Permanent-Transitory decomposition of cointegrated time series via Dynamic Factor Models, with an application to commodity prices

We propose a cointegration-based Permanent-Transitory decomposition for non-stationary Dynamic Factor Models. Our methodology exploits the cointegration relations among the observable variables and assumes they are driven by a common and an idiosyncratic component. The common component is further split into a long-term non-stationary and a short-term stationary part. A Monte Carlo experiment shows that incorporating the cointegration structure into the DFM leads to a better reconstruction of the space spanned by the factors, compared to the most standard technique of applying a factor model in differenced systems. We apply our procedure to a set of commodity prices to analyse the comovement among different markets and find that commodity prices move together mostly due to long-term common forces; while the trend for the prices of most primary goods is declining, metals and energy exhibit an upward or at least stable pattern since the 2000s.

Psychometric Evaluation of the Malay Version of the Family Adaptability and Cohesion Evaluation Scale III for Malaysian Adolescents

The Family Adaptability and Cohesion Scale III (FACES-III) has been widely used to measure an individual’s family functioning in terms of cohesion and adaptability. In Malaysia, the FACES-III has been translated into the Malay language for the community, but its psychometric properties in this context remain unknown. Thus, the purpose of this research is to examine the psychometric properties of the Malay version of the FACES-III in 852 adolescents attending secondary schools in Kuala Lumpur, Malaysia. Data were randomly split into two halves: the exploration sample and the validation sample. Exploratory factor analysis was conducted on the exploration sample and a two-factor model was discovered after removing nine items that showed low factor loading. Then, confirmatory factor analysis was conducted on the validation sample to compare the one-factor models, two-factor models, and three-factor models. Results showed that the 11-item two-factor model (FACES-III-M-SF) was superior to the other competing models. Both the exploratory and confirmatory factor analyses replicated the two-factor structure of the original version of FACES-III. The reliability of the overall scale was consistently good, but the subscale results were mixed. This suggests that researchers should use the overall score, but not the subscale scores, in analyses.

Motor Skills Development: Peculiarities of Programmed Teaching of Acrobatic Exercises to Girls Aged 15

The purpose of the study was to determine the peculiarities of programmed teaching of a cartwheel to girls aged 15. Material and methods. The study participants were 20 girls aged 15. The children and their parents were fully informed about all the features of the study and gave their consent to participate in the experiment. To solve the tasks set, the following research methods were used: study and analysis of scientific and methodological literature; pedagogical observation, timing of training tasks; pedagogical experiment, methods of mathematical statistics, factor analysis, nearest neighbor analysis. Results. The analysis of similarities revealed that the program components are interrelated. Series of training tasks ІV, V and VI have the highest correlation. Series of training tasks І, ІІІ and IV are combined into one group and provide conditions for teaching girls aged 15 the cartwheel. Conclusions. The study obtained factor models of the teaching program, which explain 70.645% and 68.468% of the variation of results. The models characterize the two-factor structure of the teaching program where training tasks are closely connected with one another, which indicates their effective selection. It was found that the tasks of series I, II and III, and the tasks of series III, IV and V are most connected with one another, which confirms the combined nature of the method of algorithmic instructions. Optimization of the number of repetitions of the entire exercise (series of tasks VI) depends on the amount of exercises of the second and fifth series of training tasks.

VALIDATING DSGE MODELS WITH SVARS AND HIGH-DIMENSIONAL DYNAMIC FACTOR MODELS

A popular validation procedure for Dynamic Stochastic General Equilibrium (DSGE) models consists in comparing the structural shocks and impulse-response functions obtained by estimation-calibration of the DSGE with those obtained in an Structural Vector Autoregressions (SVAR) identified by means of some of the DSGE restrictions. I show that this practice can be seriously misleading when the variables used in the SVAR contain measurement errors. If this is the case, for generic values of the parameters of the DSGE, the shocks estimated in the SVAR are not “made of” the corresponding structural shocks plus measurement error. Rather, each of the SVAR shocks is contaminated by noncorresponding structural shocks. We argue that High-Dimensional Dynamic Factor Models are free from this drawback and are the natural model to use in validation procedures for DSGEs.

Factor Structure of the Memory for Intentions Test (MIsT) in Samples of Older Adults and People with HIV Disease

Objective: The Memory for Intentions Test (MIsT) is a clinical measure of prospective memory that has strong evidence for convergent, discriminative, and ecological validity. This study evaluates the latent structure of the MIsT among two samples who may experience prospective memory deficits: older adults and people living with HIV disease. Participants and Methods: Study participants included 303 people with HIV disease (ages 18-67) and 267 community-dwelling older adults (ages 50-91). Confirmatory factor analyses of the MIsT were conducted separately in each sample. We evaluated a one-factor model, as well as three two-factor models with the MIsT items loading onto each factor based on cue type, delay interval, or response modality, respectively. Results: The one-factor model provided the best (and most parsimonious) fit to the data in both study samples. All two-factor models also demonstrated good fit statistics, although correlations between the two factors in each model were high and none of the two-factor models provided a significantly better fit than the one-factor model. Conclusions: Results provide support for the factor structure of the MIsT in older adults and people with HIV disease. A total score for the MIsT provides the most parsimonious solution, although available evidence and theory also support the use of subscales (e.g., cue type). Future studies of the MIsT would be useful to determine its psychometrics in different clinical populations.