Household dependence on firewood is ubiquitous in developing countries, undermining the carbon services that forests provide. In addition, kerosene is widely used for lighting that emits black carbon. This study examines the effect of grid electricity on firewood consumption and kerosene by using an instrumental variable (IV) estimation strategy, and it evaluates the underlying mechanisms. I use three waves of large sample household surveys from Bhutan and other administrative data to complement the main results. The results show that grid electricity reduces firewood consumption by approximately 0.83–2.09 cubic meters per month and electrified households are approximately 61%–71% less likely to use kerosene as lighting fuel. Households respond to electricity provision by adopting basic electrical appliances and electricity for lighting. The results also suggest that the effect of electricity on firewood consumption is driven by road accessibility and that the reduction in firewood consumption is larger for richer households. However, I do not find such evidence for kerosene. Furthermore, one electrified household saves emissions of approximately 5.9 tCO2 and 5.2 tCO2e of black carbon annually from displaced firewood consumption. Similarly, kerosene displaced due to electricity is associated with approximately 2.45 tCO2e black carbon annually.

Age at First and Current Marriage and Women’s Entrepreneurship in Nigeria

This paper relies on the 2008 and 2013 Nigeria Demographic and Health Surveys and an instrumental variable estimation strategy to estimate the relationship between a Nigerian woman’s age at entry into her first and current marriage and entrepreneurship. The result suggests a 5-percentage point higher likelihood of engaging in entrepreneurship for women with an additional year of at marriage entry. Further, there is about a 12-percentage point increase in the likelihood of continuous engagement in self-employed work over the prior year with an additional year of age at marriage entry. This result is consistent for women who reside in rural and urban locations. Premarital investments in education, lower fertility, and better intramarriage bargaining power are the likely operative channels that explain the estimated relationship. HIGHLIGHTS Early marriage entry has economic costs and hurts women’s overall empowerment. Early marriage in Nigeria is mainly influenced by religious and cultural factors. Women who marry early are less likely to engage in entrepreneurship and to do so continuously. There are no geographic differences in the effects of early marriage entry on entrepreneurship. Later marriage is associated with better education, declining fertility, and improved bargaining power of women.

Broadband Internet and Income Inequality

Abstract Digital technologies like the Internet can affect income inequality through increased demand for employment in manual and abstract jobs and reduced demand for employment in routine jobs. In this paper, we combine city-level income distribution and jobs data with broadband data from France to investigate the impact of broadband Internet access on income inequality. Using an instrumental variable estimation strategy, we find that broadband Internet reduces income inequality through increased employment in manual jobs. These effects increase with the availability of skilled workers and are significant in cities with a large service sector or high-speed Internet access. Further, the diffusion of broadband Internet comes with relatively greater benefits in low-income cities compared to high-income cities. Several robustness checks support these findings.

Avoid Peer Information: Evidence from a Field Experiment of Charity Crowdfunding

We study the behavior of an individual avoiding peer information on charity giving. Manipulating how the peer donation information was revealed to potential donors in a field experiment, we find 89% of individuals were “information avoiders.” We further use an instrumental variable estimation strategy to show that, given the option to avoid the information, these individuals were less likely to give and to help promote charity campaigns, which reduced the total distribution of campaigns on the platform by 8.5% and the total donation amount by 7.7%. Finally, we use a theoretical model to illustrate how the pressure from peer comparison may drive the findings.

The Effect of Home-Sharing on House Prices and Rents: Evidence from Airbnb

We assess the impact of Airbnb on residential house prices and rents: using a data set of Airbnb listings from the entire United States and an instrumental variables estimation strategy, we show that Airbnb has a positive impact on house prices and rents.

Price elasticities of residential electricity demand: Estimates from household panel data in Bangladesh

Abstract We collect a household level panel dataset to estimate the price elasticities of electricity demand for different types of urban households in Bangladesh. We use an instrumental variable estimation strategy which exploits exogenous variation in average electricity prices induced by a value-added-tax shock. The results indicate significant heterogeneity in price elasticities by electricity consumption levels. We conduct a number of simulations under alternative policy scenarios to illustrate how incorporating the heterogeneous nature of price elasticities into pricing policy can help decrease electricity demand-supply mismatch and inequality in electricity consumption. The results have important policy implications for developing countries aiming to address major energy issues by implementing tariff reforms.

