From: Rebecca Nugent [rnugent@stat.cmu.edu]
Sent: Thursday, January 06, 2011 1:35 PM
To: Brian Junker
Subject: Re: 303 project ideas needed


Hi Brian,

I was doing some thinking and I agree - the students should get a little 
more creative about their surveys!  When I taught it, one group did a 
survey about flyer traffic locations where they sampled locations 
(bulletin boards) and then posted flyers with those rip tags on them. 
Something about the tag having a code to email to a generic email address 
and then they randomly gave prizes to people who emailed.  They measured 
traffic by how many people took the tags from the flyers.  That one went 
pretty well.

They also could sample things like timeframes or locations and then survey 
people's behavior.  I did a project at Stanford where I sampled thirty 
minute blocks over two days (some sort of stratified scheme) and then sat 
outside at a big intersection on campus and measured how many students ran 
the intersection on their bikes.  (It was a big problem at that 
intersection because there was heavy car traffic from the city going 
through it.)  A) it was hysterical because people started sitting out with 
me and harassing the bikers as they went through - which I had to explain 
to them was biasing my sample..... B) the maintenance workers started 
driving by yelling at me to write down that these damn kids cut them off 
all the time C) the administration actually asked to see my report.
The best part was when I had to survey at night when there was a party in 
the dorm next to me - I had lots of "help" that night.

My friend surveyed bars in the area to see if the reported Bay Area ratio 
of 3 men to 2 women was accurate.  Also hysterical.

So maybe they could sample things other than people; maybe they could do a 
cluster survey where they choose classes and then give surveys to those 
classes.  But I think that surveying people's behavior would be great. 
Maybe someone could sample building entrances/times and see if people are 
staying the requisite distance away from the door when they're smoking 
(they don't).  Or stand outside the UC and either ask people something or 
watch what they do.

Other thoughts:
Who eats at the lunch trucks?
Who uses the exercise rooms at the UC?  When?
How often do students break rules like no food/drinks in the computer 
clusters? (all the time)

Hope that helps.
Rebecca


On Tue, 4 Jan 2011, Brian Junker wrote:

> Hi Rebecca,
>
> After some thought I've decided to go ahead with the usual structure for
> 303, that is, have 9 groups doing survey projects as in the past.
>
> I can't have all 9 doing the typical on-campus email surveys, or there will
> be riots in the streets.
>
> What other kinds of successful survey projects have students done for you in
> 303?
>
> all best,
>
> -BJ
>
> Brian Junker                    (412) 268 - 2718
> Department of Statistics        brian@stat.cmu.edu
> 232 Baker Hall                  FAX: (412) CMU-STAT
> Carnegie Mellon University        or (412) 268-7828
> Pittsburgh PA 15213 USA
>
> WWW: http://www.stat.cmu.edu/~brian/
>
>