Endurance.Net Ridecamp Archives

This post is about logic and validity, not whether we should or should not have a 
minimum age for Juniors.
And it's long, so if you've had it with this subject, just delete.

Joe Long wrote:
> On Wed, 22 Feb 2006 21:57:56 EST, Merryben@xxxxxxx wrote:
> > ...570 members out of a membership of about 6,000 said they wanted an age
> > restriction.  Out of that number 188 said at least 8 years old and 165 said
> > over 8 years old.  The rest said anywhere from 5 to 8.  Only about 18% of
> > the entire  membership even answered the question.
>
> When you are personally opposed to something, you can always twist the 
> numbers
> like that...
Maryben twisted/"cooked" nothing.  She simply restated Mike Maul's figures and then 
she added that based on a total membership of 6000, 1080 represented only 18% of the 
membership.

> ...and you will never have a majority favoring anything.
With respect to a survey, yes you can, IF the sample surveyed is reliably 
representative of the membership.

> A survey is just that -- a survey.  It is a representative sample.
No, a representative sample must reflect all, or at least most, aspects of the 
underlying universe.  Statistical sampling is an art and a science and just sending 
out a bunch of questionnaires to our membership and using the data on the ones 
returned does NOT qualify.

> And in that sample, a majority DID favor change, DID favor a minimum age for
> riders.  No amount of "cooking the numbers" alters that simple fact.
There are basically two kinds of surveys:  1) those where a statistical sample is 
drawn from a given universe and each and every member of that sample is surveyed and 
2) those where a survey is sent to every member of a given universe and the data 
collected results from those who return the survey.  The former, if properly 
constructed, can be expected to return statistically valid results for the universe
with an identifiable margin of error.  However, in the latter type of survey, it 
cannot be known if the results gathered are or are not representative of the universe 
and therefore it has no statistical validity for any of the members of the universe 
who failed to respond.

The basic hypotheses of statistical sampling theory are:
1) The population is a homogeneous group and
2) There is no bias in the selection of items of the sample. All items of the 
population have equal chance of being selected in the sample.*
While AERC, for the purposes of the 2004 Survey, may be considered a homogeneous 
group, the "sample" is extremely biased as it is limited to only those who were 
willing to take the time to fill out the survey and send it in.  It may seem that 
each member had an equal chance of being selected but the word "selected" above 
refers to inclusion in the sample, not inclusion in the universe.  Thus the actual 
"sample" is biased because it does not contain even one person in the 80% of the 
universe who didn't respond to the survey.  If you want a survey with results that 
ARE representative of the membership, you must first obtain a sample that is a 
statistically valid cross-section of our membership, next devise questions that are 
not biased and lastly survey each member of the sample.

> Mike Maul's figures show that there are five, six, seven-year-olds riding
> endurance rides every year.  How long are you going to continue to claim that it
> is not a problem?
The reason many do not think there is a problem is that they do not consider the fact 
of young children riding to be a problem in and of itself.  Lack of control.  Yes 
that's a problem.  Lack of responsibility for one's mount.  Another problem. But 
being 5 years old, no.  They don't see that as a "problem".  They see it as a "fact", 
like you are 5 or 10 or 45.  If one wishes to convince these members that 
participating in a Distance Ride and being 5 years old is a problem, one needs to 
demonstrate WHY it's a problem.  Using "what if's" won't work because almost all the 
"what if's" can be equally applied to older participants.  What is needed are 
specific examples of why a 5 year old riding is a problem, not why it MIGHT BE a 
problem.  If the reasons given ring true to the majority, they will push for age 
limits.  If they don't, or someone just says, "Because I said so", then those who are 
opposed to age limits now are not going to change their minds.

---------------------------------------------------------
*http://www.asosai.org/R_P_auditquality/appendixe.htm




=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=

Ridecamp is a service of Endurance Net, http://www.endurance.net.
Information, Policy, Disclaimer: http://www.endurance.net/Ridecamp
Subscribe/Unsubscribe http://www.endurance.net/ridecamp/logon.asp

Ride Long and Ride Safe!!

=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=