1,721,026 research outputs found
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Recommended from our members
Detecting Differential Score Inflation in Charter Schools
No full textcharter schools, score inflation, high-stakes testin
Recommended from our members
Exploring the Role of Randomization in Causal Inference
No full textThis manuscript includes three topics in causal inference, all of which are under the randomization inference framework (Neyman, 1923; Fisher, 1935a; Rubin, 1978). This manuscript contains three self-contained chapters.
Chapter 1. Under the potential outcomes framework, causal effects are defined as comparisons between potential outcomes under treatment and control. To infer causal effects from randomized experiments, Neyman proposed to test the null hypothesis of zero average causal effect (Neyman’s null), and Fisher proposed to test the null hypothesis of zero individual causal effect (Fisher’s null). Although the subtle difference between Neyman’s null and Fisher’s null has caused lots of controversies and confusions for both theoretical and practical statisticians, a careful comparison between the two approaches has been lacking in the literature for more than eighty years. I fill in this historical gap by making a theoretical comparison between them and highlighting an intriguing paradox that has not been recognized by previous re- searchers. Logically, Fisher’s null implies Neyman’s null. It is therefore surprising that, in actual completely randomized experiments, rejection of Neyman’s null does not imply rejection of Fisher’s null for many realistic situations, including the case with constant causal effect. Furthermore, I show that this paradox also exists in other commonly-used experiments, such as stratified experiments, matched-pair experiments, and factorial experiments. Asymptotic analyses, numerical examples, and real data examples all support this surprising phenomenon. Besides its historical and theoretical importance, this paradox also leads to useful practical implications for modern researchers.
Chapter 2. Causal inference in completely randomized treatment-control studies with binary outcomes is discussed from Fisherian, Neymanian and Bayesian perspectives, using the potential outcomes framework. A randomization-based justification of Fisher’s exact test is provided. Arguing that the crucial assumption of constant causal effect is often unrealistic, and holds only for extreme cases, some new asymptotic and Bayesian inferential procedures are proposed. The proposed procedures exploit the intrinsic non-additivity of unit-level causal effects, can be applied to linear and non- linear estimands, and dominate the existing methods, as verified theoretically and also through simulation studies.
Chapter 3. Recent literature has underscored the critical role of treatment effect variation in estimating and understanding causal effects. This approach, however, is in contrast to much of the foundational research on causal inference; Neyman, for example, avoided such variation through his focus on the average treatment effect and his definition of the confidence interval. In this chapter, I extend the Ney- manian framework to explicitly allow both for treatment effect variation explained by covariates, known as the systematic component, and for unexplained treatment effect variation, known as the idiosyncratic component. This perspective enables es- timation and testing of impact variation without imposing a model on the marginal distributions of potential outcomes, with the workhorse approach of regression with interaction terms being a special case. My approach leads to two practical results.
First, I combine estimates of systematic impact variation with sharp bounds on over- all treatment variation to obtain bounds on the proportion of total impact variation explained by a given model—this is essentially an R2 for treatment effect variation. Second, by using covariates to partially account for the correlation of potential out- comes problem, I exploit this perspective to sharpen the bounds on the variance of the average treatment effect estimate itself. As long as the treatment effect varies across observed covariates, the resulting bounds are sharper than the current sharp bounds in the literature. I apply these ideas to a large randomized evaluation in educational research, showing that these results are meaningful in practice.StatisticsCausal inference; Randomizatio
Recommended from our members
Essays on Educational and Labor Market Transitions
No full textThe education pipeline is characterized by a series of well-defined and extensively documented transitions. From preschool to kindergarten, elementary to middle to high school, and college to work, students at multiple stages of human development experience transitions that shape their downstream outcomes. In this dissertation, I use administrative data and quasi-experimental analytic approaches to examine how people, programs, and policies impact individual outcomes during periods of educational transition.
