It’s fairly easy to identify the obvious cases where correlation is mistaken for cause.  But that’s not enough for a nurse or a critical thinker.  We need to evaluate some causal hypothesis that have actual evidence to back them up, and we need to determine whether that evidence is sufficient.  How certain can we be of a causal relationship given the best available data? 

So, let’s take this claim:  Having a dog is good for your health.  

First, that’s a generalization.  Not everyone is going to benefit from having a dog.  And we’re being a little vague on what “good health” means.  But we have some hard data we can look at.  Here’s the description of  a 2019 Swedish study from the researchers:

“We used the Swedish National Patient Register to identify all patients aged 40 to 85 presenting with an acute myocardial infarction (n=181?696; 5.7% dog ownership) or ischemic stroke (n=154?617; 4.8% dog ownership) between January 1, 2001 and December 31, 2012. Individual information was linked across registers for cause of death, sociodemographic, and dog ownership data. We evaluated all-cause mortality and risk of recurrent hospitalization for the same cause until December 31, 2012. Models were adjusted for socioeconomic, health, and demographic factors at study inclusion such as age, marital status, the presence of children in the home, area of residence, and income, as well as all registered comorbidities and hospitalization for cardiovascular disease in the past 5 years. Dog owners had a lower risk of death after hospitalization for acute myocardial infarction during the full follow-up period of 804?137 person-years, with an adjusted hazard ratio (HR) of 0.67 (95% CI, 0.61 to 0.75) for those who lived alone, and HR of 0.85 (95% CI, 0.80 to 0.90) for those living with a partner or a child. Similarly, after an ischemic stroke, dog owners were at lower risk of death during the full follow-up of 638?219 person-years adjusted HR of 0.73 (95% CI, 0.66 to 0.80) for those who lived alone and HR of 0.88 (95% CI, 0.83 to 0.93) for those living with a partner or a child. We further found an association of dog ownership with reduced risk of hospitalization for recurrent myocardial infarction (HR, 0.93; 95% CI, 0.87 to 0.99). “

Not so simple to make sense out of, is it?  Or to see immediately how strong or weak this study might be?  So, let’s use the chapter 11 concepts.  Ask yourself, is this a controlled experiment or an observational study?  Prospective or retrospective?  What are the confounding variables that would be impossible to account for in this type of experiment?  Why do you think the researchers looked at data after the hospitalization?  Does that compromise the sample from which we are trying to generalize?  And would this info apply to patients in the US?

I’d love to hear your answers to those questions.  It’s exactly the type of analysis of evidence you want in your research papers, too.   

Mubanga, M., Mwenya Mubanga Department of Medical Sciences, Byberg, L., Liisa Byberg Department of Surgical Sciences, Egenvall, A., Agneta Egenvall Department of Clinical Sciences, Ingelsson, E., Erik Ingelsson Department of Medical Sciences, Fall, T., Fall, T. F. T., The Data Supplement is available at https://www.ahajournals.org/doi/suppl/10.1161/CIRC… Fall, & Kazi, D. S. (2019, October 8). Dog ownership and survival after a major cardiovascular event. Circulation: Cardiovascular Quality and Outcomes. Retrieved March 9, 2022, from https://www.ahajournals.org/doi/10.1161/CIRCOUTCOM…