Measurement Invariance of the SQWLi Instrument Over Time

Abstract

The SQWLi questionnaire was developed for the long-term measurement of subjectively perceived quality of working life. The aim of this study is to test the instrument’s measurement invariance between 2009 and 2019 and determine whether – despite the modifications made to the instrument over the years – the results remain comparable. Data from eight representative surveys of the economically active population in the Czech Republic were analysed (total N = 6909) using the MG CFA method (configural, metric, and scalar invariance) and the alignment method (approximate measurement invariance). The findings from the MG CFA tests for measurement invariance indicate that the SQWLi instrument achieves configural and metric invariance over time but not full scalar invariance. Achieving a partial scalar invariance would be challenging because of the many high modification indices; therefore, an approximate measurement invariance approach, namely the Alignment Method, was applied. The results suggest that comparisons of latent means across all years can be made. Consequently, it is possible to make meaningful comparisons of overall indices of dimensions (batteries) and of more general domains. However, not all the individual items can be compared. The results confirm that the biggest risk of invariance is caused by conceptual changes to items and by substantial or frequent modifications to item wording. Conversely, the results also show that a conceptual change to an entire dimension may not necessarily cause any problem on the general level, and that a disruption of invariance caused by changes to the range of scales used can be rectified by means of their harmonisation ex post. keywords: SQWLi, subjective quality of working life, exact and approximate measurement invariance, alignment method Sociologický časopis/Czech Sociological Review, 2021, Vol . 57, No . 3: 343–375 https://doi .org/10 .13060/csr .2020 .048 * Acknowledgements: This work was supported by European Structural and Investments Funds, Operational Programme Research, Development and Education, project reg. no. CZ.02.1.01/0.0/0.0/16_013/0001796. ** Direct all correspondence to: Jiří Vinopal, Institute of Sociology, Czech Academy of Sciences, Jilská 1, 110 00 Prague 1, e-mail: Jiri.Vinopal@soc.cas.cz; Kristýna Pospíšilová, Institute of Sociology, Czech Academy of Sciences, Jilská 1, 110 00 Prague 1, e-mail: kristyna. pospisilova@soc.cas.cz. Sociologický časopis/Czech Sociological Review, 2021, Vol. 57, No. 3 344 The SQWLi questionnaire was developed for the long-term measurement of subjectively perceived quality of working life. It is to be used (primarily) to produce time series of various indices of working-life quality and its partial dimensions or domains. A critical part of the observation of any social phenomenon over time is equivalent method. This study seeks to examine whether measurement invariance and consequently also the comparability of data in a time series are adversely affected when changes are made to the instrument of measurement; and if so, how large an effect the various modifications have on measurement invariance. The analyses presented in this paper (1) provide information on the quality of the SQWLi instrument itself and how suitable its data are for creating time series and (2) on a more general level provide an idea of what effect any modifications to the research instrument may have on the quality of the time series. They will also show that invariance can be increased ex post by harmonising the measurement scales. Measuring the (subjective) quality of working life For decades now there have been efforts to observe working-life quality in various contexts and on different levels. At the country level, the quality of working life is one dimension that figures in political debates about the direction of the economy, the labour market and labour regulations, etc. In this area it is one of the macro indicators cited by various parties to policy negotiations, and in this function it must necessarily assume the fullest, most aggregate form possible. At the opposite end of the spectrum, working-life quality is addressed as an element in the employee policies of individual employers, where it figures as one aspect of employee care – for example, in efforts to minimise fluctuation, improve work performance, or maintain social harmony. In such cases it is not about describing or analysing large populations, but rather about closely analysing individual workers for targeted, practical effects. In between these macro and micro levels, there are various motives and methods behind efforts to survey the quality of working life or its alternative or related conceptualisations such as job satisfaction, job stress, working conditions, decent work, etc. [Hoppock 1935; Cranny et al. 1992; Danna and Griffin 1999; Sirgy et al. 2001; Ghai 2008; Judge et al. 2012]. From this perspective, the SQWLi is an instrument of the macro level, where measuring working-life quality has its own long tradition [e.g. Sirgy et al. 2001; Tangian 2005; Lowe 2007; Leschke et al. 2008; Fuchs 2009; Swamy et al. 2015] and is currently also being pursued through many different avenues. The biggest projects that deal directly with working-life quality or that serve as the most common source of data on the subject are the European Working Conditions Surveys (EWCS), European Union Statistics on Income and Living Conditions (EU-SILC), and the European Labour Force Survey (ELFS); but there is also, for example,