| Main Page - | Survey Content - | Notes and definitions - | Methodology - | Data products - | Data services - | Publications - | More information |
Description of a longitudinal survey
Longitudinal respondents
Longitudinal research themes
There are two types of recurring surveys: in one you interview a new cross-section of people each time, as most surveys do, while in the other, you interview the same people over a period of time, as in a longitudinal survey.
The advantage of cross-sectional surveys is that they are generally more representative of the population, and they reveal the levels and trends of income or labour for the whole population or its sub-groups. But such surveys do not answer questions about changes or fluctuations faced by individuals or families: What are the fluctuations in people's labour, income or family characteristics at the micro level? What events tend to coincide? How often do people change jobs or get laid off, with what impact on their total family income? How many families split or join together in a given time period? What proportion of households are "persistently poor" year after year, and what makes it possible for others to emerge from periods of low income? These and many other similar questions can only be answered by a longitudinal survey.
In a survey like SLID, the focus extends from static cross-sectional measures to a whole range of longitudinal events: transitions, durations, and repeat occurrences of people's financial and work situations. These yield a number of possible longitudinal research themes.
Paradoxically, the comprehensive data that make SLID so valuable, also makes it more complex for Statistics Canada to maintain the confidentiality of respondents. In order to comply with the strict confidentiality provisions of the Statistics Act. SLID longitudinal data are made available through special modes of dissemination (see data services).
Longitudinal respondents are the people belonging to the selected households when a new six-year panel of respondents is introduced. These respondents are interviewed twice a year whether they stay, move away or split up. New joiners, called cohabitants in SLID, are interviewed as long as they continue to live with a longitudinal respondent. That's because the family make-up and family income situation of longitudinal respondents is of key interest. Interviewing cohabitants also improves the quality of cross-sectional estimates.
People aged 16 and over are asked questions on labour, income and education. Children present in the original households are also followed for the full six years. When these children turn 15, they complete a preliminary interview. When they turn 16, they join other longitudinal respondents in completing both labour and income interviews. On the other hand, people aged 70 years and over are not asked labour-related questions.
Discussions with prospective users and insights from other panel surveys with similar content helped identify seven longitudinal research themes that illustrate some of the survey's potential. Depending on the angle of study, it may make sense to use individuals, jobs, employers, or spells (of unemployment, for example) as the unit of analysis. SLID covers up to six jobs and six employers that a person might have during each calendar year.
Labour force activity data usually show total employment, unemployment and inactivity. Changes in employment and unemployment between two months or two years are calculated by comparing these totals. SLID, however, shows the flow into each type of labour force activity experienced by individuals. Flow data of persons or jobs are possible by industry, occupation, or worker characteristics. Durations of spells may be of interest too; for example, to what extent are long spells of unemployment experienced by the same individuals? What are the major determinants? Why do people withdraw from the labour market, and what precedes a transition into self-employment?
Using SLID data, one can study major labour market transitions associated with particular stages of the life cycle, such as transitions from school to work, transitions from work to retirement and work absences taken to have or raise children. What are typical life-cycle patterns in Canada today? What are the subsequent activities of high school drop-outs, and what precedes a return to school?
SLID supports research in such areas as wage differences between men and women, under-employment, occupational mobility, earnings growth over a period of several years, and wage and hours polarisation among the working population.
How stable is family income? What proportion of families experience a significant improvement or deterioration in income between two points in time? What are the determinants of these changes? How important are changes in family composition (divorce, remarriage) in explaining a change in financial well-being.
This research theme concerns the prevalence and duration of spells of low income and the factors related to families moving into or out of low income. Researchers can isolate and characterize a "persistently poor" sub-population, as is done using longitudinal surveys in other countries. There is also interest in looking at receipt of employment insurance benefits, social assistance and other government transfers in relation to flows into and out of low income.
Central to SLID's demographic potential is information on family relationships, which make it possible to accurately identify blended and multi-generational families. The longitudinal aspect permits the study of life events and their determinants or impact. For example, what are the family's economic circumstances preceding a marriage break-up, and what are they for each spouse and child following a separation?
It is possible to view educational activity and attainment in the evolving context of an individual's other activities and family circumstances. What are the family circumstances of young people pursuing post-secondary education? How much do high school or postsecondary students combine work and school?