ThreadSky
About ThreadSky
Log In
ccanonne.bsky.social
•
63 days ago
Forget even about variance, what if the expectation isn't defined?
Comments
Log in
with your Bluesky account to leave a comment
[–]
rishav84ia.bsky.social
•
63 days ago
Shouldn’t the expectation of any symmetric distribution be 0?
0
1
reply
[–]
ccanonne.bsky.social
•
63 days ago
Unfortunately no :)
https://en.m.wikipedia.org/wiki/Cauchy_distribution
3
2
reply
[–]
dirque.bsky.social
•
63 days ago
We shouldn't blame the distribution for this. Blame the expectation which fails to be zero although it clearly *has* to be
3
reply
[–]
sarielhp.bsky.social
•
63 days ago
Easier example..
P(Zi=k)= (Zi=-k) =c/k*k, for all positive integer k, for appropriate constant c.
OTOH the median of such a distribution is zero. No?
1
1
reply
[–]
ccanonne.bsky.social
•
62 days ago
Yes
1
reply
Posting Rules
Be respectful to others
No spam or self-promotion
Stay on topic
Follow Bluesky's terms of service
×
Reply
Post Reply
Comments
P(Zi=k)= (Zi=-k) =c/k*k, for all positive integer k, for appropriate constant c.
OTOH the median of such a distribution is zero. No?