297 research outputs found
Maximum Likelihood Estimation of a Binary Choice Model with Random Coefficients of Unknown Distribution
No full textIchimura, Hidehiko; Thompson, T. Scott. (1993). Maximum Likelihood Estimation of a Binary Choice Model with Random Coefficients of Unknown Distribution. Retrieved from the University Digital Conservancy, https://hdl.handle.net/11299/55580
Estimation of single index models
No full textThesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Economics, 1988.by Hidehiko Ichimura.Ph.D
Semiparametric Least Squares (SLS) and Weighted SLS Estimation of Single-Index Models
No full textFor the class of single-index models, I construct a semiparametric estimator of coefficients
up to a multiplicative constant that exhibits 1/ Vn-consistency and asymptotic normality. This
class of models includes censored and truncated Tobit models, binary choice models, and duration
models with unobserved individual heterogeneity and random censoring. I also investigate
a weighting scheme that achieves the semi parametric efficiency bound.Ichimura, Hidehiko. (1991). Semiparametric Least Squares (SLS) and Weighted SLS Estimation of Single-Index Models. Retrieved from the University Digital Conservancy, https://hdl.handle.net/11299/55563
The impact of student loans on educational attainment: the case of a program at the pontifical catholic university of Peru
No full textDuring the past decades, the Pontifical Catholic University of Peru (known as PUCP) has been giving student loans to some of its students with satisfactory academic performance but who face certain economic problems which might interrupt their studies. Although this program was created more than forty years ago, its results have not been rigorously evaluated. This document attempts to assess to what extent the program has benefited students. Because the collected data come from academic and social records, the completion of this task requires using modern techniques specifically designed to work with non experimental data. After estimating by propensity score matching with multiple treatments, I find a statistically significant impact of this program on the time a student employs to complete the course of study at PUCP (measured in semesters) only when a student was awarded with a loan for 6 semesters or more. That effect is not significantly different from zero when the loan lasts less than 6 semesters. Similar results were found when I analyzed the impact on the probability of degree completion of student loans, where students with loan were more likely to meet all graduation requirements by 6 years and a half after they start studying at PUCP. Again this effect was significant only when the student participates in the program for six semesters or more. However, the impact on that probability was small.Student Loans, Matching, Treatment Effect
Retirement Process in Japan: New evidence from Japanese Study on Aging and Retirement (JSTAR)
No full textWhile the average retirement age is higher in Japan, the retirement process has not been in-depth explored from multiple factors including economic, health and family statuses. We examine the transition of work status and working hours for Japanese males and females using JSTAR (Japanese Study on Aging and Retirement) in 2007 and 2009. We provide some empirical patterns of retirement. First, those who are aged 60 or over and retired stay retired two years later, either male or female, while some portion of those who are aged in 50s come back to work. Second, the probability to retire in 2009 for those who were not retired in 2007 ranges 20-30%. Higher index workers in their 60s are less likely to retire but quickly retire if working hours are reduced. Third, higher index workers seem to keep working at the current working hours than lower index counterparts.
