The Experts below are selected from a list of 261897 Experts worldwide ranked by ideXlab platform
Ronald L Oaxaca - One of the best experts on this subject based on the ideXlab platform.
-
inter industry wage differentials and the gender wage gap an Identification Problem
Industrial and Labor Relations Review, 2001Co-Authors: William C Horrace, Ronald L OaxacaAbstract:An intuitively appealing method for estimating gender wage gaps by industry is shown to yield estimates that vary according to the arbitrary choice of left-out reference groups for non-industry categorical variables, such as race and marital status. This study uses data from the Current Population Surveys to explore alternative methods for estimating gender wage gaps by industry that are not susceptible to the Identification Problem. Statistical significance measures reveal when relative industry wage gap rankings are not statistically meaningful. The methodology readily extends to other contexts such as racial, union-non-union, or immigrant-native wage gaps by industry, occupational, or regional groupings.
-
inter industry wage differentials and the gender wage gap an Identification Problem
Industrial and Labor Relations Review, 2001Co-Authors: William C Horrace, Ronald L OaxacaAbstract:An intuitively appealing method for estimating gender wage gaps by industry is shown to yield estimates that vary according to the arbitrary choice of left-out reference groups for non-industry cat...
Myeongsu Yun - One of the best experts on this subject based on the ideXlab platform.
-
Identification Problem and detailed oaxaca decomposition a general solution and inference
Journal of economic and social measurement, 2008Co-Authors: Myeongsu YunAbstract:It is well-known that the standard Oaxaca decomposition method on wage differentials produces arbitrary results when calculating the coefficients effect of sets of dummy variables: the estimated sum of coefficients effects of sets of dummy variables is not invariant to the choice of reference groups. We generalize this Identification Problem in the detailed Oaxaca decomposition and its solution based on a normalized equation to a decomposition analysis for differences in the first moment where linear or non-linear (e.g., probit or logit) models can be used for estimation. We provide a practical and simple algorithm to derive the normalized equation, and show that using normalized equation does not change the size and inference of the overall characteristics and coefficients effects. JEL classification: C20, J70
-
a simple solution to the Identification Problem in detailed wage decompositions
Economic Inquiry, 2005Co-Authors: Myeongsu YunAbstract:I. INTRODUCTION Oaxaca and Ransom (1999) show that the Oaxaca decomposition suffers from one nagging conceptual Problem: The detailed Oaxaca decomposition of wage differentials is not invariant to the choice of reference group when dummy variables are used. (1) That is, if one uses dummy variable(s), then the detailed coefficients effect attributed to dummy variables is not invariant to the choice of the omitted group(s). (2) This invariance or Identification Problem is well-known to labor economists and has plagued decomposition and discrimination analysis for a long time. (3) This article proposes a simple and practical solution to this Identification/invariance Problem. The solution is based on the intuitive idea that if alternative reference groups yield different estimates of the characteristics and coefficients effects for each individual variable, then it is natural to obtain estimates of the two effects for every possible specification of the reference groups and take the average of the estimates of the two effects with various reference groups as the "true" contributions of individual variables to wage differentials. A close inspection shows that averaging the two effects in the decomposition equation with varying reference groups (the "averaging approach") is equivalent to finding average estimates of constant and dummy variables in wage equations with varying reference groups and then using the average estimates to calculate the Oaxaca decomposition equation. Researchers may react a bit negatively to this suggestion because it could be quite cumbersome and tedious to estimate wage equations permuting the choice of reference groups. This article shows that there is no need to estimate multiple wage equations. One set of regression estimates is sufficient to resolve the Identification Problem in the detailed decompositions. That is, the average of the estimates with varying reference groups can be easily calculated by using only "one" set of regression estimates with any specific reference group(s). The Identification Problem for the detailed decomposition disappears once the contribution of the dummy variables and the constant in the regression equations are identified. (4) II. Identification Problem AND INVARIANT DECOMPOSITION: AN ILLUSTRATION To understand what the Identification Problem in the detailed wage decomposition is, I will first illustrate the Problem with a simple example. Suppose that there are three categories, and the regression equation has only a constant and two dummy variables on the right-hand side where the reference group is the first category. (5) That is, (1) [y.sub.i] = [[alpha].sub.i] + [3.summation over (k=2)] [D.sub.ki] [[beta].sub.ki] + [e.sub.i], where y is log-wages and i = A or B for two comparison groups. Coefficients for two dummy variables taking category one as the reference group are estimated using ordinary least squares (OLS) regression and are reported in the second column of Table 1 for sample A and for sample B. Note that the coefficient of the reference group (category 1) is restricted to zero. Similarly, I may change my reference group specification and estimate the wage equation two more times. The estimates taking category 2 or 3 as the reference group are reported on the next two columns. Because I have three sets of estimates with varying reference groups, I may decompose the wage differentials (0.15 = 0.76 - 0.61) into characteristics and coefficients effects three times. The characteristics effect ([[DELTA].sub.X(1)]) and coefficients effects ([[DELTA].sub.