scholarly journals Apples and Oranges? The Problem of Equivalence in Comparative Research

2011 ◽  
Vol 19 (4) ◽  
pp. 471-487 ◽  
Author(s):  
Daniel Stegmueller
Keyword(s):  
Item Response ◽  
Comparative Research ◽  
Large Scale ◽  
Structural Parameters ◽  
Simultaneous Estimation ◽  
Response Behavior ◽  
Item Response Model ◽  
Individual Level ◽  
Level Data ◽  
Cross National

Researchers in comparative research are increasingly relying on individual level data to test theories involving unobservable constructs like attitudes and preferences. Estimation is carried out using large-scale cross-national survey data providing responses from individuals living in widely varying contexts. This strategy rests on the assumption of equivalence, that is, no systematic distortion in response behavior of individuals from different countries exists. However, this assumption is frequently violated with rather grave consequences for comparability and interpretation. I present a multilevel mixture ordinal item response model with item bias effects that is able to establish equivalence. It corrects for systematic measurement error induced by unobserved country heterogeneity, and it allows for the simultaneous estimation of structural parameters of interest.

scholarly journals The measurement of populist attitudes: Testing cross-national scales using item response theory

Politics ◽  
2019 ◽  
Vol 40 (1) ◽  
pp. 3-21 ◽  
Author(s):  
Steven M Van Hauwaert ◽  
Christian H Schimpf ◽  
Flavio Azevedo
Keyword(s):  
Item Response Theory ◽  
Item Response ◽  
Empirical Evaluation ◽  
Measurement Model ◽  
Future Research ◽  
Response Theory ◽  
Individual Level ◽  
National Measurement ◽  
The Individual ◽  
Cross National

Recent research in the populism literature has devoted considerable efforts to the conceptualisation and examination of populism on the individual level, that is, populist attitudes. Despite rapid progress in the field, questions of adequate measurement and empirical evaluation of measures of populist attitudes remain scarce. Seeking to remedy these shortcomings, we apply a cross-national measurement model, using item response theory, to six established and two new populist indicators. Drawing on a cross-national survey (nine European countries, n = 18,368), we engage in a four-folded analysis. First, we examine the commonly used 6-item populism scale. Second, we expand the measurement with two novel items. Third, we use the improved 8-item populism scale to further refine equally comprehensive but more concise and parsimonious populist measurements. Finally, we externally validate these sub-scales and find that some of the proposed sub-scales outperform the initial 6- and 8-item scales. We conclude that existing measures of populism capture moderate populist attitudes, but face difficulties measuring more extreme levels, while the individual information of some of the populist items remains limited. Altogether, this provides several interesting routes for future research, both within and between countries.

scholarly journals Four dimensions characterize comprehensive trait judgments of faces

2019 ◽  
Author(s):  
Chujun Lin ◽  
Umit Keles ◽  
Ralph Adolphs
Keyword(s):  
Large Scale ◽  
Real Life ◽  
Three Dimensions ◽  
Prior Work ◽  
Four Dimensions ◽  
Individual Level ◽  
Level Data ◽  
Trait Words ◽  
Psychological Dimensions

People readily attribute many traits to faces: some look beautiful, some competent, some aggressive1. These snap judgments have important consequences in real life, ranging from success in political elections to decisions in courtroom sentencing2,3. Modern psychological theories argue that the hundreds of different words people use to describe others from their faces are well captured by only two or three dimensions, such as valence and dominance4, a highly influential framework that has been the basis for numerous studies in social and developmental psychology5–10, social neuroscience11,12, and in engineering applications13,14. However, all prior work has used only a small number of words (12 to 18) to derive underlying dimensions, limiting conclusions to date. Here we employed deep neural networks to select a comprehensive set of 100 words that are representative of the trait words people use to describe faces, and to select a set of 100 faces. In two large-scale, preregistered studies we asked participants to rate the 100 faces on the 100 words (obtaining 2,850,000 ratings from 1,710 participants), and discovered a novel set of four psychological dimensions that best explain trait judgments of faces: warmth, competence, femininity, and youth. We reproduced these four dimensions across different regions around the world, in both aggregated and individual-level data. These results provide a new and most comprehensive characterization of face judgments, and reconcile prior work on face perception with work in social cognition15 and personality psychology16.

