Common Factor Structure Research Articles

Innovation, Structural Change, and Inclusion. A Cross Country PVAR Analysis

Structural change can be both, a cause or a consequence of innovation, while structural change and innovations are usually accompanied by short-term outcomes of social inclusion or exclusion. Inclusion may in turn have an impact on further innovations. Yet, we find little evidence in the literature on the three-way relations between innovation, structural change and inclusion. This paper advances a first exercise in this direction. Given the multidimensionality of each (innovation, structural change, and inclusion), we extract the underlying unobserved common factor structure from various well-known macro indicators. With a structural vector auto regression (SVAR) model for a short panel of developing countries over 13 years, we find the following main results. First, we confirm the virtuous cycle between innovation and structural change, aligning with existing literature. Second, the strongest result is the positive effect of inclusion on both innovation and structural change, that suggests policy to improve inclusion beyond poverty and inequality. Third, on decomposing the innovation index (formal, firm-level and ICT), we find each related differently to both structural change and inclusion, that suggests specific policy roles in their influence on inclusion and structural change.

Sharing a ride on the commodities roller coaster: Common factors in business cycles of emerging economies

We explore the hypothesis that fluctuations in commodity prices are an important driver of business cycles in small emerging market economies (EMEs). First, we document that commodity prices exhibit strong comovement with other macro variables along the business cycle of these economies; and that a common factor accounts for most of the time series dynamics of these commodity prices. Guided by these stylized facts, we embed a commodity sector into a dynamic, stochastic, multi-country business cycle model of EMEs where exogenous fluctuations in commodity prices coexist with other driving forces. Commodity prices follow a common dynamic factor structure in the model. When estimated with EMEs data, the model gives to commodity shocks, mostly in the form of perturbations to their common factor, a paramount role when accounting for aggregate dynamics: more than a third of the variance of real output across the EMEs considered is associated to commodity price shocks. The model also performs well when accounting for other business cycle facts. A further amplification mechanism is a “spillover” effect from commodity prices to interest rates. Yet, sometimes, positive commodity price shocks have also cushioned other negative domestic shocks, particularly during the fast recovery from the world financial crisis.

Measuring the international dimension of output volatility

This paper studies output fluctuations in a panel of OECD economies with the aim to decompose the evolution in output volatility into domestic and international factors. To this end we use a factor-augmented dynamic panel model with both domestic and international shocks and spillovers between countries through trade linkages. Changes in the volatility of output growth can be due to time-varying sensitivity to these shocks, changes in the propagation mechanism or shifts in the variances of shocks. We explicitly model cross-sectional dependence in the variance equation by specifying a common factor structure in the volatility of domestic shocks. The results show that while the size of international shocks and spillovers does not decrease in most countries, the volatilities of domestic shocks share a clear common decreasing trend. Hence, the ‘Great Moderation’ appears to be mainly driven by a decline in the volatility of domestic shocks rather than smaller international shocks.

A simple randomization test for spatial correlation in the presence of common factors and serial correlation

A randomization test is proposed for detecting spatial dependence in panel models with cross-sectional dependence induced by an unobserved common factor structure. Spatial dependence is related to the position of observations in space while cross-sectional dependence is generally not; yet spatial correlation tests have power against both. Permuting the pairs of neighbouring observations in the proximity matrix yields a simple spatial dependence test which is robust to the presence of non-spatial cross-sectional correlation, serial correlation and can accommodate short and unbalanced panels. The proposed procedure is evaluated and compared to alternatives through Monte Carlo simulation; it is then illustrated by an application to recent research on technology spillovers. A user-friendly R implementation is provided.