[beta](1)] are specified as follows when category 1 is the reference group: [[DELTA].sub.X(1)] = [[summation].sup.3.sub.k=2] ([[bar.D].sub.kA] - [[bar.D].sub.kB]) [[beta].sub.kB], and [[DELTA].sub.[beta](1)] = [[alpha].sub.A] - [[alpha].sub.B] + [[summation].sup.3.sub.k=2] [[bar.D].sub.kA] ([[beta].sub.kA] - [[beta].sub.kB]). …
-
a simple solution to the Identification Problem in detailed wage decompositions
Social Science Research Network, 2005Co-Authors: Myeongsu YunAbstract:Oaxaca and Ransom (1999) show that a detailed decomposition of the coefficients effect is destined to suffer from an Identification Problem since the detailed coefficients effect attributed to dummy variables is not invariant to the choice of reference groups. It turns out that the Identification Problem in the decomposition equation is a disguised Identification Problem of constant and dummy variables in a regression equation. This article proposes a simple and natural remedy for this Problem by using "normalized" regressions, which enable me to identify the constant and estimates of each dummy variable.
-
a simple solution to the Identification Problem in detailed wage decompositions
Research Papers in Economics, 2003Co-Authors: Myeongsu YunAbstract:Oaxaca and Ransom (1999) show that a detailed decomposition of the coefficients effect is destined to suffer from an Identification Problem since the detailed coefficients effect attributed to a dummy variable is not invariant to the choice of reference groups. It turns out that the Identification Problem in the decomposition equation is a disguised Identification Problem of constant and dummy variables in a regression equation. This paper proposes a simple and natural remedy for this Problem by utilizing “normalized” regressions which enable us to identify the constant and estimates of each dummy variable. The Identification Problem is automatically resolved once we obtain “normalized” regression equations for two comparison groups.
William C Horrace - One of the best experts on this subject based on the ideXlab platform.
-
inter industry wage differentials and the gender wage gap an Identification Problem
Industrial and Labor Relations Review, 2001Co-Authors: William C Horrace, Ronald L OaxacaAbstract:An intuitively appealing method for estimating gender wage gaps by industry is shown to yield estimates that vary according to the arbitrary choice of left-out reference groups for non-industry categorical variables, such as race and marital status. This study uses data from the Current Population Surveys to explore alternative methods for estimating gender wage gaps by industry that are not susceptible to the Identification Problem. Statistical significance measures reveal when relative industry wage gap rankings are not statistically meaningful. The methodology readily extends to other contexts such as racial, union-non-union, or immigrant-native wage gaps by industry, occupational, or regional groupings.
-
inter industry wage differentials and the gender wage gap an Identification Problem
Industrial and Labor Relations Review, 2001Co-Authors: William C Horrace, Ronald L OaxacaAbstract:An intuitively appealing method for estimating gender wage gaps by industry is shown to yield estimates that vary according to the arbitrary choice of left-out reference groups for non-industry cat...
Aislinn J Bohren - One of the best experts on this subject based on the ideXlab platform.
-
inaccurate statistical discrimination an Identification Problem
Research Papers in Economics, 2019Co-Authors: Aislinn J Bohren, Kareem Haggag, Alex Imas, Devin G PopeAbstract:Discrimination---differential treatment by group identity---is widely studied in economics.Its source is often categorized as taste-based or statistical (belief-based)---a valuable distinction for policy design and welfare analysis. We argue that in many situations, individuals may have inaccurate beliefs about the relevant characteristics of different groups. This possibility creates an Identification Problem when isolating the source of discrimination. When not accounted for, we show both theoretically and experimentally that such inaccurate statistical discrimination will be misclassified as taste-based. A review of the empirical discrimination literature in economics reveals the scope of this issue: a small minority of papers---fewer than 7%---consider inaccurate beliefs. We then examine two alternative methodologies for differentiating between these three sources of discrimination---varying the amount of information presented to evaluators and eliciting evaluators' beliefs. We propose a possible intervention: when presented with accurate information, we show that inaccurate statistical discrimination decreases.
