Main conclusions and significance of the results
The CENSOPAS-COPSOQ presented evidence of validity and reliability for the medium version and the short version, therefore, its use could be recommended in the Peruvian population to assess occupational psychosocial risks. The quality of the fit indices supports the proof of validity by internal structure, while the internal consistency coefficients of alpha and omega support the reliability of the measure for the two versions. Additionally, it has been identified that the medium and short versions of the CENSOPAS-COPSOQ are closely related, so it is unlikely that information will be lost when using a shorter version.
However, the “psychological demands at work” dimension in the medium version presents an insufficient adjustment, but good levels of reliability. Therefore, the results of this dimension in particular should be taken with caution in the average version. Also, some models have adequate CFI values but inadequate RMSEA values. As we have few degrees of freedom and the sample is small compared to the number of parameters used, it is advisable to consider only the CFI values [25, 26]. Therefore, we consider the goodness-of-fit index values to be adequate, suggesting an adequate fit. Moreover, some CENSOPAS-COPSOQ sub-dimensions were identified as having overestimated values and others as underestimated since they explain a small proportion of the total variance of the construct. This is normal in multifactorial instruments that assess a variable as complex as psychosocial risks. Therefore, although there are some problematic sub-dimensions in the instrument, this does not detract from the overall rating of the instrument.
Compare results with existing literature
Different studies have evaluated the measurement properties of the COPSOQ, using heterogeneous analysis methods and providing results that included different factorial solutions both in number of items and in number of dimensions.
Two studies were identified that present inadequate analysis methods, which suggest unstable factorial solutions. In Spain, the validity of the COPSOQ-ISTAS-21 among workers was analyzed by factor analysis with varimax rotation, and the internal consistency of the model was assessed by the Alpha coefficient [27]. However, this rotation method used was not adequate because it assumed that the items and dimensions are independent, which does not occur within psychological variables since they are closely related to each other. [28], even more so in an instrument of such factorial complexity (i.e. with a large number of dimensions and sub-dimensions). In this Spanish study, 27 subdimensions were found, possibly due to the use of an analysis method that did not conform to the nature of the variables (categorical-ordinal). The short version of the instrument they presented had 38 elements [27], which represents 7 items more than the one presented in our study. On the other hand, a study carried out in Brazil validated the average version of the COPSOQ-ISTAS-21 II among academics [29]. In this study, the authors state that they used confirmatory factor analysis, exploratory factor analysis and internal consistency reliability analysis. [29], managing to identify a factorial model composed of 21 sub-dimensions comprising 70 items. However, in the analysis plan of their paper, they state that they used principal component analysis, varimax rotation, and the number of dimensions was determined with the eigenvalue. This method of analysis is not recommended because it is very subjective and may overestimate the number of dimensions [28].
Two other studies identified four-dimensional patterns, which diverges from our results where six dimensions were identified in the Peruvian population. A Persian COPSOQ study evaluated the short version of the instrument [30], finding through confirmatory factor analysis a total of 4 dimensions (32 items): quality of leadership, social support from supervisors, rewards, fairness and respect, trust and predictability (dimension 1), self-rated health status, burnout, stress , work – family conflict and emotional demands (dimension 2), job meaning, work commitment, work influence and role clarity (dimension 3) and offensive behavior (dimension 4). Unlike the CENSOPAS-COPSOQ (our study), the Persian study by Aminian et al. groups the dimensions to obtain a more stable factorial solution. However, conceptually, they retain the same indicators as our study. On the other hand, a study validated the French version of the COPSOQ based on the short version in Danish language [31]. By exploratory factor analysis, only 4 dimensions were presented (“interpersonal relations and leadership”, “influence and development”, “tension”, and “demands”) with 32 items. This version is similar in the number of items that are proposed in our study for the short version.
Two other studies argued that a five-dimensional version is more stable compared to the other factorial solutions. One of them adapted the medium version of the COPSOQ to Persian and concluded that the items were grouped into 20 sub-dimensions [32], as in our model. However, in this study, these sub-dimensions were grouped into only 5 dimensions (Type of production and tasks, Work organization and content, Interpersonal relations and leadership, Work-individual interaction, and Health and well-being) [32]. Similarly, a study that assessed the validity of the COPSOQ among professional drivers in Spain also reported a better factorial solution in 5 dimensions (“Demands”, “Influence and development”, “Interpersonal relations and leadership”, “Insecurity of the ‘Job’ and ‘Strain’)[33]. These two studies present similar results between them and by what our research has identified since their dimensions are very similar to those proposed in our study.