Quantile Co-Movement in Financial Markets; a Panel Quantile Model with Unobserved Heterogeneity

This paper introduces a new procedure for analyzing the quantile co-movement of a large number of financial time series based on a large-scale panel data model with factor structures. The proposed method attempts to capture the unobservable heterogeneity of each of the financial time series based on sensitivity to explanatory variables and to the unobservable factor structure. In our model, the dimension of the common factor structure varies across quantiles, and the factor structure is allowed to be correlated with the explanatory variables. The proposed method allows for both cross-sectional and serial dependence, and heteroskedasticity, which are common in financial markets. We propose new estimation procedures for both frequentist and Bayesian frameworks. Consistency and asymptotic normality of the proposed estimator are established. We also propose a new model selection criterion for determining the number of common factors together with theoretical support. We apply the method to analyze the returns for over 6,000 international stocks from over 60 countries during the subprime crisis, European sovereign debt crisis, and subsequent period. The empirical analysis indicates that the common factor structure varies across quantiles. We find that the common factors for the quantiles and the common factors for the mean are different.

Multifactor Models and the APT: Evidence from a Broad Cross-Section of Stock Returns

We seek to describe the broad cross-section of average stock returns. We follow the APT literature and estimate the common factor structure among a large cross-section containing 278 decile portfolios associated with 28 market anomalies. Our statistical model contains seven common factors (with an economic meaning) and prices well both the original portfolio returns and an efficient combination of these portfolios. This model clearly outperforms the empirical workhorses in the literature when it comes to pricing this broad cross-section. Augmenting the empirical models with new factor-mimicking portfolios, based on APT principles, significantly improves their performance. Our results shed light on the number of factors necessary to describe expected stock returns. Moreover, we show that there is significant room for improving the existing multifactor models in terms of explaining the large cross-section of stock returns (and in a way that is consistent with the APT).

Modified CADF and CIPS Panel Unit Root Statistics with Standard Chi‐squared and Normal Limiting Distributions

AbstractIn an influential paper Pesaran (‘A simple panel unit root test in presence of cross‐section dependence’, Journal of Applied Econometrics, Vol. 22, pp. 265–312, 2007) proposes two unit root tests for panels with a common factor structure. These are the CADF and CIPS test statistics, which are amongst the most popular test statistics in the literature. One feature of these statistics is that their limiting distributions are highly non‐standard, making for relatively complicated implementation. In this paper, we take this feature as our starting point to develop modified CADF and CIPS test statistics that support standard chi‐squared and normal inference.

Comparability of Mean Scores of Gifted Students on the Jordanian Version of the Overexcitability Questionnaire (OEQII) Across Gender

The aim of the present study was to investigate the comparability of the mean scores of gifted students on the Jordanian version of the Overexcitabilities Questionnaire OEQII in light of gender. A cluster random sampling technique was used to collect data from 448 males and females gifted students who are enrolled in the King Abdullah II Schools of Excellence in Jordan. Results of multi-group confirmatory factor analysis clearly indicate that measurement invariance with respect to gender is untenable. Uniform measurement bias was observed in all subscales. Results suggested that the Jordanian version of OEQII failed to display scalar invariance across gender which is a requirement to scores’ comparability. Initial analyses of fitting the model to the data for each subscale suggested that the theoretical common factor structure didn’t display a reasonable fit to the data for any subscale. Results suggested that the Jordanian version of OEQII failed initially to display configural invariance across gender. In light of the results, it is recommended that the mean-level comparisons of OEQII subscale scores across gender should be interpreted with caution. Moreover, re-validating and re- standardizing of the Jordanian version of OEQII was suggested to justify mean scores comparability on its subscales.

Comparability of Mean Scores of Gifted Students on the Jordanian Version of the Overexcitability Questionnaire (OEQII) Across Gender

The aim of the present study was to investigate the comparability of the mean scores of gifted students on the Jordanian version of the Overexcitabilities Questionnaire OEQII in light of gender. A cluster random sampling technique was used to collect data from 448 males and females gifted students who are enrolled in the King Abdullah II Schools of Excellence in Jordan. Results of multi-group confirmatory factor analysis clearly indicate that measurement invariance with respect to gender is untenable. Uniform measurement bias was observed in all subscales. Results suggested that the Jordanian version of OEQII failed to display scalar invariance across gender which is a requirement to scores’ comparability. Initial analyses of fitting the model to the data for each subscale suggested that the theoretical common factor structure didn’t display a reasonable fit to the data for any subscale. Results suggested that the Jordanian version of OEQII failed initially to display configural invariance across gender. In light of the results, it is recommended that the mean-level comparisons of OEQII subscale scores across gender should be interpreted with caution. Moreover, re-validating and re- standardizing of the Jordanian version of OEQII was suggested to justify mean scores comparability on its subscales.