-
inaccurate statistical discrimination an Identification Problem
Social Science Research Network, 2019Co-Authors: Aislinn J Bohren, Kareem Haggag, Alex Imas, Devin G PopeAbstract:Discrimination has been widely studied in the social sciences. Economists often categorize the source of discrimination as either taste-based or statistical—a valuable distinction for policy design and welfare analysis. In this paper, we highlight that in many situations economic agents may have inaccurate beliefs, and demonstrate that the possibility of inaccurate statistical discrimination generates an Identification Problem for attempts to isolate the source of differential treatment. We introduce isodiscrimination curves—which represent the set of preferences and beliefs that generate the same level of discrimination—to formally outline the Identification Problem: when not accounted for, inaccurate statistical discrimination can be mistaken for taste-based discrimination, accurate statistical discrimination, or their combination. A review of the empirical discrimination literature in economics, spanning 1990-2018, reveals the scope of this issue. While most papers discuss and attempt to distinguish between taste and statistical discrimination, a small minority—fewer than 7%—consider inaccurate beliefs in the analysis. An experiment illustrates a methodology for differentiating between the three sources of discrimination, demonstrating the pitfalls of the Identification Problem while presenting a portable solution.
Andrea Milani - One of the best experts on this subject based on the ideXlab platform.
-
the asteroid Identification Problem iv attributions
Icarus, 2001Co-Authors: Andrea Milani, M E Sansaturio, Steven R ChesleyAbstract:Abstract Existing archives of asteroid observations contain many objects with very short observed arcs. In this paper we present a method that we have used with considerable success to attribute these short arc “discoveries” to other objects with better defined orbits. The method consists of a three-stage filtering process whereby several billion possible attribution/orbit pairs are systematically analyzed with more and more exact algorithms, at each stage rejecting improbable cases. The first stage compares an attributable, by definition a synthetic observation representative of all the observations over a short arc, with the predicted observation for each available orbit. The second stage compares the proposed attributable observations with predicted positions from the known orbit using conventional linear covariance techniques, considering both the position and motion on the celestial sphere. In the final filter we attempt to compute a best-fitting orbit by differential corrections using the combined dataset. With this algorithm we have found 1675 attributions in approximately one year of operations, in addition to 902 Identifications found with another algorithm. We discuss the lessons learned from this one-year experiment and the possibilities of further improvement and automation of the procedure.
-
the asteroid Identification Problem iii proposing Identifications
Icarus, 2000Co-Authors: Andrea Milani, Alessandra La Spina, M E Sansaturio, Steven R ChesleyAbstract:Abstract A large fraction of asteroids have been lost shortly after discovery, thus the asteroid catalogs contain a large number of low accuracy orbits. Two of these inaccurate orbits can belong to the same physical object; the challenge is to find effective algorithms for Identification. We give a new method to propose Identifications of orbits, applicable in the case where each of the two observed arcs provides enough information to solve for all the orbital elements by a least-squares fit to the observations. Even if the optimum fit solution is unique, there is a confidence region in the space of orbital elements containing orbital solutions compatible with the observations: the Identification of orbits is the search for an orbital solution in the intersection of the two confidence regions. In the linear approximation there is a rigorous and simple algorithm to find the optimum joint solution and the increase in the RMS of the residuals relative to the two separate solutions. The linear approximation may fail if two poorly determined orbits are too far apart in the orbital elements' space. In this case, the linear algorithm becomes more stable when restricted to only some of the orbital elements. Our procedure proposes orbit Identification using a cascade of tests, all based upon Identification metrics taking into account the difference in the orbits weighted with the uncertainty. The first test is based only upon the orbital plane; the couples of orbits compatible according to the first test are submitted to further tests using Identification metrics based upon 5 and 6 orbital elements. Finally, the couples passing all tests are submitted to an accurate computation, by differential correction, of the orbit fitting both sets of observations. This procedure has been tested on a set of 100 already known Identifications and was found to be effective in 99% of the cases. Finally we show that these methods have been used to obtain 152 previously unknown orbit Identifications.
