Ethical and conceptual considerations
What are some ethical considerations that researchers need to take into account when conducting cross-cultural research? How do these considerations differ from those in other types of research?
How can cultural differences in values and beliefs impact the ethical considerations in cross-cultural research? What are some examples of cultural differences that researchers need to be aware of?
How can researchers ensure that their cross-cultural research is ethical, while still being scientifically rigorous and producing valuable insights? What are some best practices or guidelines that researchers can follow?
Psychology starts with a question about how people think or behave.
How does early childhood experience affect personality and behaviour?
What are the effects of social media on self-esteem?
Why do some people believe in a God or gods and others do not?
Why are some people motivated to sacrifice for others?
Does marriage make people happy?
How do early childhood experiences differ across cultures, and how do these differences impact personality and behavior development?
Are there cultural differences in the way social media use affects self-esteem and body image?
How do cultural and religious beliefs shape individual attitudes towards the concept of God or gods?
What are the cultural and individual factors that motivate people to engage in acts of altruism or sacrifice for others, and how do these factors vary across cultures?
Are there cultural differences in the factors that contribute to marital satisfaction and happiness, and how do cultural expectations and values surrounding marriage play a role?
“Ask my married parents if they are happy.”
“Consult a palm reader.”
Assertion: “Yes marriage always makes people happy”; “No marriage can’t possibly make anyone happy”
Intuition: “It depends on the gender of the individual. Men are always happier in marriage, while women are never happier.”
Intuition: “It depends on the cultural background of the individuals. Couples from Western cultures are always happier in marriage, while couples from Eastern cultures are never happier.”
Conduct a literature review of previous research on the association between marriage and happiness, including cross-cultural studies that compare different cultural attitudes and practices regarding marriage and their relationship to happiness.
Conduct a survey of a large and diverse sample of individuals to assess their happiness levels, as well as their marital status assess the relationship.
What would this tell us?
What would this not tell us?
Definitions:
How might this go wrong?
Construct: e.g. Happiness - a subjective experience of positive emotions, such as joy, contentment, and satisfaction with life/
Item: A question or statement used to measure an aspect of happiness. Example: “I feel content with my life.”
Scale: A collection of items designed to measure a construct. Example: a happiness scale might consist of items rated on a Likert-type scale, with an overall score reflecting the level of happiness being measured. Example:
Part 1: Measurement matters
Suppose we are confident in measurement, administer survey, and find an relationship.
Does marriage cause happiness cross culturally?
This doesn’t work if there is reverse causation: Regression coefficient for Marriage (M) is biased.
## Simulate data
set.seed(123)
sim_fun_B = function() {
n <- 1000
A <- rnorm(n, 1) # simulates age,
H <- rnorm(n , A) # simulates happy as function of age
M <- rnorm(n , A) + .2 * H # simulate marriage as a function of age + happiness
# Simulate dataframe from function
simdat_B <- data.frame(
A = A,
H = H,
M = M)
# model in which marriage "predicts" happiness controlling for age
sim_B <- lm(H ~ M + A, data = simdat_B)
sim_B # returns output
}
# Replication 100 times
r_lm_B <- NA
r_lm_B = replicate(100, sim_fun_B(), simplify = FALSE )
# print model results
parameters::pool_parameters(r_lm_B)# Fixed Effects
Parameter | Coefficient | SE | 95% CI | Statistic | df | p
------------------------------------------------------------------------------
(Intercept) | 4.12e-03 | 0.06 | [-0.12, 0.13] | 0.07 | 220.99 | 0.947
M | 0.19 | 0.04 | [ 0.10, 0.27] | 4.42 | 234.19 | < .001
A | 0.77 | 0.07 | [ 0.64, 0.91] | 11.17 | 211.13 | < .001Week 7: Causal inference: Causal Graphs(Joseph Bulbulia). How to diagnosis sources of confounding and what to do about it.
Week 8: Causal inference: Target Trial Emulation (Joseph Bulbulia). How to emulate an experiment with observational data and how to identify the modification of effects by cultural groups.
Week 9: Causal inference: Reconsidering measurement and selection biases (Joseph Bulbulia). A discussion of problems in standard approaches to measurement.
Week 10 Causal inference: Cross-Cultural Experiments (Joseph Bulbulia & Guests). For whom to our results generalise?
Week 11 Ethics and Ownership (Joseph Bulbulia & Guests). Can causal inference help us to improve ethical reasoning? Why is data protection important? How do the ethics of data protection relate to the ethics of open science?
Week 12 Future Horizons (Joseph Bulbulia, Torven, Inkuk):
Key Concepts ::: {.fragment .highlight-red} 1. Measurement = quantification 2. Validity = accuracy 3. Confounder = interference :::
For an account of the history of measurement in psychological research, see: (Briggs 2021)
For an account of key concepts and current debates in psychometrics, see: (Bandalos 2018)
For an account of special measurement problems that arise in cross-cultural research, see: (Van de Vijver and Leung 2021)
For an accessible introduction to causal inference and its history see: (Pearl and Mackenzie 2018)