You might be surprised to hear that not only can linear regression fit lines between a response variable Y and one or more predictor variables, X, it can fit curves too. There are many ways to do this, but the simplest is by adding a polynomial term.
So what is a polynomial term and how do you know you need one?
The linear parameters in a regression model
A linear regression model has a few key parameters. These include the intercept coefficient, the slope coefficient, and the residual variance.
That intercept defines the height of the regression line. It does so by measuring the height of the line at one specific point: when all X = 0.
The slope defines how much Y differs, on average, for each one unit difference in X. In other words, it measures the constant relationship between X and Y. Yes, there can be multiple Xs and each one has its own slope.
A polynomial term–a quadratic (squared) or cubic (cubed) term turns a linear regression model into a curve.
(more…)
Have you ever wondered whether you should report separate means for different groups or a pooled mean from the entire sample? This is a common scenario that comes up, for instance in deciding whether to separate by sex, region, observed treatment, et cetera.
(more…)
No matter what statistical model you’re running, you need to go through the same steps. The order and the specifics of 
how you do each step will differ depending on the data and the type of model you use.
These steps are in 4 phases. Most people think of only the third as modeling. But the phases before this one are fundamental to making the modeling go well. It will be much, much easier, more accurate, and more efficient if you don’t skip them.
And there is no point in running the model if you skip phase 4.
If you think of them all as part of the analysis, the modeling process will be faster, easier, and make more sense.
Phase 1: Define and Design
In the first 5 steps of running the model, the object is clarity. You want to make everything as clear as possible to yourself. The more clear things are at this point, the smoother everything will be. (more…)
If you’ve tried coding in Stata, you may have found it strange. The syntax rules are straightforward, but different from what I’d expect.
I had experience coding in Java and R before I ever used Stata. Because of this, I expected commands to be followed by parentheses, and for this to make it easy to read the code’s structure.
Stata does not work this way.
An Example of how Stata Code Works
To see the way Stata handles a linear regression, go to the command line and type
h reg or help regress
You will see a help page pop up, with this Syntax line near the top.
(If you need a refresher on getting help in Stata, watch this video by Jeff Meyer.)
This is typical of how Stata code looks. (more…)
Ever consider skipping the important step of cleaning your data? It’s tempting but not a good idea. Why? It’s a bit like baking.
I like to bake. There’s nothing nicer than a rainy Sunday with no plans, and a pantry full of supplies. I have done my shopping, and now it’s time to make the cake. Ah, but the kitchen is a mess. I don’t have things in order. This is no way to start.
First, I need to clear the counter, wash the breakfast dishes, and set out my tools. I need to take stock, read the recipe, and measure out my ingredients. Then it’s time for the fun part. I’ll admit, in my rush to get started I have at times skipped this step.
(more…)
There are many designs that could be considered Repeated Measures design, and they all have one key feature: you measure the outcome variable
for each subject on several occasions, treatments, or locations.
Understanding this design is important for avoiding analysis mistakes. For example, you can’t treat multiple observations on the same subject as independent observations.
Example
Suppose that you recruit 10 subjects (more…)