scholarly journals Impact of increasing vegetarian availability on meal selection and sales in cafeterias

2019 ◽  
Vol 116 (42) ◽  
pp. 20923-20929 ◽  
Author(s):  
Emma E. Garnett ◽  
Andrew Balmford ◽  
Chris Sandbrook ◽  
Mark A. Pilling ◽  
Theresa M. Marteau
Keyword(s):  
Large Scale ◽  
Population Level ◽  
Field Studies ◽  
Individual Level ◽  
Rebound Effects ◽  
Percentage Points ◽  
Physical Environments ◽  
Meat Meal ◽  
Level Data ◽  
The Impact

Shifting people in higher income countries toward more plant-based diets would protect the natural environment and improve population health. Research in other domains suggests altering the physical environments in which people make decisions (“nudging”) holds promise for achieving socially desirable behavior change. Here, we examine the impact of attempting to nudge meal selection by increasing the proportion of vegetarian meals offered in a year-long large-scale series of observational and experimental field studies. Anonymized individual-level data from 94,644 meals purchased in 2017 were collected from 3 cafeterias at an English university. Doubling the proportion of vegetarian meals available from 25 to 50% (e.g., from 1 in 4 to 2 in 4 options) increased vegetarian meal sales (and decreased meat meal sales) by 14.9 and 14.5 percentage points in the observational study (2 cafeterias) and by 7.8 percentage points in the experimental study (1 cafeteria), equivalent to proportional increases in vegetarian meal sales of 61.8%, 78.8%, and 40.8%, respectively. Linking sales data to participants’ previous meal purchases revealed that the largest effects were found in the quartile of diners with the lowest prior levels of vegetarian meal selection. Moreover, serving more vegetarian options had little impact on overall sales and did not lead to detectable rebound effects: Vegetarian sales were not lower at other mealtimes. These results provide robust evidence to support the potential for simple changes to catering practices to make an important contribution to achieving more sustainable diets at the population level.

Violence By and Against Women: A Comparative and Cross-National Analysis

1993 ◽  
Vol 8 (3) ◽  
pp. 253-270 ◽  
Author(s):  
Candace Kruttschnitt
Keyword(s):  
At Risk ◽  
Current Knowledge ◽  
Levels Of Analysis ◽  
Aggregate Level ◽  
Individual Level ◽  
Violent Offending ◽  
Level Data ◽  
Societal Level ◽  
National Analysis ◽  
Cross National

Drawing from different kinds and levels of analysis, this article synthesizes current knowledge on women’s violent offending and victimization cross-nationally. Individual-level data indicate characteristics and situations that put women at risk for violence within particular countries. Aggregate-level data concentrate on women’s risks of violent encounters across nations and the societal-level factors that are associated with these risks. This multinational, multilevel approach reveals substantial gaps between our understanding of the types of encounters in which women are at greatest risk for violence and the societal correlates that predict gender distributions in violence across nations.

An Item Response Model for the Estimation of Demographic Effects

1983 ◽  
Vol 8 (3) ◽  
pp. 165-186 ◽  
Author(s):  
Mark Reiser
Keyword(s):  
Item Response ◽  
Demographic Variables ◽  
Response Model ◽  
Item Response Model ◽  
National Assessment ◽  
Individual Level ◽  
Matrix Sampling ◽  
Cross Classification ◽  
Sampling Procedures

Item sampling procedures employed in many assessment studies are designed so that each respondent answers a small number of items in each of a large number of skill areas. If the item population contains several items designed to measure an underlying variable such as computation skill, it may be desirable to fit an item response model to the data. In studies that employ multiple matrix sampling there are not enough answers from each individual to employ such a model. To circumvent this problem, a model is formulated on the assumption that individual level variability appears as independent error within the cells of the cross classification of manifest demographic variables such as sex and race. This model is successfully fit to a scale of items, involving addition of fractions, from the National Assessment Study.

