Recent PSC Publication Abstracts
Below are the 10 most recent additions to the PSC publication collection.
Kowalski, Amanda. 2018. "Biology Meets Behavior in a Clinical Trial: Two Relationships between Mortality and Mammogram Receipt." PSC Research Report No. 18-892. 9 2018. Abstract. PDF.
I unite the medical and economics literatures by examining relationships between biology and behavior in a clinical trial. Specifically, I identify relationships between mortality and mammogram receipt using data from the Canadian National Breast Screening Study, an influential clinical trial on mammograms. I find two important relationships. First, I find heterogeneous selection into mammogram receipt: women more likely to receive mammograms are healthier. This relationship follows from a marginal treatment effect (MTE) model that assumes no more than the local average treatment effect (LATE) assumptions. Second, I find treatment effect heterogeneity along the mammogram receipt margin: women more likely to receive mammograms are more likely to be harmed by them. This relationship follows from an ancillary assumption that builds on the first relationship. My findings contribute to the literature concerned about harms from mammography by demonstrating variation across the mammogram receipt margin. This variation poses a challenge for current mammography guidelines for women in their 40s, which unintentionally encourage more
mammograms for healthier women who are more likely to be harmed by them.
Kowalski, Amanda. 2018. "How to Examine External Validity within an Experiment." PSC Research Report No. 18-891. 8 2018. Abstract. PDF.
A fundamental concern for researchers who analyze and design experiments is that the experimental result might not be externally valid for all policies. Researchers often attempt to assess external validity by comparing data from an experiment to external data. In this essay, I discuss approaches from the treatment effects literature that researchers can use to begin the examination of external validity internally, within the data from a single experiment. I focus on presenting the approaches simply using figures.
Fisher, Jonathan, David S. Johnson, Timothy S. Smeeding, and Jeffrey Thompson. 2018. "The Demography of Inequality: Income, Wealth and Consumption, 1989-2016." PSC Research Report No. 18-890. 7 2018. Abstract. PDF.
Inequality differentially affects demographic groups, and the socioeconomic measure we use matters quite a lot when understanding how inequality differentially affects demographic groups. We examine the demography of inequality using age, race, education, and family type for children, and we show how the demography of inequality depends on the resource measure used: income, consumption, or wealth. Children and the elderly are worse off than non-elderly adults in income terms, but only children and their parents are increasingly and disproportionately found in the lower reaches of the wealth and consumption distributions. For some groups, all lenses show the same picture, as children in single parent households, blacks, and those with less than a high school education are worse off in terms of all resource measures - income, wealth or consumption.
Johnson, David S., Robert F. Schoeni, Laura Tiehen, and Jennifer Cornman. 2018. "Assessing the Effectiveness of SNAP by Examining Extramarginal Participants." PSC Research Report No. 18-889. 4 2018. Abstract. PDF.
A primary objective of in-kind transfer programs is to promote the consumption of specific goods. Standard economic theory implies that the program's ability to achieve this objective depends critically on the proportion of recipients whose spending on the good is limited to the amount of the in-kind transfer, i.e., they are extramarginal. For these families, an increase in benefits will translate into an equal sized increase in consumption of the good. We find that roughly 30% of participants in SNAP are extramarginal, which is larger than previous estimates and implies in-kind benefits provided through SNAP promote food consumption. Furthermore, very low income SNAP families are much more likely to be extramarginal, and extramarginal families have extremely low income and are nearly five times more likely to be food insecure than families not on SNAP, implying that families are extramarginal not because their food needs are fully met by SNAP, but because their income is so low.
Mehta, Neil, and Hui Zheng. 2018. "Do the effects of major risk factors for mortality rise or fall with age?" PSC Research Report No. 18-888. 2 2018. Abstract. PDF.
Researchers are often interested in how a risk factor's effect on mortality changes with age because the pattern has direct relevancies to life-course theories, public health practice, and demographic modeling. Here we highlight the importance of mathematical scale to interpreting risk factor by age interactions, describing how the choice of scale has critical implications for theory development and arguing that many life-course studies have not recognized the importance of scale to conclusions drawn from their findings. We also provide an empirical analysis of risk factor by age interactions drawing from a set of major risk factors for mortality often studied in demography and epidemiology. We show that these risk factors conform to a general pattern-the strength of their association with mortality tends to increase with age. This prevailing pattern of increasing risks by age across multiple major risk factors for mortality has not been identified previously. We go on to argue that the pattern has critical underpinnings for life-course theory, public health allocation, and clinical practice.
Axinn, William G., James Wagner, Mick P. Couper, and Scott Crawford. 2018. "Campus Climate Surveys of Sexual Misconduct: Limiting the Risk of Nonresponse Bias." PSC Research Report No. 18-887. 2 2018. Abstract. PDF.
High attention to campus surveys of sexual misconduct has raised concerns about the potential of nonresponse bias in data from these surveys. Best practices in survey methodology offer many options to limit nonresponse. Here we examine two of the most potent options: individual incentives for participation and two-phase survey designs that alter the method of contact. Analyzing data from the University of Michigan's 2015 campus climate survey we demonstrate that a two-phase design introducing telephone and face-to-face reminders to complete the survey can produce stronger change in response rates, characteristics of those who respond, and statistical estimates than higher incentive levels. Cost comparison also reveals use of trained interviewers to contact students can be more efficient than higher incentive levels.
Zhou, Xiang, and Yu Xie. 2018. "Heterogeneous Treatment Effects in the Presence of Self-Selection: A Propensity Score Perspective." PSC Research Report No. 18-886. 1 2018. Abstract. PDF.
