W7: Longitudinal designs (structural equation modelling)

Question 1

Possible MCQ Question:

What is one statistical advanced method that we can use to test things longitudinally?

Answer 1

Structural equation modelling

Question 2

Longitudinal designs are … (2)

Answer 2

Used to study changes across the life span by observing same participants at different points in time

It assess same variables at each timepoint

Question 3

The length of the longitudinal design study can vary

Answer 3

Based on design or funds (longitudinal designs are expensive)

Question 4

Longitudinal designs are often

Answer 4

survey-based (e.g., Likert scale questions)

Question 5

Longitudinal designs prone to

Answer 5

many threats of internal validity (e.g., maturation)

Question 6

Longitudinal designs require

Answer 6

Substantial resources and time to complete

Question 7

Longitudinal design (issues)

What is time lag?

Answer 7

Distance between timepoints

Question 8

Longitudinal design (issues)

Too much time lage can

Answer 8

causes issues

Question 9

Longitudinal design (issues)

Issue with time lag - frequency

Answer 9

How frequent should we measure?

Question 10

Longitudinal designs (issues) - Attrition (3)

Answer 10

• Participants dropout over time
  
  • Loss of interest
  • Losing contact with researcher (e.g pps changing phone number, home address)

Question 11

Longitudinal design (issues) - Attrition - how do we address this?

Answer 11

Money for the participants to engage in the study/Amazon vouchers

Question 12

Longitudinal designs (issues) - threats to the internal validity of long study due to - (3)

Answer 12

1. Maturation effects (naturally occurring process)
2. Historical effects (events that are outside of our control) - e.g., COVID-19
3. Practice effect (improvement on test due to repeated experience)

Question 13

How do we test longitudinal studies? (repeated-measure design)

Answer 13

Repeated measures t-test and ANOVA

Question 14

More complex longitudinal design requires more robust statistics (than repeated measure t-test and ANOVA)

such as… (3)

Answer 14

1. Mediator/mechanism (3rd var)
2. Understand complex pathways to poor health
3. Enter… Structural equation modelling!

Question 15

Structural equation modelling - Most longitudinal studies utilise survey designs (7)

Answer 15

Scales which include several items

Rated using Likert scales

• 1 (Strongly disagree)
• 2 (Disagree)
• 3 (Neither agree or disagree)
• 4 (Agree)
• 5 (Strongly agree)

Question 16

Structural equation modelling - what are construct?s

Answer 16

Hypothetical variable we are trying to capture

Question 17

Structural equation modelling

Construct limits (2)

Answer 17

Almost impossible to actually measure directly

Assess variables which estimate the construct

Question 18

Structural equation modelling -=

We can capture the constructs through… (4)

Answer 18

Self-report

Behavioral

Physiological

Etc

Question 19

Structural equation modelling - construct with its operational definitions

Answer 19

• E.g., may measure aggression (construct) through behavioural observations (e.,g operational definition)

Question 20

Structural equation model tests

Answer 20

“fit” of each item on construct

Question 21

Structural equation model estimates a

Answer 21

“weight” for each path - how much each item predicts the construct

Question 22

Structual equation model interprets the weight as a

Answer 22

standardized regression coefficient (beta) or correlation

Question 23

Structural equation modelling high and low weights (3)

Answer 23

Higher weights = good fit!

Lower weights = poor fit!

The better the fit, the more predictive that item is of the construct!

Question 24

Structural equation modeling

Answer 24

• 3 best predictors of anxiety is 1, 3 and 5 (green)
• Red is maybe not best predictor of generalised anxiety - tells us maybe not measuring anxiety

Question 25

Structural equation modelling

Using constructs to predict .. constructs (2)

Answer 25

Once we have items that nicely fit onto a construct, we can then use it to predict other constructs with good fitting items

Can create pathways based on evidence

Question 26

Example of pathways (3) with different constructs

Answer 26

Question 27

Structural equation modelling

From theory to testing… (2)

Answer 27

Structural equation modelling often used to test theories

Provides evidence on whether theories are accurate or need revision (whether pathway someone theorised exists or not)

Question 28

Racism and health

Gibbons et al. (2014) - PROCEDURE (3)

Answer 28

Longitudinal study with 680 female Black Americans

Assessed 4 times over several years

Used structural equational modelling!

Question 29

Racism and health

Gibbons (2014) - Measures (5)

Answer 29

1. Perceived discrimination
2. Internalizing factors (depression, anxiety, distress)
3. Externalizing factors (hostility, anger)
4. Physical health
5. Substance use (alcohol)

Question 30

Gibbon et al. (2014)

Structural equation modelling (3)

Answer 30

Use of evidence and theory to form a structural equation model

Evidence shows that..

Internalizing (distress) predictive of poor physical health

Externalizing (hostility) predictive of greater alcohol use

Question 31

Gibbon et al. (2014)

If… (2)

Answer 31

If racism leads to distress (e.g., depression, anxiety)… - makes them have poor physical health

If racism leads to hostility and anger…leads to greater alcohol use

Question 32

Gibbons et al. (2014) findings (4)

Answer 32

Racism leads to distress which predicts poorer physical health

However… while racism promotes more hostility, this does not necessarily lead to greater rates of substance use!

• Contrary to the proposed model
• Not good enough fit!

Question 33

Gibbons et al. (2014) - Limitations

Answer 33

Men are on average more hostile and also tend to have more problematic alcohol use than women

Could explain why the pathway of Time point 3 of hostility between Time 4 problematic drinking use