When unintended effects are really unintended: depressive symptoms and other psychological effects of forgivable loan programs for college education

This article estimates the effects on depressive symptoms, family relationships, social support, and academic self-efficacy of participating in a forgivable loan program, using an instrumental variable (IV) estimation strategy. In particular, we estimate local average treatment effects (LATE) of program participation on these variables, using program eligibility as an instrument. In this case, estimation needs to account for endogeneity, given that not all eligible students decided to participate in the program and that variables affecting the decision to participate in the program might be related to the psychological variables being evaluated. We found negative effects on all the psychological variables. Additionally, we found that program participants were significantly more likely to move and attend elite, accredited, and more expensive universities, which explains the observed psychological symptoms. Results are interpreted in terms of the pressures that non-traditional students receiving financial aid face when adapting to college.

Returns to Grid Electricity: Mechanism of Causal Conservation and Household Technology

The unprecedented stock of greenhouse gases in the atmosphere is changing the traditional role of the forest to one of the carbon sinking and carbon sequestration. However, the dependence on firewood for household energy is ubiquitous in developing countries, thus undermining the ecosystem services that the forest provides. One of the options to address this problem is to provide access to alternatives, such as electricity. This study examines the effect of grid electricity on firewood consumption using an instrumental variable estimation strategy, and it examines the mechanisms of the causal effect. I use three waves of large sample household surveys from Bhutan and other administrative data to complement the main results. The results show that grid electricity reduces firewood consumption by approximately 1.51 cubic metres per month. The households respond to electricity provision by making adjustment in household technology, particularly in terms of shifting to newly available source of household fuels and adopting basic electrical appliances.

Does Intra-household Contagion Cause an Increase in Prescription Opioid Use?

Opioid use claims many thousands of lives each year. This article considers the diffusion of prescription opioid (PO) use within family households as one potential culprit of the proliferation of these medications. In an analysis of hundreds of millions of medical claims and almost 14 million opioid prescriptions in one state between 2010 and 2015, we show that the use of POs spreads within family households. We also show that the treatment effect of exposure to a family member’s PO use is driven by an increase in PO consumption for medical conditions that members of treated and untreated families experience at nearly identical rates. This pattern of results suggests household exposure causes an uptick in patient demand for prescription opioids. We use an instrumental variable estimation strategy to address the well-known challenges to estimating a causal effect of intra-household contagion, such as genotypic similarities among family members, assortative matching in partner selection, and clustering of health conditions within households. The results spotlight the salience of the most ubiquitous social structure, the family household, in accelerating opioid consumption to unprecedented levels. The findings also suggest that rather than direct social influence between physicians, the spread of prescription behavior in physician networks may be driven by shifts in patient demand that propagate through the patient sharing network.

All in the mind? Estimating the effect of mental health on health behaviours

BackgroundHealth behaviours and mental illness have been found to be strongly correlated, both across and within individuals. However, establishing the precise nature of this link, particularly in terms of causality and its direction, remains a challenge. Much of the relevant existing research follow an experimental design and focus on measuring how changes in health behaviours affect mental health. ObjectiveThe study examines changes in mental health and health behaviours within individuals across time and evaluates the evidence for a causal pathway from psychological distress to risky health behaviours. MethodUsing a population representative longitudinal survey providing data from Australian households, this study employs a fixed-effects panel model framework to account for unobserved time-invariant individual heterogeneity. An instrumental variable estimation strategy is employed to specifically evaluate the evidence of a causal pathway from psychological distress to risky health behaviours. ResultsThe results confirm strong within-individual associations between psychological distress and health behaviours. Further evidence supports a causal relationship from psychological distress to health behaviours, though only for men and lifestyle habits. The case for a direct causal pathway is less straightforward when considering dietary habits, and potentially also for women. This lack of clarity suggests at least some of the observed within-individual associations reflect causal effects of psychological distress on risky health behaviours. ConclusionsGiven the substantial burden of disease associated with unhealthy behaviours, further research examining potential causal pathways from mental health to health behaviours should be a priority, as there is the potential to reduce health burden through mental health improvements.

