Stats question-continued - additional information

[msherman]

Here is some additional information for those that have requested it.


 The data is completely self-reported data. All respondents were
given a time line as to when specific events occurred (WTC 1 Hit,
Announcement in WTC 2 about WTC 1, WTC 2 Hit, WTC 2 collapsed, WTC 1
Collapsed). Minimally all respondents had some notion as to when thest
things happened. They were then asked when (to the best of their
ability) to provide the estimated time and floor when they specific
actions on their part occurred).
Arrived at work??
First became aware that something unusual had happened.
Concluded that something serious had happened.
Made the decision to evacuate.
Began to evacuate (physically).
Reached the street access level.
Exited on th street.
Reached home.

The correlation between where they started and the time between began
to evacuate and reached the street is .64.

>>>>>>>I saw the original posting and then watched the exchanges about
how to work
this problem. I'd like to ask a really basic question, more out of
curiosity
than anything else. The question is where did these data come from? I
read
the popularly published account of the attack (the name of which I
forget)
and find it kind of hard to believe that people could recall very
accurately
when they started down and when they hit the 'ground floor' however
you
define that. I doubt also that there were 'official' records of people
coming down. To the extent that the accounts in the book are accurate,
I'd
also think that one's velocity down the stairs depended on when one
started
down. Velocity would have slowed as volume increased and as rescue
people
started up. But, mainly, I'm curious of the circumstances of the
data's
collection.

[Craig Johnson]

I have a couple of questions and possibly some potential new avenues for you.

1)  Out of curiosity how many cases are in your data set?

2)  One of the things you may want to consider is finding out the
structure of the towers.  As I understand it there were several
different levels with elevators and what not.  I'm not sure if certain
floors shut down elevators or not but this could certainly have an
affect on the findings.  It is possible that some people left the
building quickly or when the elevators were still working.

3) If you have access to the data you could also throw in who the
individuals worked for.  It is possible that different companies on
different sections of the towers handled the evacuation differently.
I really don't know if this would play out or not....but I know some
companies take drills for fires and what not more seriously than
others.  Perhaps something like this played out and could play out in
your information.

4) The rate of evacuation per floor in my opinion is not a good way to
go.  The simple fact is that the result of this would be a slowly
decaying curve, with the longer they have to go the slower they would
have descended.  By simply trying to figure the average per floor you
would miss this effect.  For a case in point...... if you had to go
down 80 floors would your time between floors 80-79 be the same as
floors 22-21?  It is probable that it will not be because you are
tired OR the flow of people increased and you had to slow down.
Averaging this out would be an artifical guess of what was going on.

5) You may also want to consider how the stairwells are constructed.
I'm not sure if the stairwells were continuous from top to bottom or
were broken up by sections in the tower.  If they were broken up
within the tower it may or may not have slowed up the decent of the
people involved.

Things to think about.

Craig