Now we plan to conduct a case-control study and analysis the data by propensity score matching (PSM).
The PSM were conducted by R package “MatchIt”.
We have learned the document of package “MatchIt” and found it very excellent.
But we have to confess that I'm a little bit confused.
If we analysis the data by the code as the example in the document:
m.out1 <- matchit(treat ~ age + educ + race + married +
nodegree + re74 + re75, data = lalonde,
method = "nearest", distance = "glm")
In the example, we can find the value of caliper was not defined.
So how larger is the value of caliper in the PS matching code when the method was set with “nearest” (method_nearest, Nearest Neighbor Matching).
That is, how larger is the value of caliper by default in the PS matching code when the method was set with “nearest” .
Or the caliper was not considered as a Parameter at the situation.
If we would not define a caliper, there is none caliper.
What's the truth？
- MatchIt: Getting Started. MatchIt: Getting Started • MatchIt.