1

Steps in

12/20/2022
Mehwish E
observational
studies
Observational study 2

12/20/2022
Mehwish E
 Observational studies are usually
quite straightforward to design and
conduct. Sometimes all you need is a
notebook and pen! As you design
your study, you can follow these
steps.
Step 1: Identify your research 3

topic and objectives

12/20/2022
Mehwish E
 Thefirst step is to determine what
you’re interested in observing and
why. Observational studies are a
great fit if you are unable to do an
experiment for ethical or practical
reasons, or if your research topic
hinges on natural behaviors.
Example: Observational study 4

topic

2
12/20/202
Mehwish E
 You’re interested in the interactions of
toddlers at daycare, specifically how they
deal with big emotions like excitement,
fear, anger, or sadness. Running an
experiment could be challenging for
ethical reasons: toddlers are a vulnerable
population and cannot consent to
participate.
Step 2: Choose your 5

observation type and technique

2
12/20/202
Mehwish E
 In terms of technique, there are a few things to consider:
 Are you determining what you want to observe beforehand, or
going in open-minded?
 Is there another research method that would make sense in
tandem with an observational study?
 Does it make a difference to your analysis if your participants
know you are there?
 If yes, make sure you conduct a covert observation.
 If not, think about whether observing from afar or actively
participating in your observation is a better fit.
 How can you preempt confounding variables that could impact
your analysis?
Example: Observational study 6

approaches

2
12/20/202
Mehwish E
 There are a few ways that you could proceed with your research,
depending on your research topic:
 You could observe the children playing at the playground in a
naturalistic observation.
 You could spend a month at a day care in your town conducting
participant observation, immersing yourself in the day-to-day life
of the children.
 You could conduct covert observation behind a wall or glass,
where the children can’t see you.
 Overall, it is crucial to stay organized. Devise a shorthand for your
notes, or perhaps design templates that you can fill in. Since
these observations occur in real time, you won’t get a second
chance with the same data.
Example: Observational study 7

approaches

2
12/20/202
Mehwish E
 There are a few ways that you could proceed with your research,
depending on your research topic:
 You could observe the children playing at the playground in a
naturalistic observation.
 You could spend a month at a day care in your town conducting
participant observation, immersing yourself in the day-to-day life
of the children.
 You could conduct covert observation behind a wall or glass,
where the children can’t see you.
 Overall, it is crucial to stay organized. Devise a shorthand for your
notes, or perhaps design templates that you can fill in. Since
these observations occur in real time, you won’t get a second
chance with the same data.
Step 3: Set up your 8

observational study

2
12/20/202
Mehwish E
 Before conducting your observations, there are a few things to attend
to:
 Plan ahead: If you’re interested in day cares, you’ll need to call a few
in your area to plan a visit. They may not all allow observation, or
consent from parents may be needed, so give yourself enough time to
set everything up.
 Determine your note-taking method: Observational studies often rely
on note-taking because other methods, like video or audio recording,
run the risk of changing participant behavior.
 Get informed consent from your participants (or their parents) if you
want to record: Ultimately, even though it may make your analysis
easier, the challenges posed by recording participants often make pen-
and-paper a better choice
Step 4: Conduct your 9

observation

2
12/20/202
Mehwish E
 After you’ve chosen a type of observation, decided on your technique, and chosen a
time and place, it’s time to conduct your observation.

 Example: Observational study

 You’ve decided that there is a particular characteristic about the toddlers that you
are interested in. Let’s say you hypothesize that only children are more likely to be
upset when they are dropped off at day care than children with siblings.
 Here, you can split them into case and control groups. The children with siblings
have a characteristic you are interested in (siblings), while the children in the
control group do not.
 You can then attend the morning drop-off at the carpool lane, observing whether the
children with siblings are, indeed, less upset when their caregivers drop them off.
 When conducting observational studies, be very careful of confounding or “lurking”
variables. In the example above, you observed children as they were dropped off,
gauging whether or not they were upset. However, there are a variety of other
factors that could be at play here (e.g., illness).
Step 5: Analyze your data 10

2
12/20/202
Mehwish E
 After
you finish your observation,
immediately record your initial thoughts
and impressions, as well as follow-up
questions or any issues you perceived
during the observation. If you audio- or
video-recorded your observations, you can
transcribe them.
inductive or deductive 11

approach:

2
12/20/202
Mehwish E
 Your analysis can take an inductive or deductive approach:
 If you conducted your observations in a more open-ended
way, an inductive approach allows your data to determine
your themes.
 If you had specific hypotheses prior to conducting your
observations, a deductive approach analyzes whether your
data confirm those themes or ideas you had previously.
 Next, you can conduct your thematic or content analysis.
Due to the open-ended nature of observational studies, the
best fit is likely thematic analysis.
Step 6: Discuss avenues for 12

future research

2
12/20/202
Mehwish E
 Observational studies are generally exploratory in nature,
and they often aren’t strong enough to yield standalone
conclusions due to their very high susceptibility to observer
bias and confounding variables. For this reason,
observational studies can only show association, not
causation.
 If you are excited about the preliminary conclusions you’ve
drawn and wish to proceed with your topic, you may need to
change to a different research method, such as an
experiment.
 13

12/20/2022
Mehwish E
Thank you
for
watching