-
the asteroid Identification Problem i recovery of lost asteroids
Icarus, 1999Co-Authors: Andrea MilaniAbstract:Abstract When an asteroid is lost, the observers need to know the portion of the celestial sphere where it could be recovered at a given time. This region is an image of the region, in the space of orbital elements, where the orbit is compatible with the previous observations. The map between these two regions is nonlinear; therefore the classical linear approximation can fail. Indeed it fails by a large amount when both these regions are large, which is precisely when an asteroid has been observed only over a short arc and/or it has been lost for a long time. The recovery, and Identification, of asteroids long lost is very difficult if the only available prediction is a single point corresponding to the least squares solution, which could be very far from the real state; thus the availability of an efficient algorithm to bound the recovery region is essential, also to decide if the recovery is worth the effort. This paper proposes three new algorithms to better approximate the recovery region based upon approximations going beyond linearization. It gives the results of tests based upon asteroids which have been recovered by chance and could have been found in the recovery region computed by the new algorithms. Free software is available now, by means of which the new algorithms can be tested, and eventually adopted, by the observers and by the ephemerides computation centers.
-
The Asteroid Identification Problem: II. Target Plane Confidence Boundaries
Icarus, 1999Co-Authors: Andrea Milani, Giovanni B. ValsecchiAbstract:Abstract The nominal orbit solution for an asteroid/comet resulting from a least squares fit to astrometric observations is surrounded by a region containing solutions equally compatible with the data, the confidence region. If the observed arc is not too short, and for an epoch close to the observations, the confidence region in the six-dimensional space of orbital elements is well approximated by an ellipsoid. This uncertainty of the orbital elements maps to a position uncertainty at close approach, which can be represented on a Modified Target Plane (MTP), a modification of the one used by Opik. The MTP is orthogonal to the geocentric velocity at the closest approach point along the nominal orbit. In the linear approximation, the confidence ellipsoids are mapped on the MTP into concentric ellipses, computed by solving the variational equation. For an object observed at only one opposition, however, if the close approach is expected after many revolutions, the ellipses on the MTP become extremely elongated, therefore the linear approximation may fail, and the confidence boundaries on the MTP, by definition the nonlinear images of the confidence ellipsoids, may not be well approximated by the ellipses. In theory the Monte Carlo method by Muinonen and Bowell (1993, Icarus 104 , 255–279) can be used to compute the nonlinear confidence boundaries, but in practice the computational load is very heavy. We propose a new method to compute semilinear confidence boundaries on the MTP, based on the theory developed by Milani (1999, Icarus 137 , 269–292) to efficiently compute confidence boundaries for predicted observations. This method is a reasonable compromise between reliability and computational load, and can be used for real time risk assessment. These arguments can be applied to any small body approaching any planet, but in the case of a potentially hazardous object (PHO), either an asteroid or a comet whose orbit comes very close to that of the Earth, the application is most important. We apply this technique to discuss the recent case of asteroid 1997 XF 11 , which, on the basis of the observations available up to March 11, 1998, appeared to be on an orbit with a near miss of the Earth in 2028. Although the least squares solution had a close approach at 1/8 of the lunar distance, the linear confidence regions corresponding to acceptable size of the residuals are very elongated ellipses which do not include collision; this computation was reported by Chodas and Yeomans. In this paper, we compute the semilinear confidence boundaries and find that they agree with the results of the Monte Carlo method, but differ in a significant way from the linear ellipses, although the differences occur only far from the Earth. The use of the 1990 prediscovery observations has confirmed the impossibility of an impact in 2028 and reduces the semilinear confidence regions to subsets of the regions computed with less data, as expected. The confidence regions computed using the linear approximation, on the other hand, do not reduce to subsets of the regions computed with less data. We also discuss a simulated example (Bowell and Muinonen 1992, Bull. Am. Astron. Soc. 24 , 965) of an Earth-impacting asteroid. In this hypothetical case the semilinear confidence boundary has a completely different shape from the linear ellipse, and indeed for orbits determined with only few weeks of observational data the semilinear confidence boundary correctly includes possible collisions, while the linear one does not. Free software is available now, allowing everyone to compute target plane confidence boundaries as in this paper; in case a new asteroid with worrisome close approaches is discovered, our method allows to quickly perform an accurate risk assessment.