What (Exactly) Is A Longitudinal Study?
A Plain-Language Explanation & Definition (With Examples)
By: Derek Jansen (MBA) | June 2020
If you’re new to the world of research, or it’s your first time writing a dissertation or thesis, you’re probably feeling a bit overwhelmed by all the technical lingo that’s hitting you. If you’ve landed here, chances are one of these terms is “longitudinal study”, “longitudinal survey” or “longitudinal research”.
Worry not – in this post, we’ll explain exactly:
What is a longitudinal study?
A longitudinal study or a longitudinal survey (both of which make up longitudinal research) is a study where the same data are collected more than once, at different points in time. The purpose of a longitudinal study is to assess not just what the data reveal at a fixed point in time, but to understand how (and why) things change over time.
The opposite of a longitudinal study is a cross-sectional study, which is a design where you only collect data at one point in time.
Example: Longitudinal vs Cross-Sectional
Here are two examples – one of a longitudinal study and one of a cross-sectional study – to give you an idea of what these two approaches look like in the real world:
Longitudinal study: a study which assesses how a group of 13-year old children’s attitudes and perspectives towards income inequality evolve over a period of 5 years, with the same group of children surveyed each year, from 2020 (when they are all 13) until 2025 (when they are all 18).
Cross-sectional study: a study which assesses a group of teenagers’ attitudes and perspectives towards income equality at a single point in time. The teenagers are aged 13-18 years and the survey is undertaken in January 2020.
From this example, you can probably see that the topic of both studies is still broadly the same (teenagers’ views on income inequality), but the data produced could potentially be very different. This is because the longitudinal group’s views will be shaped by the events of the next five years, whereas the cross-sectional group all have a “2020 perspective”.
Additionally, in the cross-sectional group, each age group (i.e. 13, 14, 15, 16, 17 and 18) are all different people (obviously!) with different life experiences – whereas, in the longitudinal group, each the data at each age point is generated by the same group of people (for example, John Doe will complete a survey at age 13, 14, 15, and so on).
There are, of course, many other factors at play here and many other ways in which these two approaches differ – but we won’t go down that rabbit hole in this post.
What are the advantages of a longitudinal study?
Longitudinal studies and longitudinal surveys offer some major benefits over cross-sectional studies. Some of the main advantages are:
Patterns – because longitudinal studies involve collecting data at multiple points in time from the same respondents, they allow you to identify emergent patterns across time that you’d never see if you used a cross-sectional approach.
Order – longitudinal studies reveal the order in which things happened, which helps a lot when you’re trying to understand causation. For example, if you’re trying to understand whether X causes Y or Y causes X, it’s essential to understand which one comes first (which a cross-sectional study cannot tell you).
Bias – because longitudinal studies capture current data at multiple points in time, they are at lower risk of recall bias. In other words, there’s a lower chance that people will forget an event, or forget certain details about it, as they are only being asked to discuss current matters.
Need a helping hand?
See how Grad Coach can help you...
What are the disadvantages of a longitudinal study?
As you’ve seen, longitudinal studies have some major strengths over cross-sectional studies. So why don’t we just use longitudinal studies for everything? Well, there are (naturally) some disadvantages to longitudinal studies as well.
Cost – compared to cross-sectional studies, longitudinal studies are typically substantially more expensive to execute, as they require maintained effort over a long period of time.
Slow – given the nature of a longitudinal study, it takes a lot longer to pull off than a cross-sectional study. This can be months, years or even decades. This makes them impractical for many types of research, especially dissertations and theses at Honours and Masters levels (where students have a predetermined timeline for their research)
Drop out – because longitudinal studies often take place over many years, there is a very real risk that respondents drop out over the length of the study. This can happen for any number of reasons (for examples, people relocating, starting a family, a new job, etc) and can have a very detrimental effect on the study.
Which one should you use?
Choosing whether to use a longitudinal or cross-sectional study for your dissertation, thesis or research project requires a few considerations. Ultimately, your decision needs to be informed by your overall research aims, objectives and research questions (in other words, the nature of the research determines which approach you should use). But you also need to consider the practicalities. You should ask yourself the following:
- Do you really need a view of how data changes over time, or is a snapshot sufficient?
- Is your university flexible in terms of the timeline for your research?
- Do you have the budget and resources to undertake multiple surveys over time?
- Are you certain you’ll be able to secure respondents over a long period of time?
If your answer to any of these is no, you need to think carefully about the viability of a longitudinal study in your situation. Depending on your research objectives, a cross-sectional design might do the trick. If you’re unsure, speak to your research supervisor or connect with one of our friendly Grad Coaches.
Psst… there’s more (for free)
This post is part of our dissertation mini-course, which covers everything you need to get started with your dissertation, thesis or research project.