Group v Individual

[From Rick Marken (971129.1820)]

Kenneth Kitzke (971129.20:00 EST) --

Are you willing to concede that group methods are important fo
determine the behavior of groups of individuals?

Not only do I concede it; I strongly _advocate_ it! For example,
in an earlier post I mentioned my support of the "statisitcal"
approach to taking the US census using sampling techniques.
There is a great book on sampling by Slonim (forgot his first
name and the name of the book) that explains when and why sampling
methods are often more accurate than enumerative counts of
populations.

The statistical methods used in psychology are perfectly
appropriate to the study of populations using samples (assuming
appropriate sampling methods are used, which is rarely the case);
but they tell us nothing about individuals.

Best

Rick

···

--
Richard S. Marken Phone or Fax: 310 474-0313
Life Learning Associates e-mail: rmarken@earthlink.net
http://home.earthlink.net/~rmarken/

[From Bruce Abbott (971130.0005 EST)]

Rick Marken (971129.1820) --

Kenneth Kitzke (971129.20:00 EST)

Are you willing to concede that group methods are important fo
determine the behavior of groups of individuals?

Not only do I concede it; I strongly _advocate_ it! For example,
in an earlier post I mentioned my support of the "statisitcal"
approach to taking the US census using sampling techniques.
There is a great book on sampling by Slonim (forgot his first
name and the name of the book) that explains when and why sampling
methods are often more accurate than enumerative counts of
populations.

You dodged Kenny's second question:

Such studies provide knowledge on how individuals are likely to behave.
This can have value that may exceed knowing how any particular individual
will behave. Do you agree?

Well, do you?

Regards,

Bruce

[From Bill Powers (971130.0544 MST)]

Bruce Abbott (971130.0005 EST) (replying to Rick Marken)

You dodged Kenny's second question:

Such studies provide knowledge on how individuals are likely to behave.
This can have value that may exceed knowing how any particular individual
will behave. Do you agree?

I, at least, agree. If a teacher finds that class sizes tend to dwindle
during a semester, the teacher might find this a useful indicator of some
deficiency in the teacher's way of teaching the course. Which individuals
drop out of the class is not the main question (although it could be
relevant -- maybe the course description in the catalogue omitted the
prerequisites).

But suppose an administrator looks at another teacher's class attendance
records, and finds that there is a 25% absentee rate. "The students in your
class," he thunders at the teacher, "are attending your lectures only 75%
of the time. What is wrong with these kids?" The answer is that there is
nothing wrong with "them" -- only with the 25% who are football players and
NEVER attend the class.

If you assume that group characteristics apply to every individual in the
group, but are simply masked by random influences, you gain no
understanding of the individuals. On the other hand if you study
individuals, most of the variance in the group statistics will be
explained, although the correct explanation is likely to be different for
each individual. In the case of class attentendance, the group statistics
give the impression that any given student is likely to cut class a quarter
of the time. In fact, the students who do attend _always_ attend, and the
failure of the others to appear is completely explained once you know that
football players are being given an automatic B in that course.

Our dispute is not about the use of group statistics for legitimate
purposes, those related to performance of the group. It is about attempts
to apply the results of group studies to individuals rather than studying
the individuals one at a time.

Best,

Bill P.

[From Rick Marken (971130.0845)]

Bruce Abbott (971130.0005 EST) to me:

You dodged Kenny's second question:

Such studies provide knowledge on how individuals are likely
to behave. This can have value that may exceed knowing how
any particular individual will behave. Do you agree?

Well, do you?

Bill Powers (971130.0544 MST), butting in;-)

I, at least, agree.

For those who think one of my main goals in life is defending
everything that Bill says, listen up! I completely DISAGREE
with Ken's statement and I think Bill is _wrong_ --VERY WRONG --
to say that he agrees with it. In fact, Bill was _not_ agreeing
with Ken's statement that "such [group] studies provide knowledge
on how individuals are likely to behave". Bill's post agreed with
a statement Ken _didn't_ make: "The results of such [group]
studies can be explained in terms of the results of individual
studies." Here is Bill's agreement with THAT statement:

If you assume that group characteristics apply to every
individual in the group, but are simply masked by random
influences, you gain no understanding of the individuals.
On the other hand if you study individuals, most of the
variance in the group statistics will be explained, although
the correct explanation is likely to be different for each
individual.