scholarly journals Ignoring a Multilevel Structure in Mixture Item Response Models: Impact on Parameter Recovery and Model Selection

2017 ◽  
Vol 42 (2) ◽  
pp. 136-154 ◽  
Author(s):  
Woo-yeol Lee ◽  
Sun-Joo Cho ◽  
Sonya K. Sterba
Keyword(s):  
Model Selection ◽  
Item Response ◽  
Cluster Size ◽  
Response Model ◽  
Item Response Model ◽  
Number Of Clusters ◽  
Parameter Recovery ◽  
Single Level ◽  
Multilevel Structure ◽  
Level Data

The current study investigated the consequences of ignoring a multilevel structure for a mixture item response model to show when a multilevel mixture item response model is needed. Study 1 focused on examining the consequence of ignoring dependency for within-level latent classes. Simulation conditions that may affect model selection and parameter recovery in the context of a multilevel data structure were manipulated: class-specific ICC, cluster size, and number of clusters. The accuracy of model selection (based on information criteria) and quality of parameter recovery were used to evaluate the impact of ignoring a multilevel structure. Simulation results indicated that, for the range of class-specific ICCs examined here (.1 to .3), mixture item response models which ignored a higher level nesting structure resulted in less accurate estimates and standard errors ( SEs) of item discrimination parameters when the number of clusters was larger than 24 and the cluster size was larger than six. Class-varying ICCs can have compensatory effects on bias. Also, the results suggested that a mixture item response model which ignored multilevel structure was not selected over the multilevel mixture item response model based on Bayesian information criterion (BIC) if the number of clusters and cluster size was at least 50, respectively. In Study 2, the consequences of unnecessarily fitting a multilevel mixture item response model to single-level data were examined. Reassuringly, in the context of single-level data, a multilevel mixture item response model was not selected by BIC, and its use would not distort the within-level item parameter estimates or SEs when the cluster size was at least 20. Based on these findings, it is concluded that, for class-specific ICC conditions examined here, a multilevel mixture item response model is recommended over a single-level item response model for a clustered dataset having cluster size [Formula: see text] and the number of clusters [Formula: see text].

Multilevel Item Response Models: An Approach to Errors in Variables Regression

1997 ◽  
Vol 22 (1) ◽  
pp. 47-76 ◽  
Author(s):  
Raymond J. Adams ◽  
Mark Wilson ◽  
Margaret Wu
Keyword(s):  
Item Response ◽  
Latent Variables ◽  
Population Distribution ◽  
Estimation Method ◽  
Student Population ◽  
Simultaneous Estimation ◽  
Item Response Model ◽  
Student Model ◽  
Measurement Models ◽  
Two Step Estimation

In this article we show how certain analytic problems that arise when one attempts to use latent variables as outcomes in regression analyses can be addressed by taking a multilevel perspective on item response modeling. Under a multilevel, or hierarchical, perspective we cast the item response model as a within-student model and the student population distribution as a between-student model. Taking this perspective leads naturally to an extension of the student population model to include a range of student-level variables, and it invites the possibility of further extending the models to additional levels so that multilevel models can be applied with latent outcome variables. In the two-level case, the model that we employ is formally equivalent to the plausible value procedures that are used as part of the National Assessment of Educational Progress (NAEP), but we present the method for a different class of measurement models, and we use a simultaneous estimation method rather than two-step estimation. In our application of the models to the appropriate treatment of measurement error in the dependent variable of a between-student regression, we also illustrate the adequacy of some approximate procedures that are used in NAEP.

scholarly journals Approximate conditional phenotype analysis based on genome wide association summary statistics

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Peitao Wu ◽  
Biqi Wang ◽  
Steven A. Lubitz ◽  
Emelia J. Benjamin ◽  
James B. Meigs ◽  
...  
Keyword(s):  
Large Scale ◽  
Genome Wide Association Study ◽  
Genome Wide Association ◽  
Summary Statistics ◽  
Phenotypic Data ◽  
Individual Level ◽  
Genome Wide ◽  
Level Data ◽  
A Genome ◽  
Phenotype Analysis