Sharing a Ride on the Commodities Roller Coaster: Common Factors in Business Cycles of Emerging

Fluctuations in commodity prices are an important driver of business cycles in small emerging market economies (EMEs). We document how these fluctuations correlate strongly with the business cycle in EMEs. We then embed a commodity sector into a multi-country EMEs' business cycle model where exogenous fluctuations in commodity prices follow a common dynamic factor structure and coexist with other driving forces. The estimated model assigns to commodity shocks 42 percent of the variance in income, of which a considerable part is linked to the common factor. A further amplification mechanism is a 'spillover' effect from commodity prices to risk premia.

Evaluation of the three-component model of organizational commitment in South Korea

Allen and Meyer's(1990) 3-component model of organizational commitment(OC) was investigated using exploratory structural equation modeling(ESEM) with samples of full-time social workers at social welfare organizations in South Korea. Confirmatory factor analysis(CFA) has been at the heart of testing factor structure of the 3-component model in organizational commitment research wherein each scale of the affective, continuance, and normative commitment is reported to measure conceptually and empirically separable construct. The present study applied ESEM, specifically ‘intra-scale’ and ‘inter-scale’ ESEM, to scrutinize factor structure of the 3-component scales. ESEM methodology uses exploratory approach in that all cross-loadings are estimated between each measure and factors, with uniqueness correlated according to the researcher's hypotheses as in CFA. In this respect, ESEM can be viewed as an open approach to item analysis distinguished from the conventional (closed) approach, such as EFA and CFA. This study provided detailed assessment of the 3-component model through comparisons of factor structures estimated by EFA, CFA and ‘intra’ ESEM, followed by the ‘inter’ ESEM conducted on all other variables(assumed to be similar constructs with or antecedents of OC). As a result, the ‘intra-scale’ ESEM showed a substantially better fit and yielded more discriminated factors(less correlated) than did EFA and CFA that are models for planned scale. The ‘inter-scale’ ESEM revealed how seriously method effect can distort an original factor structure in empirical data measured together with multiple scales of other constructs. Using ESEM has advantages of estimating common factor structures, controlling for common method effect that are typically included in measures in applied research. Also, it allows for much more possibilities that each item can measure multiple constructs so as to reveal more realistic factor structures. Taken together, the present results suggest a need to conceptualize and validate a new scale for organizational commitment reflecting Korean culture.

Evaluation of the Three-Component Model of Organizational Commitment in South Korea: Exploratory Structural Equation Modeling(ESEM) Approach

Allen and Meyer's(1990) 3-component model of organizational commitment(OC) was investigated using exploratory structural equation modeling(ESEM) with samples of full-time social workers at social welfare organizations in South Korea. Confirmatory factor analysis(CFA) has been at the heart of testing factor structure of the 3-component model in organizational commitment research wherein each scale of the affective, continuance, and normative commitment is reported to measure conceptually and empirically separable construct. The present study applied ESEM, specifically ‘intra-scale’ and ‘inter-scale’ ESEM, to scrutinize factor structure of the 3-component scales. ESEM methodology uses exploratory approach in that all cross-loadings are estimated between each measure and factors, with uniqueness correlated according to the researcher's hypotheses as in CFA. In this respect, ESEM can be viewed as an open approach to item analysis distinguished from the conventional (closed) approach, such as EFA and CFA. This study provided detailed assessment of the 3-component model through comparisons of factor structures estimated by EFA, CFA and ‘intra’ ESEM, followed by the ‘inter’ ESEM conducted on all other variables(assumed to be similar constructs with or antecedents of OC). As a result, the ‘intra-scale’ ESEM showed a substantially better fit and yielded more discriminated factors(less correlated) than did EFA and CFA that are models for planned scale. The ‘inter-scale’ ESEM revealed how seriously method effect can distort an original factor structure in empirical data measured together with multiple scales of other constructs. Using ESEM has advantages of estimating common factor structures, controlling for common method effect that are typically included in measures in applied research. Also, it allows for much more possibilities that each item can measure multiple constructs so as to reveal more realistic factor structures. Taken together, the present results suggest a need to conceptualize and validate a new scale for organizational commitment reflecting Korean culture.