My answer to Ken's statement is an emphatic NO!!! Group studies
do _not_ provide knowledge of how each individual is _likely_ to
behave. Thinking so is the _prejudice_ of using group statistics
to gain "knowledge" of individuals. It leads the Mozart deprived
to think that such studies tell you something worthwhile about
individuals. Group studies tell you no such thing!

If group researchers followed up their investigations with
individual studies, such as the one suggested in Bill Powers'
(971130.0544 MST) example, then, indeed, the results of
group research would tell you how individuals are likely to
behave because you would now have the _individual data_ showing
how each individual behaves (you would know for sure, for
example, that an individual on the football team, in Bill's
example, will not attend class for the entire semester). But,
as Bruce Abbott, the author of a forthcoming text on group
methods, knows full well, psychologists _never_ (count them,
NEVER) follow up their group studies with individual studies
aimed at explaining the group results. If Abbott claims in his
textbook that groups statistics provide knowledge of individuals,
then I hope that he has the decency to give his text an
informative title, like "The Misuse of Statistics" or,
better, "Insitutionalized Prejudice".

Best

Rick

···

--
Richard S. Marken Phone or Fax: 310 474-0313
Life Learning Associates e-mail: rmarken@earthlink.net
http://home.earthlink.net/~rmarken/

[From Bruce Abbott (971130.1210 EST)]

Bill Powers (971130.0544 MST) --

But suppose an administrator looks at another teacher's class attendance
records, and finds that there is a 25% absentee rate. "The students in your
class," he thunders at the teacher, "are attending your lectures only 75%
of the time. What is wrong with these kids?" The answer is that there is
nothing wrong with "them" -- only with the 25% who are football players and
NEVER attend the class.

I had to laugh at this example. Administrators (at least the ones I've
dealt with) would not ask what is wrong with the students, they would ask
what is wrong with the teacher. Of course, this also begs the question.

If you assume that group characteristics apply to every individual in the
group, but are simply masked by random influences, you gain no
understanding of the individuals. On the other hand if you study
individuals, most of the variance in the group statistics will be
explained, although the correct explanation is likely to be different for
each individual.

Ah, now you're talkin' my lingo. Murray Sidman, a protege of B. F. Skinner,
said exactly this in _Tactics_ (1960).

Our dispute is not about the use of group statistics for legitimate
purposes, those related to performance of the group. It is about attempts
to apply the results of group studies to individuals rather than studying
the individuals one at a time.

From my perspective, our dispute is not about that either. My position was

not that one can with certainty apply the results of group studies to
individuals, but that group studies may identify variables whose effects
(under the conditions studied) apply with sufficient regularity to
individuals that differences appear in group means. Variables so identified
warrant further study on a case-by-case basis. This is a weaker position
that is supported by research experience. I don't know that you would
disagree with this, but I did feel that in the rush to condemn group-based
designs, such proper uses were not being mentioned, and so I wanted to point
out (rather innocuously, I thought) that useful information can be gained
from them under proper conditions.

There _are_ cases in which group-based functions and individual functions
look much alike, by the way. Some functions are sufficiently general that
they do not vary radically from individual to individual; one task within
any science is to identify such general relationships. For example, we
might expect certain parameters such as gain to vary across individuals
controlling cursor position in a tracking study, but would not expect
radical differences from individual to individual in the nature of the
function. For example, I have seen group data in a study of body-weight
control in rats (not our study) that looks like just what one would expect
of an individual control system's behavior in response to disturbance.

Having said this, I should probably remind everyone that I am a strong
proponent of the single-subject approach, and am well aware of the
shortcomings of group-based designs when it comes to applying their results
to individuals. Nor am I claiming that everyone doing psychological
research using these methods is as aware of these limitations as I.

Regards,

Bruce

[From Bill Powers (971130.1033 MST)]

Rick Marken (971130.0845)--

For those who think one of my main goals in life is defending
everything that Bill says, listen up! I completely DISAGREE
with Ken's statement and I think Bill is _wrong_ --VERY WRONG --
to say that he agrees with it. In fact, Bill was _not_ agreeing
with Ken's statement that "such [group] studies provide knowledge
on how individuals are likely to behave".