A Chilean study performed a validity and reliability analysis for the short version of the COPSOQ-ISTAS-21, which they called SUSESO-ISTAS21 [34]. This study proposed a factorial structure of 5 dimensions (“Psychological demands”; “Development of work and skills”; “Social support in the company and quality of leadership”; “Remuneration” and “Double presence”) with a total of 20 items. However, this structure composed of 5 dimensions did not present adequate fit indices (CFI = 0.795; TLI = 0.762; RMSEA = 0.080) [21]. Despite validity issues, it achieved adequate internal consistency coefficients (α > 0.70) [23]. Therefore, although the instrument shows evidence of reliability, its factor structure is unstable and a five-dimensional correlated solution might not be the most appropriate.
The COPSOQ presents several studies that prove its convergent validity; however, the versions of the instrument used being very heterogeneous, a direct comparison is not possible. Our study identified a very high relationship between the medium version and the short version of the instrument, suggesting that the instrument does not lose information by eliminating items. However, since the medium version has the same elements as the short version, the data would be interdependent. Despite this, when evaluating the relationship with the one-dimensional models, a moderate correlation is always identified, so we consider that no information would be lost from one version to another.
The COPSOQ studies presented heterogeneous factorial structures and each obtained different dimensions and numbers of items, depending on the characteristics of their populations. Additionally, measurement properties have been assessed in various ways such as exploratory and confirmatory factor analyses, and some studies have used poorly recommended analytical methods that could lead to unstable results. [27, 29]. It should be noted that our study provides for the use of second-order models, which makes it possible to obtain an overall score by dimension and considers the 20 sub-dimensions within its structure. Therefore, we consider that our study provides a new approach to the available evidence of COPSOQ-ISTAS21 and is renamed CENSOPAS-COPSOQ.
The evidence presented corresponds to the second edition of the COPSOQ; however, it should be noted that the third edition of the COPSOQ was published in December 2019 [35]. The third edition adds a set of mandatory basic elements that must be included in all versions of the instrument (short, medium or long), regardless of the country or context that adapts the scale. This will allow future studies conducted with the third edition of the COPSOQ to have a consistent set of items across all versions, allowing comparisons to be made between countries and versions. This represents an important advance for the measurement of psychosocial risks because it will make it possible to know the most appropriate items in the context while respecting a set of mandatory items.
Strengths and limitations
Our CENSOPAS-COPSOQ study had a representative sample of workers from different economic activities and regions of Peru, allowing the representativeness of workers with different characteristics. However, this study is not without limitations. First, evaluations using two-factor models, or ESEM, could not be carried out, their sample size being insufficient to make the models converge; thus, there might be other factorial solutions that might be more stable using these models. Secondly, the CENSOPAS-COPSOQ collects information on the psychosocial risks at work perceived by the worker, however, an identification of the psychosocial risk at work has not been carried out, to corroborate the worker’s perception. Third, it was not possible to apply other instruments that assess occupational psychosocial risks, which allows other evidence of validity to be presented as evidence of relationship with other CENSOPAS-COPSOQ variables (discriminant validity ). Fourth, an analysis of invariance by gender, economic sector and natural region was attempted, but was not possible because the assumptions of the analysis were not met (not all participants not checked all answer options) [36].
Implications for public health and decision-making
The COPSOQ is an instrument used in different contexts and countries to assess psychosocial risks at work. It is therefore a valid and reliable tool that would guide public policies and periodic evaluations for work centers of 25 people or less with the short version (31 items), as well as for work centers more than 25 workers with the average version. (69 items). Other countries have used the COPSOQ to design and evaluate their labor policies [10]therefore, this instrument can be used in Peru as a tool to guide decision-making in occupational and occupational health.
The CENSOPAS-COPSOQ could be used to assess the effect of organizational or work interventions since it would make it possible to see whether the safety and risk management strategies applied in the workplace have a positive or protective effect on the health of workers. , carrying out evaluations before and after the interventions. Therefore, the CENSOPAS-COPSOQ joins other instruments adopted in the Peruvian context to assess aspects of public health work [37, 38].
