A quick explainer of how you can calculate exposure time between cases and contacts using R programming.
I’ve been at the annual conference of the Council of State and Territorial Epidemiologists all this week. The first conference I attended was back in 2008, when I was working at the Maryland Department of Health as an epidemiologist doing influenza surveillance. I remember it being a lot of fun because I got to learn a lot from people who had the same interests as I did. This has not changed much since then, but things around us in the world have. Let me explain…
When comparing two or more health indicators, it’s important to keep in mind that they might be on a different scale and presenting completely different information. In order to make the comparison more accurately, you can standardize the variables’ values and then create a Health Condition Index. So let’s use R and some open data to see how this can be done.
Sometimes, age-specific death counts are hard to come by. Something happened that doesn’t allow you to know how many people died in each age group, but you know the total number of people who died. So how do you account for differences in the age distribution of the population? Glad you asked!
Anecdotes are not data, but they could be canaries in the coal mine that are still worth looking into. If we don’t do due diligence and look into them, what could happen? What could we delay or even miss out on doing?
What happens when you get rid of your outliers? Depending on which outliers and how you chose to get rid of them, nothing might happen… Or you can royally screw things up.
Have we become too dependent on the p-value being greater than or less than 0.05 in order to make our decisions? Yes. Probably. Maybe. I’m 95% confident we have…