I was of two minds about this statement. If Ken had said "group studies
provide knowledge on how AN INDIVIDUAL IS LIKELY TO BEHAVE," I would have
had no problem with disagreeing. But when people speak of "individuals" in
the plural, they are no longer speaking about one sample of one person.
They are speaking about a group. So what Ken said was that group studies
provide knowledge about how a group is likely to behave, and with that I
find no disagreement (other than quibbles about sample size).

Best,

Bill P.

Bill's post agreed with

···

a statement Ken _didn't_ make: "The results of such [group]
studies can be explained in terms of the results of individual
studies." Here is Bill's agreement with THAT statement:

If you assume that group characteristics apply to every
individual in the group, but are simply masked by random
influences, you gain no understanding of the individuals.
On the other hand if you study individuals, most of the
variance in the group statistics will be explained, although
the correct explanation is likely to be different for each
individual.

My answer to Ken's statement is an emphatic NO!!! Group studies
do _not_ provide knowledge of how each individual is _likely_ to
behave. Thinking so is the _prejudice_ of using group statistics
to gain "knowledge" of individuals. It leads the Mozart deprived
to think that such studies tell you something worthwhile about
individuals. Group studies tell you no such thing!

If group researchers followed up their investigations with
individual studies, such as the one suggested in Bill Powers'
(971130.0544 MST) example, then, indeed, the results of
group research would tell you how individuals are likely to
behave because you would now have the _individual data_ showing
how each individual behaves (you would know for sure, for
example, that an individual on the football team, in Bill's
example, will not attend class for the entire semester). But,
as Bruce Abbott, the author of a forthcoming text on group
methods, knows full well, psychologists _never_ (count them,
NEVER) follow up their group studies with individual studies
aimed at explaining the group results. If Abbott claims in his
textbook that groups statistics provide knowledge of individuals,
then I hope that he has the decency to give his text an
informative title, like "The Misuse of Statistics" or,
better, "Insitutionalized Prejudice".

Best

Rick
--
Richard S. Marken Phone or Fax: 310 474-0313
Life Learning Associates e-mail: rmarken@earthlink.net
http://home.earthlink.net/~rmarken/

[Martin Taylor 971130 12:50]

Bill Powers (971130.0544 MST)]

I, at least, agree. If a teacher finds that class sizes tend to dwindle
during a semester, the teacher might find this a useful indicator of some
deficiency in the teacher's way of teaching the course. Which individuals
drop out of the class is not the main question (although it could be
relevant -- maybe the course description in the catalogue omitted the
prerequisites).

I'm reminded of a situation recently on TV in which the reverse was the
case. The teacher's reference was to have all but one student drop out
as the lecture series went on. That one student was checking the correctness
of the proof of Fermat's Last Theorem. The others were not supposed to
know that this was the topic of the course--which was, however, accurately
described in terms of the various component theories that were addressed.

In this case, the teacher's efficiency (not deficiency) was shown by the
dwindling class size! And it really did matter which individual student(s)
stayed or left.

···

-----------------

Bill Powers (971130.0500 MST)

Not all people using theories have the luxury of applying them only to the
groups used by the researchers and under the same conditions. A businessman
is not interested in how college sophomores in a mix of 60 percent affluent
and 40 percent underpriviledged participants, with half of them being women
and half men, will change their judgments depending on whether they are
paid one dollar or five dollars.

We have this nonsensical situation right now in Ontario. There was a ten-day
test given to all Grade 3 students, and this week school ratings came out
based on the average scores. Several schools in Toronto complained that
the scores were unfair because the tests were given only in English and
many of the students could only read some other language. But other
people say it would be unfair to rate the schools only on those students
capable of taking the test, because the other students who speak Somali,
Chinese, or whatever are, after all, in the school. So the schools _must_
be doing badly if the average score is poor. That the kids are bright, and
know the subject matter of the test is irrelevant. They didn't score well
on the test, and that's that.

It matters, in the context of the Ontario Government's decision to take
all direction of schools into the central bureacracy's hands, and to force
them all into a common curriculum (in the name of "improving education").
If it were not for that, one could laugh at the ludicrousness of the
argument, but as it is, these poorly ranked schools are likely to lose
funding and the support they need to help the kids who don't speak English.