AbstractBecause single genetic variants may have pleiotropic effects, one trait can be a confounder in a genome-wide association study (GWAS) that aims to identify loci associated with another trait. A typical approach to address this issue is to perform an additional analysis adjusting for the confounder. However, obtaining conditional results can be time-consuming. We propose an approximate conditional phenotype analysis based on GWAS summary statistics, the covariance between outcome and confounder, and the variant minor allele frequency (MAF). GWAS summary statistics and MAF are taken from GWAS meta-analysis results while the traits covariance may be estimated by two strategies: (i) estimates from a subset of the phenotypic data; or (ii) estimates from published studies. We compare our two strategies with estimates using individual level data from the full GWAS sample (gold standard). A simulation study for both binary and continuous traits demonstrates that our approximate approach is accurate. We apply our method to the Framingham Heart Study (FHS) GWAS and to large-scale cardiometabolic GWAS results. We observed a high consistency of genetic effect size estimates between our method and individual level data analysis. Our approach leads to an efficient way to perform approximate conditional analysis using large-scale GWAS summary statistics.

Corruption and its Impact on Protest Activities in Post-communist Europe

2021 ◽  
pp. 1-15
Author(s):  
Milan Školník
Keyword(s):  
Political Participation ◽  
Large Scale ◽  
Role Of Government ◽  
Individual Level ◽  
Level Data ◽  
Public Protest ◽  
State Administration ◽  
Communist Countries ◽  
The Impact

Corruption is a phenomenon that affects societies. It lowers trust in public institutions, lowers trust among people, undermines economic development, undermines democracy, and has implications for political participation. This article contributes to current debates on the impact of corruption by looking at other possible consequences of corruption. Specifically, this article looks at the impact of the perception of corruption on the approval of public protest meetings and demonstrations because, if corruption leads to these non-institutionalized forms of political participation, this may lead to security problems or a direct outbreak of violence. This study analyses this relationship by using seven post-communist countries that have undergone specific developments in terms of corruption. These developments were largely due to large-scale privatizations, politicized state administration, and the linking of politicians to the private sector. This research was conducted with individual-level data. The module ‘The Role of Government V’ from the International Social Survey Programme was used. Descriptive charts have revealed that in six out of the seven countries, most respondents considered politicians to be very corrupt. Around 80% of respondents in all seven countries approve of the organization of public protest meetings. Around 70% of respondents in all seven countries approve of demonstrations. Regression analysis revealed that there is a relationship between the perception of corruption among politicians and the approval of protest activities. Specifically, the more politicians are corrupt, the more people approve of holding public protest meetings and demonstrations.

scholarly journals Four dimensions characterizing comprehensive trait judgments of faces

2020 ◽  
Author(s):  
Chujun Lin ◽  
Umit Keles ◽  
Ralph Adolphs
Keyword(s):  
Large Scale ◽  
Developmental Psychology ◽  
Three Dimensions ◽  
Four Dimensions ◽  
Individual Level ◽  
Psychological Theories ◽  
Level Data ◽  
Trait Words ◽  
Psychological Dimensions

Abstract People readily attribute many traits to faces: some look beautiful, some competent, some aggressive. Modern psychological theories argue that the hundreds of different words people use to describe others from their faces are well captured by only two or three dimensions, such as valence and dominance, a highly influential framework that has been the basis for numerous studies across social and developmental psychology, social neuroscience, and engineering applications. However, all prior work has used only a small number of words (12 to 18) to derive underlying dimensions, limiting conclusions to date. Here we employed deep neural networks to select a comprehensive set of 100 words that are representative of the trait words people use to describe faces, and to select a set of 100 faces. In two large-scale, preregistered studies we asked participants to rate the 100 faces on the 100 words (obtaining 2,850,000 ratings from 1,710 participants), and discovered a novel set of four psychological dimensions that best explain trait judgments of faces: warmth, competence, femininity, and youth. We reproduced these four dimensions across different regions around the world, in both aggregated and individual-level data. These results provide a new and most comprehensive characterization of face judgments.

Sign in / Sign up

Export Citation Format

Share Document