Archived Comments for:
Hospital characteristics and patient populations served by physician owned and non physician owned orthopedic specialty hospitals
An interesting article. However, it is not appropriate to make conclusions based on non-significant findings. The authors report (both in the abstract and later again in the results section) that "physician owned specialty hospitals were located in neighborhoods with a higher proportion of black residents (8.2% vs. 6.7%, P = .76)." This difference is not significant, yet the authors seem to treat it otherwise. Non-significance means that any differences observed between conditions are due to chance and/or random error, and thus cannot be used to make conclusions about what is being studied.
The authors could have very easily said that physician owned hospitals treat fewer blacks but are located in neighborhoods with proportions of black residents similar to non-physician owned hospitals, and it would have still sent the desired message while being scientifically accurate.
Please treat non-significant findings as such
11 December 2007
An interesting article. However, it is not appropriate to make conclusions based on non-significant findings. The authors report (both in the abstract and later again in the results section) that "physician owned specialty hospitals were located in neighborhoods with a higher proportion of black residents (8.2% vs. 6.7%, P = .76)." This difference is not significant, yet the authors seem to treat it otherwise. Non-significance means that any differences observed between conditions are due to chance and/or random error, and thus cannot be used to make conclusions about what is being studied.
The authors could have very easily said that physician owned hospitals treat fewer blacks but are located in neighborhoods with proportions of black residents similar to non-physician owned hospitals, and it would have still sent the desired message while being scientifically accurate.
Competing interests
No competing interests to my knowledge