Martin

[From Bill Powers (971130.1041 MST)]

Bruce Abbott (971130.1210 EST) --

I had to laugh at this example. Administrators (at least the ones I've
dealt with) would not ask what is wrong with the students, they would ask
what is wrong with the teacher. Of course, this also begs the question.

I had already given an example in which the conclusion was about the
teacher, so I thought I'd throw in one on the other side. Note that if the
teacher were blamed, that would also be incorrect. The problem is with the
administrator who gives the football players a free pass. The general
principle is that administrators always use statistics to blame someone
else for effects caused by the administrators. See Dilbert.

If you assume that group characteristics apply to every individual in the
group, but are simply masked by random influences, you gain no
understanding of the individuals. On the other hand if you study
individuals, most of the variance in the group statistics will be
explained, although the correct explanation is likely to be different for
each individual.

Ah, now you're talkin' my lingo. Murray Sidman, a protege of B. F. Skinner,
said exactly this in _Tactics_ (1960).

Seems to me you have a rather hard conflict to resolve, if you believe this
and also teach conventional statistics courses.

Our dispute is not about the use of group statistics for legitimate
purposes, those related to performance of the group. It is about attempts
to apply the results of group studies to individuals rather than studying
the individuals one at a time.

From my perspective, our dispute is not about that either. My position was

not that one can with certainty apply the results of group studies to
individuals, but that group studies may identify variables whose effects
(under the conditions studied) apply with sufficient regularity to
individuals that differences appear in group means.

I tried to discuss that a while back and you didn't respond. If it is true
that the group effect arises because the treatment affects all the members
of the group similarly, then your conclusion is correct. But even if the
treatment affects all the members of the group differently, it is still
quite possible that there will be a group effect. Simply by doing the group
study, you can't determine which is the case: whether the individuals are
affected differently or in the same way. The only way to settle that
question is to investigate the individuals one at a time. If you do
investigate the individuals one at a time, the group study is superfluous.
But if you don't do the individual studies, the group study tells you
nothing about the individuals.

The logic is clear: group studies tell us nothing about individuals.

Variables so identified
warrant further study on a case-by-case basis. This is a weaker position
that is supported by research experience. I don't know that you would
disagree with this, but I did feel that in the rush to condemn group-based
designs, such proper uses were not being mentioned, and so I wanted to point
out (rather innocuously, I thought) that useful information can be gained
from them under proper conditions.

I am not condemning group-based designs. They are fine for studying group
behavior. Anything you think you learn about individuals from the group
study, however, you can learn faster from the individual studies, which you
will have to do in any case.

The only condition under which I could agree with you would be when the
group study is used as a quick way of eliminating treatments that have NO
effect. Unfortunately, all treatments have some effect. If the effect
doesn't reach significance, you just use a larger sample; eventually, if
you have the resources to test hundreds of thousands or millions of people,
you will get a significant effect no matter what you manipulate. And then,
to show that it is valid for predicting individual behavior, you will have
to start testing individuals. So you might as well just start with the
individuals, if individual behavior is what you're interested in.

Remember the invalid syllogism:

A manipulation that affects all individuals in a group the same way will
affect the group behavior in the same way as the individuals. (fact)

A manipulation affects group behavior. (observation)

Therefore the individual behaviors are affected the same way as the group
behavior. (conclusion)

The correct conclusion is that from the group behavior you can infer
nothing about the individual behaviors.

Succinctly:
A --> B.
B;
Therefore A.

... is wrong.

Best,

Bill P.

···

There _are_ cases in which group-based functions and individual functions
look much alike, by the way. Some functions are sufficiently general that
they do not vary radically from individual to individual; one task within
any science is to identify such general relationships. For example, we
might expect certain parameters such as gain to vary across individuals
controlling cursor position in a tracking study, but would not expect
radical differences from individual to individual in the nature of the
function. For example, I have seen group data in a study of body-weight
control in rats (not our study) that looks like just what one would expect
of an individual control system's behavior in response to disturbance.

Having said this, I should probably remind everyone that I am a strong
proponent of the single-subject approach, and am well aware of the
shortcomings of group-based designs when it comes to applying their results
to individuals. Nor am I claiming that everyone doing psychological
research using these methods is as aware of these limitations as I.

Regards,

Bruce