# The defining values

From Flat Earth News:

You could argue that every profession has its defining value. For carpenters, it might be accuracy: a carpenter who isn’t accurate shouldn’t be a carpenter. For diplomats, it might be loyalty: they can lie and spy and cheat and pull all sorts of dirty tricks, and as long as they are loyal to their government, they are doing their job. For journalists, the defining value is honesty–the attempt to tell the truth. That is our primary purpose. All that we do–all that is said about us–must flow from the single source of truth-telling.

What is the defining value of statisticians?

P.S. My favorite of the responses below is Mike Anderson’s:

Separate the signal from the noise, then look at the noise for more signals.

I like this because (a) it acknowledges the presence of “noise” (that is, variation) but (b) recognizes that the “signal” is what’s most important.

## 30 thoughts on “The defining values”

1. Uncertainty?

2. Nominee #1: Summarizing.

Start: pile of data.
End: small (but not too small) number of statistics that describe the data.

Nominee #2: Making errors.

As in "I never knew the world was so full of errors everywhere until I took a stat class."

3. Herman Rubin has five commandments that he posted on UseNet from time to time:

For the client:

1. Thou shalt know that thou must make assumptions.

2. Thou shalt not believe thy assumptions.

For the consultant:

3. Thou shalt not make thy client’s assumptions for him.

4. Thou shalt inform thy client of the consequences of his assumptions.

For the person who is both (e. g., a biostatistician or psychometrician):

5. Thou shalt keep thy roles distinct, lest thou violate some of the other commandments.

4. "For journalists, the defining value is honesty," is this guy for real?

i'd say the defining value of statistics is describing

5. A desire to find out what is *really* going on by using real information about the world, and not ignoring the random element.

6. Not overstating what the data tell us, i.e., talking about confidence intervals instead of point estimates, talking about real-world significance instead of statistical significance, not claiming that being consistent with a data makes a theory true, etc.

7. Here are some possibilities:

accuracy
confidence (for the double entendre)
diligence
explication
inquisitiveness
insight
meticulousness
rigor
utility

8. I think most of the comments offered are descriptive of statistics not of the character of a statistician. I'd say it's digging. One might find a better word, but I'm trying indicate the process of digging out the truth hidden in data. If you aren't committed to digging into data, then you shouldn't be a statistician. Your ability to dig into data defines how good you are as a statistician.

BTW, I see clarity or impartiality as ideals. Statistics are mostly used to make points and further agendas and clarity is not only in the eye of the beholder but is often selectively used to highlight one argument.

9. Separate the signal from the noise, then look at the noise for more signals.

Try to do better at our job than modern journalists are doing with that "truth" thing.

10. Humility

11. Skepticism? I can't help feeling a statistician would wonder how far it was possible for a journalist to be truthful, failing practice in dealing with the cussedness of data.

12. I think the defining value of statisticians is either:

(1) Blind faith in whatever data land on your desk, or

(2) A belief that mathematical theorems have some connection to reality.

Or else,

(3) An overarching skepticism which conveniently reduces to complete credulity for the items that happen to fly under your personal b.s. radar.

13. I like skepticism as a defining value. Or at least it should be a defining value, because no data is ever perfect. (Unless of course, you fall into Prof.Gelman's "defining value" #3!

14. I think that our defining value is honesty about uncertainty. A lot of fields (machine learning, bioinformatics, signal processing, etc.) are focused on performing inference from data or separating signal from noise. However, in my experience, statistics is somewhat unique in its focus on on rigorously quantifying uncertainty.

15. So what value type would that be according to Schwartz's typology of human values? :)

16. Remain incredulous in the face of apparent evidence (mathematical evidence or data evidences).

I second the digg thing.