Add User Testimonials Section to docs

[matthewfeickert]

Description

Given the goodwill towards pyhf that @lukasheinrich has been reporting lately, it could be fun to ad something along the lines of a "User Testimonials" section to the docs, where we quote different analysis teams on their experience using pyhf. :)

This might be more of a fun idea then a practical one, but if there are no objections then let's do it? @kratsg @lukasheinrich

[kratsg]

"For years, I suffered from cluster headaches with no release. Aleve, Motrin, etc.. all didn't work.. but then I discovered pyhf, and I can finally see."

[smeehan12]

"Sometimes I wake up in a cold sweat in the middle of the night, shaken from a dream where I'm running, running, running, from a toothbrush carrying an apple and a chainsaw wearing Blues Brothers shades ... then it comes to me - pyhf - and I drift off back into a deep and restful hibernation. "

No, but seriously, the learning curve in the past couple weeks has been much easier to get up than when working with standard workspaces. Being able to inspect and easily modify the text-based input makes things less opaque and navigating the code-base is totally manageable . And the examples that exist thus far, even in the beta-state, are fantastic! Well done pyhf team!

[matthewfeickert]

Received in an email today (which made my evening):

Wow. THANK YOU.

I can’t believe this actually exists. I’ve been waiting for a simple easy-to-use example since… forever.

I went from zero to a result in 2 minutes, including installation time. And in python. *chef’s kiss*

I’m totally using this with all new students.

[kratsg]

Received in an email recently :)

What concerns use of pyhf in Belle II, I would say I am the first one in Belle II :) On the other hand, I have advertised this tool to our collaboration this past month as I found it very intuitive and very clear, so I am expecting few colleagues to join me. In the past (I used to work for LHCb) I had to write all the model/statistical interpretation myself and it took me long time so it was nice to see that someone else had worked it out this time around. Please do not hesitate to ask me any specific questions.

One feature of the pyhf package that I really appreciate is that I can validate the limit-setting with RooStats by converting my json file into XML-root and run the same statistical tests and get the same limit. As this is a new tool, cross-check with RooStats is necessary and you made it very easy to do.

[matthewfeickert]

From Twitter:

pyhf was really a critical tool throughout the whole Ph.D.!

https://twitter.com/lucas_borgna/status/1557348556431835139?s=20&t=tN2YKn8hLxd3GrB5D9laAQ