Current Projects
This paper provides novel Bayesian econometric methods that allow the effect of early-life conditions and education on health to be unravelled in the absence of any prior information on the latent structure underlying the data and in the presence of data rich on measurements proxying these factors.
A burgeoning literature in Bayesian econometrics currently focuses on the estimation of factor models with an unknown number of latent factors. In this paper, we implement Bayesian methods that go beyond traditional approaches like preliminary exploratory factor analysis or scree plots. These new methods represent an important step forward in determining the latent structure of the model, with respect to the number of latent factors, but also to the shape of their distribution and to their correlation. In fact, the recent literature is rich on highly structured factor analysis, mostly due to increasing degree of complexity of data and/or applications in modern applied sciences.
These methods are applied to the 1970 British Cohort Study to analyze the effect of early-life cognition and personality on education and later-life health. These data are unusually rich in terms of both the quantity and the quality of measurements on early cognitive and personality traits. In this application, we focus on seven cognitive scales and five psychosocial scales administered to the cohort members when they were aged ten, to their mothers and to their teachers. The total number of items amounts to more than a hundred, and cover a wide range of cognitive abilities, personal attitudes, and behaviors. However, this richness has rarely been fully exploited, and the available measurements have been aggregated and used by different researchers in different ways. We provide methods for exploiting the available information in a systematic way which does not rely on arbitrary a priori decisions on model structure and sub-scale construction. Our methods have wide applicability to several other circumstances in which researchers face a data-rich environment but are agnostic as to the underlying latent structure.
Overall, our work highlights the crucial role played by the early years in promoting health and the importance of prevention in the reduction of health disparities, and refocuses the role of education policy as health policy.
Key Personnel: Professor James Heckman of the University of Chicago, Dr. Gabriella Conti of the University of Chicago, and Dr. Remi Piatek of the University of Chicago
The Chicago Longitudinal Study is a prospective cohort study that tracked the progress of 1,539 students who attended kindergarten at low-income schools in 1985 into the present. The majority of the students participated in Child Parent Center programs, which provided intensive preschool, kindergarten, and follow-on services to eligible students. The rest of the students attended typical Title I schools in similar neighborhoods. The research team intends to use the data to explore the role of parent and teacher inputs to the education production function.
Key Personnel: Professor James Heckman of the Univesity of Chicago, Jing Jing Hsee of the Univesity of Chicago, Miriam Gensowski of the Univesity of Chicago, Maryclare Griffin of the Univesity of Chicago, and Dr. Junjian Yi of the Univesity of Chicago
This project investigates the General Educational Development (GED) testing program. We study the attributes of GED recipients and the social and economic benefits of GED certification. We find that GED recipients tend to be as smart as other high school graduates who do not attend college but lack other, non-cognitive abilities. We use a variety of methods to estimate the effect of GED certification and high school graduation on annual earnings, employment, hourly wages, and hours worked. In general, after accounting for differences in adolescent traits, GED recipients perform similarly to other dropouts in the labor market and other aspects of life. These findings hold across several data sets.
This research demonstrates that passing the GED, a standardized test, does not create meaningful opportunity for the average dropout. Our other work on the GED testing program shows that many high school students choose to drop out due to a false belief that the obtaining a GED certificate is equivalent to graduating from high school. Society’s misconception that the GED certificate is equivalent to a high school diploma has distorted the national perspective on true high school graduation rates and the value of education in America.
Key Personnel: Professor James Heckman of the University of Chicago, Dr. Nicholas Mader of the University of Chicago, Jacob Bergmann Larsen of the University of Chicago, Roger Fan of the University of Chicago, Jin Soo Han of the University of Chicago, and Timothy Kautz of the University of Chicago.
The Nurse-Family Partnership (NFP) is an evidence-based home visitation intervention for first time, low-income mothers from pregnancy through infancy (2 years old). During these home visitations, nurses would provide pregnancy support and guidance to foster the mothers' parenting skills and economic self-sufficiency. The NFP program had initial trials in Elmira, NY (1979), Memphis, TN (1990), and in Denver, CO (1994) where follow-up studies and analysis continue to be conducted to this day. Our team is currently conducting research using the Memphis, TN sample on three unique projects. The first project reanalyzes the treatment effects evidence using an inference strategy that accounts for departures from the initial randomization protocol and then examines the potential mediation of treatment effects on later childhood outcomes via maternal investments and early improvements in the child's skill formation (Cognitive and Noncognitive skills). The second project analyzes the differential response to treatment on birth outcomes that differ by the gender of the child. The third project will delve into how the quantity and quality of the home visits affect the treatment that the mother and child receives and subsequent later outcomes.
Key Personnel: Professor James Heckman of the University of Chicago, Dr. Gabriella Conti of the University of Chicago, Terrance Oey of the University of Chicago, Rodrigo Pinto of the University of Chicago, Maria Fernanda Rosales Rueda of the University of Chicago, and Willem Van Vliet of the University of Chicago
We formulate a dynamic structural model of educational choices among discrete states with a factor structure, recurrent states, and option values arising from learning and nonlinearity of reward functions at di_erent stages of the life cycle. We clearly de_ne the option value of education, investigate the role of psychic cost in determining educational choices, and determine the correct concept of the rate of return to education in an environment with uncertainty and nonlinearity. We formally establish the semiparametric identi_ability of our model and generalize our proof to a class of structural dynamic discrete choice models for stopping times and associated outcomes in which agents sequentially update the information on which they act.
Key Personnel: Professor James Heckman of the University of Chicago, Philipp Eisenhauer of the University of Mannheim, Timothy Kautz of the University of Chicago, Dr. Nicholas Mader of the University of Chicago, and Stefano Mosso of the University of Chicago.
Preparing for Life (PFL) is a preventative programme which aims to improve the life outcomes of children and families living in North Dublin, Ireland, by intervening during pregnancy and working with families until the children start school. The PFL Programme is being evaluated using a mixed methods approach, incorporating a longitudinal randomised control trial design and an implementation analysis. The experimental component involves the random allocation of participants from the PFL communities to either a high support treatment group or a low support treatment group. Both groups receive developmental toys, facilitated access to preschool, public health workshops, and have access to a support worker. Participants in the high treatment group also receive weekly home visits from a trained mentor and group parent training using the
Triple P Positive Parenting Programme. The PFL treatment groups are also being compared to a ‘services as usual’ comparison group (LFP), who do not receive the PFL Programme.
In total, 233 pregnant women were recruited into the PFL Programme between January 2008 and August 2010. Randomisation resulted in 115 participants assigned to the high treatment group and 118 participants assigned to the low treatment group. In addition, 99 pregnant women were recruited into the comparison group. The population based recruitment rate was 52%. Baseline data, collected before the programme began, was available for 104 and 101 high and low PFL treatment group participants respectively, and 99 comparison group participants. Tests of baseline differences between the high and low PFL treatment groups found that the two groups did not statistically differ on 97% of the measures analysed, indicating that the randomization process was successful. The aggregate PFL group and the LFP comparison group did not statistically differ on 75% of the measures; however, the comparison group was of a relatively higher socioeconomic status.
Evaluation of this programme is being conducted by a team led by Prof. James J. Heckman at University of Chicago, Dr. Orla Doyle at University College Dublin, and Seong Hyeok Moon at University of Chicago.
