From the course: Descriptive Healthcare Analytics in R
Unlock the full course today
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
Designing confounders: Other demographics - R Tutorial
From the course: Descriptive Healthcare Analytics in R
Designing confounders: Other demographics
- [Instructor] Onto Chapter 2, section 7, where we proceed to designing demographic confounders. So, this lecture will show you how to design variables for ethnicity, race, and other demographics. The way the variables come in in the BRFSS, and in most data sets, are not suitable for analysis. You'll understand why as I walk you through this. This is why you have to almost always redesign each variable you want to use. Let's look at how I did this in the data dictionary. And back at our dictionary, we can see that our smoking grouping variable and the smoking indicator variable is documented. Next on the list, we have two, what you call two-state flags, because they can only be 1 and 0, and that is _HISPANC and SEX. But as you can see, I redid those variables too. Please notice that for some reason they did not include the second I in Hispanic in the variable. So, I call it Hispanc! I don't know who names these variables. But you get to name your own when you design them. So, as you…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Contents
-
-
-
-
Uses of a data dictionary4m 35s
-
(Locked)
How to set up a data dictionary3m 48s
-
(Locked)
Adding to the data dictionary6m 13s
-
(Locked)
Understanding confounders4m 24s
-
(Locked)
Making a web of causation6m 28s
-
(Locked)
Designing confounders: Age and smoking4m 42s
-
(Locked)
Designing confounders: Other demographics4m 19s
-
(Locked)
Designing confounders: Other variables used in analysis4m 39s
-
-
-
-
-
-