Changes

Wrong conclusions could be dangerous to your health. User should of course double check with experts like doctors and veterans of the qs community (and this wiki). Learning enough about health and statistics takes time.  

Wrong conclusions could be dangerous to your health. User should of course double check with experts like doctors and veterans of the qs community (and this wiki). Learning enough about health and statistics takes time.  

Analysis algorithms are either hard to use or too incapable. I read an article in Nature where ML was used in multiple N-of-1 studies but that approach was both incomplete and difficult for the average user. All data aggregators for self tracking, besides OH, use linear regression or nothing at all. This problem can sometimes be avoided with [[Experiment VS Observational study|careful experimental design]] like RCT.  

Analysis algorithms are either hard to use or too incapable. Article in Nature where ML was used in multiple N-of-1 studies but that approach was both incomplete and difficult for the average user.<ref>https://www.nature.com/articles/s41398-021-01445-0</ref> All data aggregators for self tracking, besides OH, use linear regression or nothing at all. This problem can sometimes be avoided with [[Experiment VS Observational study|careful experimental design]] like RCT.  

Sources can be misleading. Food companies will give bad data to make themselves look good. Even user can have biases due to "negative engagement of user".  

Sources can be misleading. Food companies will give bad data to make themselves look good. Even user can have biases due to "negative engagement of user".