In my first essay, my co-author and I examine how exposure to peers on the school bus influences one's own academic achievement and behavior. We draw from an established literature on peer effects and an emerging literature on neighborhood effects to show that an out-of-school setting like the school bus can meaningfully impact individual performance. By focusing on idiosyncratic changes to the sets of students riding the bus together that result from school transitions and the spatial structure of bus routes, we develop an approach to estimating peer effects that takes advantage of transition data. To estimate bus peer effects, we measure the extent to which changes in the unexplained component of the performance of a student's bus peers predict otherwise unexplained changes in that student's own performance. We estimate our model using a leave-out-student strategy where we measure the effects of bus peers for each student using data only from their peers. Our identifying assumption is that conditional on student, school-by-school-pair, year, and grade fixed-effects, variation in the residual of student performance common to students who ride the bus together is unrelated to factors apart from their bus ride. We report two main sets of results. First, we show that a standard deviation (SD) shift in bus peers' academic performance corresponds to own changes of 0.02 SD from elementary to middle school and 0.05 SD from middle to high school. We also document shifts in behavior ranging from 0.05 SD from elementary to middle school to 0.08 SD from middle to high school. These results demonstrate that out-of-classroom interactions are more meaningful in adolescence and are roughly half the magnitude of comparably estimated school, counselor, and teacher effects. Second, we leverage survey and neighborhood data to show that the effects of social interactions on the school bus are only partly related to students' prior academic performance and that there is little evidence that bus effects are related to survey-based measures of school climate or student engagement. Our results show that social interactions in informal settings may be important in shaping student learning outcomes, highlighting the need for research to better account for the various out-of-school settings in which students participate.
In my second essay, I move along the education pipeline to high school, where students grapple with questions related to the transition to college and the workforce. In my high school setting, I examine how access to and attainment of industry-recognized certifications (IRCs) shapes post-high school intentions, postsecondary enrollment, and earnings. IRCs are developed by industry groups or corporations for students hoping to demonstrate preparedness for a particular job or sector. In my sample, I leverage proprietary IRC data that covers a diverse set of industry areas, including business, the arts, and manufacturing. In my setting, students sit for an IRC exam and earn the certification if they obtain a passing score. If IRCs represent a postsecondary signal, then certified students may express interest in four-year college or experience higher enrollment rates. If they represent a workforce signal, then certified students may have higher earnings. I use two analytic approaches to describe the effects of earning an IRC in high school. First, I use matched samples of certified and non-certified students to show that IRC earners are considerably more likely to plan to and actually enroll in a four-year college. Moreover, these same students are considerably less likely to plan to and actually enroll in a two-year college. This result suggests that there is a trade-off on the margin of college type. Second, I leverage arguably exogenous assignment to certification status at the passing threshold to show that an IRC does not impact outcomes for the marginal examinee. At best, I uncover suggestive evidence that the marginal IRC earner is slightly more likely to express an interest to work after high school and delay college enrollment. This joint finding suggests that the marginal earner, in contrast with the average earner, uses IRCs as a workforce signal. I find no evidence through either approach that IRC attainment shapes short-term quarterly earnings. The results suggest that for the average certified student, IRCs constitute a component of the college-readiness portfolio while for the marginal student, IRCs weakly signal intentions to work. In all, the results show that IRC effects are more muted than credential proponents may suggest.
Finally, in my third essay, my colleagues and I examine the effects of credential stacking that occurs during transitions between college and work. Credential stacking refers to the practice of earning multiple credentials within a fixed period of time. The vast majority of research estimating returns to credentials focuses on the single degree—whether the associate's, bachelor's, master's, or professional degree. Credential stacking has emerged alongside the demands of employers for workers who can re-skill or up-skill in the face of technological change, the pandemic economy, and demographic shifts. To measure the effects of credential stacking, we leverage statewide administrative data in a state that has emphasized stacking as a strategic workforce initiative. Using decades of postsecondary and labor market data, we use fixed effects approaches with individual time trends to show that credential stackers earn roughly $800 more per quarter than their counterparts who attempt to stack but ultimately do not. Moreover, we show that the benefits of stacking accrue largely to female and non-white stackers, suggesting that credential stacking may be a viable approach to skill development that addresses persistent equity gaps. We also show that credential stackers who pursue a second associate's degree (whether from a certificate or first associate's degree) earn more than stacking by other means, and that stackers in healthcare fields earn roughly twice as much per quarter as the average stacker. Our results suggest that states and institutions continue to pilot and evaluate credential stacking pathways as they pursue approaches to creating broad economic opportunity for adult learners.
