Research design and reporting

Question 1

Cross-sectional versus longitudinal

Answer 1

• Cross-sectional designs capture data at one point in time.
• Longitudinal designs capture data at more than one point in time.

Question 2

Experimental versus observational

Answer 2

• Observation designs do not manipulate any variables.
• Experimental designs manipulate a variable (termed condition); participants
  are assigned to one condition at random.

Question 3

Quasi-experimental designs

Answer 3

Quasi-experimental designs do not manipulate any variables participants are assigned to a condition based on non-random criteria (e.g. gender).

Question 4

Within-subject versus between-subject

Answer 4

• Between-subject designs collect data from participants relative to one condition.
• Within-subject designs collect data from participants relative to more than one condition (usually all conditions). This design is also called repeated measures. Same measure taken more than once from each subject.

In a within-subject design, each participant experiences all experimental conditions, The data comparison occurs within the group of study participants, and each participant serves as their own baseline, whereas, in a between-subject design, different participants are assigned to each condition, with each experiencing only one condition then compared to a control group.

• A design can be mixed, with both between- and within-subject assessments.

Question 5

Sampling

Answer 5

Population-based sample
Representative of the population.
E.g. random sample of Medicare numbers.

Convivence samples
Not representative of the population.
E.g. clinic-based or through social media advertisement.

Stratification
Sampling base on pre-defined groups.
E.g. equal numbers of 5-9, 10-14 and 15-19 year olds.

Question 6

Methods to Collect data from your sample

Answer 6

In the field
E.g. Researchers base themselves within a hospital.

In the laboratory
E.g. Researchers ask participants to visit a university campus.

Survey
E.g. Researchers ask participants to complete an online survey.

Methods need to be appropriate to address your research aim.
Sampling biases should always be recognised and attenuated where possible.

Question 7

Psychology has a WEIRD sampling problem

Answer 7

• The vast majority of published psychological research is on western,
  educated, industrialised, rich, and democratic (WEIRD) samples.
• Generalisation is limited when using these samples. They are not the
  norm.
• WEIRD populations represent as much as 80 percent of study participants,
  but only 12 percent of the world’s population.

Question 8

Experimenter bias

Answer 8

The basic idea is that the experimenter, despite the best of intentions, can accidentally end up influencing the results of the experiment by subtly communicating the “right answer” or the “desired behaviour” to the participants.

Question 9

Demand effects and reactivity

Answer 9

It’s almost impossible to stop people from knowing that they’re part of a psychological study. And the mere fact of knowing that someone is watching or studying you can have a pretty big effect on behaviour.

Question 10

Operationalise key terms

Answer 10

• You must define all key variables/factors.
• Links what you are measuring to the variable/factor you are interested in, which is typically theoretical.
• Define all terms key to your aim and hypotheses.

Question 11

Research question versus research aim

Answer 11

• Same, just one is a question.
• Aim: To investigate the association between social engagement and
  depression.
• Research question: What is the association between social
  engagement and depression?

Question 12

Hypothesis

Answer 12

• Specific directional statements (positive or negative) that relate to key constructs. Prediction.

Aims and hypotheses shape the entire research report. They dictate what literature you should review in your Introduction, the method you employ, the statistics you run, the results you report, and the narrative of the Discussion. Each section of a research report should directly relate to the aim and hypothesis.

Question 13

Research methods appropriate for variables

Answer 13

Independent and dependent variables = Experimental and
quasi-experimental
research

Predictor and outcomes variables = Observational
research

Question 14

Independent and dependent variables versus Predictor and outcome variables

Answer 14

DV and outcome = is being measured in relation to the predictor; usually
an exposure.

IV and predictor = is a factor of interest and is being measured. Manipulated in an experiment.

Often, whether a variable is a predictor or outcome variable depends on the
research aim/narrative.

Question 15

Bradford Hill criteria for causation

Answer 15

A group of nine principles that can be useful in establishing epidemiologic evidence of a causal relationship between a presumed cause and an observed effect.

Strength (effect size): A small association does not mean that there is not a causal effect, though the larger the association, the more likely that it is causal.

Consistency (reproducibility): Consistent findings observed by different persons in different places with different samples strengthens the likelihood of an effect.

Specificity: Causation is likely if there is a very specific population at a specific site and disease with no other likely explanation. The more specific an association between a factor and an effect is, the bigger the probability of a causal relationship.[1]

Temporality: The effect has to occur after the cause (and if there is an expected delay between the cause and expected effect, then the effect must occur after that delay).

Biological gradient (dose–response relationship): Greater exposure should generally lead to greater incidence of the effect. However, in some cases, the mere presence of the factor can trigger the effect. In other cases, an inverse proportion is observed: greater exposure leads to lower incidence.[1]

Plausibility: A plausible mechanism between cause and effect is helpful (but Hill noted that knowledge of the mechanism is limited by current knowledge).

Coherence: Coherence between epidemiological and laboratory findings increases the likelihood of an effect. However, Hill noted that “lack of such [laboratory] evidence cannot nullify the epidemiological effect on associations”.

Experiment: “Occasionally it is possible to appeal to experimental evidence”.

Analogy: The use of analogies or similarities between the observed association and any other associations.

Some authors[3] consider, also, Reversibility: If the cause is deleted then the effect should disappear as well.

Question 16

Stanford marshmallow experiment

Answer 16

A study on delayed gratification in 1970 led by psychologist Walter Mischel, a professor at Stanford University.

In follow-up studies, the researchers found that children who were able to wait longer for the preferred rewards tended to have better life outcomes, as measured by SAT scores,[2] educational attainment,[3] body mass index (BMI),[4] and other life measures.[5] A replication attempt with a sample from a more diverse population, over 10 times larger than the original study, showed only half the effect of the original study. The replication suggested that economic background, rather than willpower, explained the other half.

Question 17

Population-based sample

Answer 17

Represents the structure of the underlying population

Question 18

Selection bias

Answer 18

The sample selected for a study or analysis is not representative of the population intended to be analyzed. This can happen due to non-random selection methods or self-selection. As a result, the findings may be skewed and not generalizable to the broader population.

Question 19

Fear bias

Answer 19

Fear bias arises when fear influences individuals’ behavior, thoughts, or responses in ways that skew results. It can lead people to avoid certain situations or alter their responses in surveys or studies due to fear of negative outcomes.

Question 20

Healthy bias

Answer 20

Healthy user bias occurs when healthier individuals are more likely to engage in certain behaviors or use certain products, making it difficult to isolate the effects of those behaviors or products.

Question 21

Under coverage bias

Answer 21

Undercoverage bias happens when some groups in the population are inadequately represented in the sample. This leads to incomplete data, making the results less reliable or valid for the entire population.

Question 22

Within-Subject Study

Answer 22

Same participants are tested across all experimental conditions.

Differences between conditions are measured within each participant.

Reduces individual differences
as a source of error since participants act as their own control.

Fewer participants are needed because the same individuals are tested in multiple conditions.

Question 23

Between-Subject Study

Answer 23

Different participants are assigned to different experimental conditions.

Differences between conditions are measured between different groups of participants.

Eliminates concerns about carryover effects because participants experience only one condition.