Semiparametric reduced form estimation of tuition subsidies
No full textThe goal of this paper is to use a semiparametric reduced form model to estimate the effects of various tuition subsidies. This approach expands on the tuition subsidy example in Ichimura and Taber (2000) in a number of dimensions. It has become common practice in the empirical literature to refer to any nonstructural empirical analysis as "reduced form." This is not the traditional sense of the phrase. A classic reduced form analysis (see e.g. Marschak, 1953) first specifies a structural model and then derives the reduced form parameters in terms of the structural parameters. While many recent studies have asserted to taking a reduced form approach, the structural parameters. While many recent studies have asserted to taking a reduced form approach, the structural model which the reduced form model should correspond is rarely specified. We explicitly specify a structural model and use the implied reduced form structure to estimate the effect of tuition subsidy policies. Specifying the underlying model has the advantage of being explicit about the assumptions that justify the analysis. This avoids Rosenzweig and Wolpin's (2000) criticism of work on natural 'natural experiments' that often leaves these conditions implicit. Our structural model is based on the model studied by Keane and Wolpin (1999). It is highly nonlinear and allows for more unobserved heterogeneity than the typical simultaneous equations framework that most previous work has used in reduced form estimation. Using hte specified structural model, we examine the assumptions discussed in Ichimura and Taber (2000) to justify reduced form estimation of the policy effects
Active labor market policy effects in a dynamic setting
No full textThis paper implements a method to identify and estimate treatment effects in a dynamic setting where treatments may occur at any point in time. By relating the standard matching approach to the timing-of-events approach, it demonstrates that effects of the treatment on the treated at a given date can be identified even though non-treated may be treated later in time. The approach builds on a "no anticipation" assumption and the assumption of conditional independence between the duration until treatment and the counterfactual durations until exit. To illustrate the approach, the paper studies the effect of training for unemployed workers in France, using a rich register data set. Training has little impact on unemployment duration. The contamination of the standard matching estimator due to later entries into treatment is large if the treatment probability is high.Treatment; program participation; unemployment duration; training; propensity score; matching; contamination bias
Semiparametric reduced-form estimation of tuition subsidies
No full textThe goal of this paper is to use a semiparametric reduced form model to estimate the effects of various tuition subsidies. This approach expands on the tuition subsidy example in Ichimura and Taber (2000) in a number of dimensions. It has become common practice in the empirical literature to refer to any nonstructural empirical analysis as reduced form. This is not the traditional sense of the phrase. A classic reduced form analysis (see e.g. Marschak, 1953) first specifies a structural model and then derives the reduced form parameters in terms of the structural parameters. While many recent studies have asserted to taking a reduced form approach, the structural parameters. While many recent studies have asserted to taking a reduced form approach, the structural model which the reduced form model should correspond is rarely specified. We explicitly specify a structural model and use the implied reduced form structure to estimate the effect of tuition subsidy policies. Specifying the underlying model has the advantage of being explicit about the assumptions that justify the analysis. This avoids Rosenzweig and Wolpin's (2000) criticism of work on natural 'natural experiments' that often leaves these conditions implicit. Our structural model is based on the model studied by Keane and Wolpin (1999). It is highly nonlinear and allows for more unobserved heterogeneity than the typical simultaneous equations framework that most previous work has used in reduced form estimation. Using hte specified structural model, we examine the assumptions discussed in Ichimura and Taber (2000) to justify reduced form estimation of the policy effect
Active Labor Market Policy Effects in a Dynamic Setting
No full textThis paper implements a method to identify and estimate treatment effects in a dynamic setting where treatments may occur at any point in time. By relating the standard matching approach to the timing-of-events approach, it demonstrates that effects of the treatment on the treated at a given date can be identified even though non-treated may be treated later in time. The approach builds on a "no anticipation" assumption and the assumption of conditional independence between the duration until treatment and the counterfactual durations until exit. To illustrate the approach, the paper studies the effect of training for unemployed workers in France, using a rich register data set. Training has little impact on unemployment duration. The contamination of the standard matching estimator due to later entries into treatment is large if the treatment probability is high.treatment, program participation, unemployment duration, matching, training, propensity score, contamination bias
Using a Social Experiment to Validate a Dynamic Behavioral Model of Child Schooling and Fertility: Assessing the Impact of a School Subsidy Program in Mexico
No full textThis paper studies the performance of a methodology that can be used to evaluate the impact of new policies that radically depart from existing ones. It uses data gathered from a randomized schooling subsidy experiment in Mexico (i) to estimate and validate a dynamic behavioral model of parental decisions about fertility and child schooling, (ii) to forecast long-term program impacts that extend beyond the life of the experiment, and (iii) to assess the impact of a variety of counterfactual policies. The behavioral model is estimated using data on families in the randomized-out control group and in the treatment group prior to the experiment, both of which did not receive any subsidy. Child wages provide a valuable source of variation in the data for identifying subsidy effects. Using the estimated model, we predict the effects of school subsidies according to the schedule that was implemented under the Mexican PROGRESA program.schooling, child labor, fertility, structural estimation, social experiments
- …