Using multi-group confirmatory factor analysis to evaluate cross-cultural research: identifying and understanding non-invariance

Multi-group confirmatory factor analysis (MGCFA) allows researchers to determine whether a research inventory elicits similar response patterns across samples. If statistical equivalence in responding is found, then scale score comparisons become possible and samples can be said to be from the same population. This paper illustrates the use of MGCFA by examining survey results relating to practising teachers' conceptions of feedback in two very different jurisdictions (Louisiana, USA, n = 308; New Zealand, n = 518), highlighting challenges which can occur when conducting this kind of cross-cultural research. As the two contexts had very different policies and practices around educational assessment, it was considered possible that a common research inventory may elicit non-equivalent responding, leading to non-invariance. Independent models for each group and a joint model for all participants were tested for invariance using MGCFA and all were inadmissible for one of the two groups. Inspection of joint model differences in item loadings, scale reliabilities, and scale inter-correlations established the extent of non-invariance. This paper discusses the implications of non-invariance within this particular study and identifies difficulties in using an inventory in cross-cultural settings. It also provides suggestions about how to increase the likelihood that a common factor structure can be recovered.

Reliability-Related Issues in the Context of Student Evaluations of Teaching in Higher Education

Student evaluations of teaching (SET) forms have been the principal instrument to elicit students’ opinion in higher education institutions. Many decisions, including high-stake ones, are made based on SET scores reported by students. In this respect, reliability of SET scores is of considerable importance. But this paper has an argument that there are some problems in choosing and use of reliability indices in SET context. Three hypothesizes were tested: (i) using internal consistency measures is misleading in SET context since the variability is mainly due to disagreement between students’ ratings which requires use of inter-rater reliability coefficients, (ii) number of minimum feedbacks is not achieved in most of the classes, resulting unreliable decisions, and (iii) calculating reliability assuming a common factor structure across all classes is misleading because a common factorial model may not be tenable for all. Results showed that use of only internal con s istency to assess SET scores may be misleading. Considerable large numbers of missing feedbacks were observed to achieve acceptable reliability levels. Findings also indicated that factorial models differed across several groups, which calculation of reliability coefficients become problematic.

Experiences in close relationships-revised (ECR-R): Measurement (non-) invariance across Chinese and Greek samples

Attachment is an important relational construct. Many studies have shown concurrent as well as longitudinal associations between attachment and many indices of adolescent and adult adaptation. The experiences in close relationships-revised (ECR-R) is one of the most commonly used self-report instruments of romantic attachment and therefore it is important to extend knowledge on its applicability in understudied non-Western samples. The purpose of this paper was threefold: (1) to examine the factor structure of the ECR-R in a Chinese sample, (2) to test the factorial equivalence of the instrument between Chinese and Greek samples, (3) to examine the measurement invariance of the instrument between those samples. Results supported the well-known two-factor structure of the instrument in the Chinese sample and the common factor structure between the two groups. Applying a multiple testing procedure we were able to detect those parameters for which invariance did not hold. Implications of results are discussed.

