So, this makes the query result for underrepresented phonemes became less accurate. But the result overrepresented phonemes are still somewhat accurate. Here are the overrepresented phonemes in language with ejectives:
Phoneme Frequency Frequency Difference
In Subset In All
kʼ 94.97 9.41 85.55
tʼ 72.96 7.23 65.72
pʼ 69.81 6.92 62.89
t̠ʃʼ 69.81 6.92 62.89
tsʼ 51.57 5.11 46.46
ʔ 85.53 45.95 39.59
ʃ 76.10 41.52 34.58
qʼ 32.70 3.24 29.46
kʷʼ 25.79 2.56 23.23
t̠ʃʰ 29.56 6.86 22.70
x 42.14 19.89 22.25
q 30.19 8.48 21.71
h 90.57 69.01 21.55
kʰ 38.99 17.77 21.23
ɬ 27.04 5.99 21.06
χ 25.79 6.48 19.30
pʰ 35.85 17.21 18.64
tʰ 30.82 13.28 17.54
ts 44.03 26.68 17.34
t̠ʃ 67.30 50.75 16.55
I think one of the thing that can be gleaned from this, is that an ejective language tend to have /ʃ q ɬ/