Symple symptom journal and health diary

Blog

Correlations

Many folks write in asking for Symple to show correlations between symptoms and factors:

  • Is acupuncture effective?
  • Does exercise alleviate depression?
  • Does gluten trigger migraines?
  • Are the meds working? 

I have hesitated to correlate your data for several reasons. Will we become subject to medical device regulation (yes)? What if our algorithm is wrong? Will you understand the difference between correlation and causation? The last one is the one I'm actually most concerned about.

We often confuse a correlation (a relationship) with a causation (a reason for something happening).

For example, what if you take your meds every morning with a bowl of cereal and a shot of vodka? Which is to blame for that woozy head? If you only track "medications" against "woozy head," you will definitely see a correlation between the two and incorrectly blame medications. You will be in danger of "making a spurious correlation."

http://www.statisticshowto.com/spurious-correlation/

http://www.statisticshowto.com/spurious-correlation/

This isn't to say that medications don't cause wooziness! But until "control for medications" by ditching that morning shot, you can't know.

Symple helps us think experimentally, to ask questions and make observations. But Symple can't and shouldn't make suggestions. That's the job of your doctor, pharmacist, dietary specialist or therapist.

natasha gajewskiComment