corr_case()
Description
Conducts Pearson (default method), Spearman rank, or Kendall’s Tau-b correlation analysis using case wise deletion. Returns the relevant information and results in 3 DataFrames for easy exporting.
DataFrame 1 is the testing information, i.e. the type of correlation analysis conducted and the number of observations used.
DataFrame 2 contains the r value results in a matrix style look.
DataFrame 3 contains the p-values in a matrix style look.
Parameters
Input
def corr_case(dataframe, method = “pearson”)
Examples
Loading Packages and Data
import researchpy, numpy, pandas
numpy.random.seed(12345)
df = pandas.DataFrame(numpy.random.randint(10, size= (100, 2)),
columns= ['beck', 'srq'])
Pearson r
# Since it returns 3 DataFrames for easy exporting, if the DataFrames
# aren't assigned to an object the outputting tuple is rather messy
# and ugly
researchpy.correlation.corr_case(df[['beck', 'srq']])
( Pearson correlation test using list-wise deletion
0 Total observations used = 100, beck srq
beck 1 0.0029
srq 0.0029 1, beck srq
beck 0.0000 0.9775
srq 0.9775 0.0000)
# As noted above, the 3 return DataFrames are information, r values,
# and p-values
# The 3 DataFrame design was decided on so each DataFrame can easily
# be exported using already supported Pandas methods
i, r, p = researchpy.correlation.corr_case(df[['beck', 'srq']])
i
Pearson correlation test using list-wise deletion |
Total observations used = 100 |
r
beck |
srq |
|
---|---|---|
beck |
1 |
0.0029 |
srq |
0.0029 |
1 |
p
beck |
srq |
|
---|---|---|
beck |
0.0000 |
0.9775 |
srq |
0.9775 |
0.0000 |