@danlewer, @tdbrothers and colleagues explain why risk factors for health outcomes shouldn't be studied by putting several independent variables into a regression model and identifying which are statistically significant in a new Methods Primer.
https://t.co/78CmzYNaTF
Among people who use heroin, tobacco smoking and illegal drugs cause a similar number of premature deaths https://t.co/k3iDmGEHth @danlewer@TattanBirch @Sharon_ACox
📷
We did some life table modelling among people who use heroin. Tobacco smoking causes as many premature deaths in this group as illegal drugs. Yet public health policies overlook smoking: https://t.co/3HQCPRqqZy New research with @Sharon_ACox and @TattanBirch
We've just published a scoping review of projects that aim to improve opioid agonist therapy (eg. methadone) in acute hospital settings: This https://t.co/ZM00x9Uf2U. This is part of our excellent iHOST project (https://t.co/Pt6P6H5nF8). A couple of findings ...
(5) My favourite find was the article "Treatment of hospitalized narcotic addicts" from the Illinois Medical Journal, 1970. https://t.co/gac7nj7jLm. This deserves an essay of its own
@bmj_latest If it sounds too good to be true it probably is. Before you stock up on dark chocolate read this response from @mendel_random https://t.co/mS2jMiJ9G0
Inflation is usually measured the change in prices compared to one year previously. Therefore, a reducing but still positive inflation figure often means REDUCING pricing month-on-month. A positive inflation figures does not always mean prices are going up.
Let's talk about the "5%" model. You just can't contribute meaningfully to a research project with 5% of your time. If you have 20 parallel projects, you literally just go to meetings and do nothing.