? Why "Burden of proof" ?

[Sean Crist]

On Sat, 7 Aug 1999 ECOLING at aol.com wrote:

> I respectfully disagree with the person who
> recently argued between the following two
> alternatives that either could be an appropriate "null hypothesis"
> (though I am greatly appreciative of that same person's
> many other contributions!)

>>    No languages are related.
>> <snip>
>>    All languages are related.

> Rather, the real null hypothesis is something like

> "We do not know whether all languages are related
> (or whether there was polygenesis)" (etc.)

"We don't know" isn't a hypothesis.  A hypothesis is a proposition about
how things are.

Science proceeds by rejecting hypotheses.  To start the process, you have
to have some initial hypothesis.  The null hypothesis is some statement of
the form "There is no connection between A and B".  If you find evidence
that the null hypothesis is wrong, then you reject the null hypothesis.

As Larry Trask has already pointed out, there are good epistemological
reasons for taking "there is no connection" as our initial hypothesis,
rather than "there is a connection"; and I won't belabor that point.
What's important is that you start with some hypothesis or other and work
on finding grounds to reject it. "We don't know" won't suit for those
purposes, because it is not a hypothesis.

  \/ __ __    _\_     --Sean Crist  (kurisuto at unagi.cis.upenn.edu)
 ---  |  |    \ /     http://www.ling.upenn.edu/~kurisuto/
  _| ,| ,|   -----
  _| ,| ,|    [_]
   |  |  |    [_]