Non-nested testing of spatial correlation

We develop non-nested tests in a general spatial, spatio-temporal or panel data context. The spatial aspect can be interpreted quite generally, in either a geographical sense, or employing notions of economic distance, or when parametric modelling arises in part from a common factor or other structure. In the former case, observations may be regularly-spaced across one or more dimensions, as is typical with much spatio-temporal data, or irregularly-spaced across all dimensions; both isotropic models and non-isotropic models can be considered, and a wide variety of correlation structures. In the second case, models involving spatial weight matrices are covered, such as “spatial autoregressive models”. The setting is sufficiently general to potentially cover other parametric structures such as certain factor models, and vector-valued observations, and here our preliminary asymptotic theory for parameter estimates is of some independent value. The test statistic is based on a Gaussian pseudo-likelihood ratio, and is shown to have an asymptotic standard normal distribution under the null hypothesis that one of the two models is correct; this limit theory rests strongly on a central limit theorem for the Gaussian pseudo-maximum likelihood parameter estimates. A small Monte Carlo study of finite-sample performance is included.

Sharing a Ride on the Commodities Roller Coaster: Common Factors in Business Cycles of Emerging Economies

Fluctuations in commodity prices are an important driver of business cycles in small emerging market economies (EMEs). We document how these fluctuations correlate strongly with the business cycle in EMEs. We then embed a commodity sector into a multi-country EMEs’ business cycle model where exogenous fluctuations in commodity prices follow a common dynamic factor structure and coexist with other driving forces. The estimated model assigns to commodity shocks 42 percent of the variance in income, of which a considerable part is linked to the common factor. A further amplification mechanism is a ”spillover” effect from commodity prices to risk premia.

DEVELOPMENT OF THE PERCEIVED EMPLOYMENT BARRIER SCALE (PEBS): MEASURING PSYCHOLOGICAL SELF‐SUFFICIENCY

The purpose of this study is to (a) validate the psychometric properties of the Perceived Employment Barrier Scale (PEBS) and (b) investigate the effect of perceived barriers on employment hope. An exploratory factor analysis (EFA), a confirmatory factor analysis (CFA), and a series of invariance tests were conducted to validate PEBS using two independent samples. Structural equation modeling (SEM) was used to test the hypothesized relationship. The latent factor structure generated by EFA failing to fit efficiently in CFA, the model was revised to a 5‐factor, 20‐item structure. This model demonstrated a common latent factor and item structure in both samples. And SEM results suggest a significant negative effect of perceived employment barriers on employment hope. PEBS is a reliable and valid measure that could be used as an evidence‐based tool for comprehensively assessing client‐centered employment barriers and providing appropriate support services to low‐income jobseekers.

Exploring Retaliation as a Coping Strategy in Response to Customer Sexual Harassment

Sexual harassment has long been studied as a gendered form of discrimination and a way to assert social dominance. Women working in customer service positions regularly cope with customer sexual harassment (CSH). This paper reports two studies that examine retaliation toward the customer as a way for service workers to both assert power and to cope when faced with CSH. The first study predicted that retaliation would share a common superordinate factor structure with four traditional coping strategies (i.e., social, advocacy seeking, avoidance, and negotiation). The second study hypothesized a latent variable model in which retaliation serves as a buffer between CSH and posttraumatic stress. Additionally, customer power was hypothesized as an antecedent to CSH and retaliation. Both studies used samples of women undergraduate students who were employed at least 10 hours per week as customer service workers in the southeastern U.S. The first study (N = 194) found support for the hypothesized factor structure; retaliation was related to, but distinguishable from more traditional styles of sexual harassment coping. The second study (N = 210) found support for the proposed mediational model. Limitations and future directions for research are discussed.

Differentiating with brand personality in economy hotel segment

The purpose of this study is to explore the applicability of brand personality in the economy hotel segment and whether hotel brand personality could differentiate between similar hotel brands. Courtyard and Hampton Inn are used in this study. The results of this study suggest that brand personality dimensions can be clearly delineated in the economy hotel sector, in consistent with Aaker’s dimensions, ruggedness, competence, excitement, sophistication, and sincerity. Moreover, similar hotel brands can be perceived differently based on their personalities. Additionally, although common brand personality factor structure can be used to describe economy hotel brands in general, specific hotel brand does exhibit some unique dimensions.