An essential feature common to all empirical social research is variability across units of analysis. Individuals differ not only in background characteristics, but also in how they respond to a particular treatment, intervention, or stimulation. Moreover, individuals may self-select into treatment on the basis of their anticipated treatment effects. To study heterogeneous treatment effects in the presence of self-selection, Heckman and Vytlacil (1999, 2001a, 2005, 2007b) have developed a structural approach that builds on the marginal treatment effect (MTE). In this paper, we extend the MTE-based approach through a redefinition of MTE. Specifically, we redefine MTE as the expected treatment effect conditional on the propensity score (instead of all observed covariates) as well as a latent variable representing unobserved resistance to treatment. The redefined MTE improves upon the original MTE in a number of aspects. First, while it is conditional on a unidimensional summary of covariates, it is sufficient to capture all of the treatment effect heterogeneity that is consequential for selection bias. Second, the new MTE is a bivariate function, and thus is easier to visualize than the original MTE. Third, as with the original MTE, the new MTE can also be used as a building block for evaluating standard causal estimands such as ATE and TT. However, the weights associated with the new MTE are simpler, more intuitive, and easier to compute. Finally, the redefined MTE immediately reveals treatment effect heterogeneity among individuals who are at the margin of treatment. As a result, it can be used to evaluate a wide range of policy changes with little analytical twist, and to design policy interventions that optimize the marginal benefits of treatment.
Teerawichitchainan, Bussarawan, and John E. Knodel. 2017. "Impacts of Migration on Households in the Dry Zone, Myanmar." PSC Research Report No. 17-882. 10 2017. Abstract. PDF.
In 2014 an estimated 12% of all Myanmar households had internal migrants and 8% had international migrants - proportions projected to grow significantly within the next decade. This study analyzes data from Myanmar's 2017 Dry Zone Migration Impact Survey to assess the impacts of migration on households in migration-source areas. It examines characteristics and patterns of migration in the Dry Zone, distinguishing between economic and non-economic migration, and the extent to which migration affects material wellbeing and livelihoods experienced by migrant-sending versus non-migrant households. It also examines the economic and social implications of migration for household members remaining in the Dry Zone. Specifically, it evaluates the wellbeing and unmet needs of potentially vulnerable segments of the population left behind in migrant-sending households, including dependent children and other family members in need of personal care (e.g., the elderly and disabled). Based on the empirical findings, the authors discuss how policy and support can be enhanced to increase the positive impacts of migration on migrant-sending households and to address its negative consequences.
Nhlapo, Mosidi, Barbara A. Anderson, and Marie Wentzel. 2017. "Trends in Voting in South Africa 2003-2014." PSC Research Report No. 17-881. 4 2017. Abstract. PDF.
This paper analyzes voting preferences of South Africans based on data from the South African Social Attitudes Surveys (SASAS) 2003-2014. The focus is on differences by race and age. In national election years, respondents were asked whether they voted and what party they voted for. In every year respondents were asked whether they would vote and what party they would vote for if the election were held tomorrow. This paper is based on vote intentions.
Since the end of apartheid in 1994, the African National Congress (ANC) has dominated elections, attracting the support of almost all Africans, while non-Africans have increasingly supported the main opposition party, the Democratic Alliance (DA). There has been much speculation about when African allegiance to the ANC might weaken. There also has been speculation that the allegiance of better educated Africans to the ANC would weaken before that of Africans with lower educational attainment. Another aspect of possible change in voting preference and behavior relates to age. As more people who spent little of their lives under apartheid reached voting age, it was thought that the allegiance of young Africans to the ANC might be weaker than of older Africans. Also, sometimes young people view issues differently than older people. Africans were more likely to intend to vote than non-Africans, but over time race mattered less in whether a person intended to vote.
It seems that over time non-Africans felt they had more of a stake in the system and thought that voting was worthwhile. Young non-Africans are significantly more likely to support the ANC than older non-Africans, and young Africans are significantly more likely to support the DA than older Africans. Thus young voters are less tied than older voters to the party favored by most members of their racial group. Over the 2003-2014 period young and older Africans and non-Africans increased their support of the DA, and education was positively related to DA support for every group. In 2013, the Economic Freedom Fighters (EFF), a revolutionary socialist party, broke off from the ANC. In the 2014 national election, the EFF won 6% of the vote. In the 2013 SASAS, 9% of young voting-age Africans and 6% of older Africans supported the EFF. Among both young and older Africans, education was positively related to supporting the EFF. However, African support for the ANC remained very high.
The lessening of the importance of race for intention to vote, as is some convergence in voting preferences of young voters, are positive developments. However, this convergence in party choice by race is limited. In 2014, 86% of older Africans and 83% of young Africans who intended to vote supported the ANC, while 81% of both young and older non-Africans who intended to vote supported the DA.
Lesthaeghe, Ron J., and Lisa Neidert. 2017. "Spatial Aspects of the American "Culture War": The Two Dimensions of US Family Demography and the Presidential Elections, 1968-2016." PSC Research Report No. 17-880. 4 2017. Abstract. PDF.
This paper explores the link between two basic dimensions of family demography and the outcome of presidential elections for states and continental counties in the United States. It shows that the spatial patterns of respectively the "Second demographic transition" (SDT) and voting start converging in the 1990s. The correlations remain very high and stable thereafter. This does not hold for the correlation between the other dimension of family demography, i.e. the pattern of disadvantage (POD), and voting. The spatial SDT-voting correlation does not depend on the issues being debated during the successive elections, and it reaches a maximum in the latest election round (2016) at the level of both states and counties. Furthermore, the zero order correlation remains intact after controls for household income, education, urbanity, religion and ethnicity at the state level, but is reduced at the county level. The latter result is produced by the high concentration of Democratic votes and SDT household structures in the metropolitan counties. On the whole, the SDT dimension is one of the strongest predictors of spatial voting patterns in the US since the turn of the century.