Find calibration thresholds
The purpose of this function is to automatically find calibration thresholds for a numerical causal condition, to be split into separate groups.
findTh(x, n = 1, hclustm = "complete", distm = "euclidean", ...)
x |
A numerical causal condition. |
n |
The number of thresholds to find. |
hclustm |
The agglomeration (clustering) method to be used. |
distm |
The distance measure to be used. |
... |
Other arguments (mainly for backwards compatibility). |
The process of calibration into crisp sets assumes expert knowledge about the best threshold(s) that separate the raw data into the most meaningful groups.
In the absence of such knowledge, an automatic procedure might help grouping the raw data according to statistical clustering techniques.
The number of groups to split depends on the number of thresholds: one thresholds splits into two groups, two thresholds splits into three groups etc.
For more details about how many groups can be formed with how many thresholds,
see cutree().
A numeric vector of length n.
Adrian Dusa
# hypothetical list of country GDPs gdp <- c(460, 500, 900, 2000, 2100, 2400, 15000, 16000, 20000) # find one threshold to separate into two groups findTh(gdp) # 8700 # find two thresholds to separate into two groups findTh(gdp, n = 2) # 8700 18000 # using different clustering methods findTh(gdp, n = 2, hclustm = "ward.D2", distm = "canberra") # 1450 8700
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.