Working from Home

This paper investigates how working from home affects employees’ work effort. Employees who have the possibility to work from home have a high autonomy in scheduling and organizing their work and are therefore assumed to have a higher intrinsic motivation. Thus, we expect working from home to positively influence work effort of employees. We introduce a theoretical model that analyzes whether intrinsic motivation influences the impact of working from home on employees’ work effort. To account for the self-selection into working locations, we use an instrumental variable (IV) estimation strategy. Our empirical results indicate that working from home has a positive influence on employees’ work effort. In addition, we show that working from home indeed increases intrinsic motivation and thus employees’ work effort. Moreover, we find that the frequency of working from home also matters. The more frequently employees work from home, the higher the work effort they provide is.

DO CELLMATES MATTER? A CAUSAL TEST OF THE SCHOOLS OF CRIME HYPOTHESIS WITH IMPLICATIONS FOR DIFFERENTIAL ASSOCIATION AND DETERRENCE THEORIES

AbstractIn the schools of crime hypothesis, social interactions between inmates are assumed to produce criminogenic rather than deterrent prison peer effects, thus implicating them in the persistence of high recidivism rates and null or criminogenic prison effects. We assess the validity of the schools of crime hypothesis by estimating prison peer effects that result from differential cellmate associations in a male, first‐time release cohort from the Pennsylvania Department of Corrections. To isolate causal prison peer effects in the presence of essential heterogeneity, we use a semiparametric local instrumental variables estimation strategy. Our results do not support the school of crime hypothesis. In our sample, prison peer effects produced in interaction with more criminally experienced cellmates are always null or deterrent rather than criminogenic. Although we do not explicitly test for the operant conditioning mechanisms theorized to underlie social influence in the context of differential association, we argue that, under the assumption that the differential association context relates positively to the direction of peer influence, our universally noncriminogenic estimates exclude direct reinforcement, vicarious reinforcement, and direct punishment as potential drivers of prison peer effects produced in interaction with more criminally experienced cellmates. Our results support the assertion that operant conditioning mechanisms connect differential association and deterrence theories.

The Sharing Economy and Housing Affordability: Evidence from Airbnb

We assess the impact of home-sharing on residential house prices and rents. Using a dataset of Airbnb listings from the entire United States and an instrumental variables estimation strategy, we show that Airbnb has a positive impact on house prices and rents. This effect is stronger in zipcodes with a lower share of owner-occupiers, consistent with non-owner-occupiers being more likely to reallocate their homes from the long- to the short-term rental market. At the median owner-occupancy rate zipcode, we find that a 1% increase in Airbnb listings leads to a 0.018% increase in rents and a 0.026% increase in house prices. Considering the median annual Airbnb growth in each zipcode, these results translate to an annual increase of $9 in monthly rent and $1,800 in house prices for the median zipcode in our data, which accounts for about one fifth of actual rent growth and about one seventh of actual price growth. Finally, we formally test whether the Airbnb effect is due to the reallocation of the housing supply. Consistent with this hypothesis, we find that, while the total supply of housing is not affected by the entry of Airbnb, Airbnb listings increase the supply of short-term rental units and decrease the supply of long-term rental units.

What level of competition intensity maximises investment in the wireless industry?

This paper investigates the relationship between competition and investment in the wireless industry from a dynamic perspective. Using firm level data and instrumental variable estimation strategy, it finds that the relationship is inverted-U shaped. The investment maximising intensity of competition is reached when operators' gross profits represent 37 or 40 per cent of their revenues, depending on whether capital expenditures are normalised by the number of subscribers. This finding means that investment increases with competition as long as operators' profits are above the thresholds of 37 or 40 per cent of their revenues. Under these thresholds, there is a tradeoff between competition and investment. The paper also finds a significant long run effect of competition on investment which amplifies the short run effect by a factor of 3–4.

Social security income and the utilization of home care: Evidence from the social security notch

This paper exploits Social Security law changes to identify the effect of Social Security income on the use of formal and informal home care by the elderly. Results from an instrumental variables estimation strategy show that as retirement income increases, elderly individuals increase their use of formal home care and become less likely to rely on informal home care provided to them by their children. This negative effect on informal home care is most likely driven by male children withdrawing from their caregiving roles. The empirical results also suggest that higher Social Security benefits would encourage the use of formal home care by those who would not have otherwise used any type of home care and would also encourage the use of both types of home care services among elderly individuals.