PsychologyOrbit
Sign in Join

#7 ·

Spot the flaw #7: Dog owners and depression

A past puzzle, with the answer. Try today's puzzle.

What is the flaw in this study?

Causal claim from correlational data. The survey measured dog ownership and depression at one moment, so it can only show that they go together. Many explanations fit: people who are already depressed may be less likely to take on a dog; people with more money, a garden, better physical health or…

A fictional study written for practice (Spot the flaw #7).

Fictional study Health · Leeds, UK

The study

A survey of 2,100 adults in and around Leeds asked whether they owned a dog and included the PHQ-9 depression questionnaire. Dog owners had an average PHQ-9 score of 5.2, against 7.0 for people without a dog, and the gap remained after adjusting for age and sex. The sample closely matched the region's census profile, and the response rate was 68%. The authors write that owning a dog protects against depression and recommend that GPs "prescribe" dog ownership to patients at risk, suggesting local councils could help with the cost of adopting from shelters.

What is the flaw in this study?

  • A Ceiling effect
  • B Causal claim from correlational data The flaw
  • C Underpowered sample
  • D Order effects
Causal claim from correlational data. The survey measured dog ownership and depression at one moment, so it can only show that they go together. Many explanations fit: people who are already depressed may be less likely to take on a dog; people with more money, a garden, better physical health or more free time may be both more likely to own dogs and less likely to be depressed. Adjusting for age and sex leaves these untouched. A causal claim, and certainly a prescription, would need longitudinal data or a trial. With 2,100 people, power is not the problem.

The concept: Correlation does not establish causation

This study is fictional, written for practice. No real study, institution or researcher is described.