Taken together, these three empirical studies shed light on factors that shape individual trajectories at critical inflection points. Each paper contributes to an established research paradigm in important ways. New estimates of transition-induced bus peer effects that approach the lower bound of established effects in education (e.g., teacher, leader, or school) suggest that out-of-school contexts matter. Causal effects of IRC attainment on college enrollment and quarterly earnings paint a mixed picture and suggest that claims about the promise of certification for school-to-work transitions may be exaggerated. Finally, returns to credential stacking in the transition between school and work suggest that the practice boosts average earnings and can reduce longstanding equity gaps in the process
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Recommended from our members
Topics in experimental and tournament design
Full text linkWe examine three topics related to experimental design in this dissertation. Two are related to the analysis of experimental data and the other focuses on the design of paired comparison experiments, in this case knockout tournaments. The two analysis topics are motivated by how to estimate and test causal effects when the assignment mechanism fails to create balanced treatment groups. In Chapter 2, we apply conditional randomization tests to experiments where, through random chance, the treatment groups differ in their covariate distributions. In Chapter 4, we apply principal stratification to factorial experiments where the subjects fail to comply with their assigned treatment. The sources of imbalance differ, but, in both cases, ignoring the imbalance can lead to incorrect conclusions.
In Chapter 3, we consider designing knockout tournaments to maximize different objectives given a prior distribution on the strengths of the players. These objectives include maximizing the probability the best player wins the tournament. Our emphasis on balance in the other two chapters comes from a desire to create a fair comparison between treatments. However, in this case, the design uses the prior information to intentionally bias the tournament in favor of the better players.Statistic
Recommended from our members
Measurement in K-12 Policy Analysis
Full text linkThis dissertation consists of three papers that consider the construction, role, and use of educational measures in educational policies and evaluation methods. Educational measures, such as student test scores, are widely used to evaluate the effectiveness of educational programs or policies.
The first paper investigates the properties of school quality scores in state educational accountability systems under the Every Student Succeeds Act (2015). I use multilevel modeling and factor analysis to simulate an accountability system based on a state’s existing student- and school-level data. I find that this system exhibits high classification accuracy of the state’s lowest performing schools, particularly for elementary schools. I also test how classification accuracy varies due to common policy decisions and show that these design choices have differential effects by school level. This challenges uniform accountability approaches across school levels and suggest the need for level-specific policy decisions in designing these complex systems.
The second paper explores the use of a nonparametric surface response estimation method, Gaussian process regression (GPR), in educational two-dimensional regression discontinuity designs. Regression discontinuity designs are used to estimate the effectiveness of policies or programs, which in education are commonly provided to students based on their scores on multiple tests, such as math and reading. GPR allows one to target an estimand of a boundary average treatment effect as well as understand treatment effect heterogeneity in student outcomes. In simulation, GPR exhibits stronger statistical properties compared to existing methods, and it improves the analysis of an empirical example of a state’s English Language Learner reclassification policy based on two test scores.
The third paper analyzes how state policy documents discuss the use of student sociodemographic variables in constructing teacher value-added model (VAM) scores. VAMs are used to evaluate educators through comparisons between expected and observed student test scores, conditioning on students’ prior achievement and other information. Despite states’ agreement that the role of student background in academic performance should be statistically accounted for when evaluating teachers to increase fairness to educators, I find that states work against their stated goals by tending to exclude race from these calculations, which I examine using tenets of quantitative critical theory.Educatio
Recommended from our members
A Three-Study Examination of Test-Based Accountability Metrics
No full textRecent state and federal policy initiatives have led to the development of a multitude of statistics intended to measure school performance. Of these, statistics constructed from student test scores number among both the most widely-used and most controversial. In many cases, researchers and policymakers alike are not fully aware of the ways in which these statistics may lead to unjustified inferences regarding school effectiveness. A substantial amount of recent research has attempted to remedy this, although much remains unknown.
This thesis seeks to contribute to these research efforts via three papers, each examining how a commonly-employed accountability statistic may be influenced by factors unrelated to student proficiency or school effectiveness. The first paper demonstrates how the discrete nature of test scores leads to biased estimates of changes in the percentage of “proficient” students between any two given years and examines estimators that provide better recovery of this parameter. The second paper makes use of a state-wide natural experiment to show that a change in testing program, from paper-and-pencil to computer-adaptive, may cause apparent changes in achievement gaps even when relative student proficiencies have remained constant. The third paper examines “growth-based” accountability metrics based on vertically-scaled assessments, showing that certain types of metrics based on gain scores can be modeled via nonlinear transformations of the underlying vertical scale. It then makes use of this result to investigate the potential magnitude of impacts of such transformations on growth-based school accountability ratings.educational assessment; accountability; education polic
- …
