This is the first huge problem; YOU CAN'T PROVE CAUSATION WITH AN OBSERVATIONAL STUDYhttps://twitter.com/GidMK/status/857091846438367232 …
The confidence intervals (a stats measure) were all also huge, meaning that a lot of these findings are just *barely* significant
-
-
And remember, statistical significance doesn't always mean very much at all https://tincture.io/an-insignificant-blog-post-570f9aa6bc5d …
-
Let me know if you'd like me to actually do this, I've been seeing a study at least once a weekhttps://twitter.com/GidMK/status/857091846438367232 …
- Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.