Felly sgrifennodd Will Hand :
You're right of course Norman, but 1/1 (if indeed it pans out that way) is a
jolly good start for a 2/3 average :-)

I suspect there are people around here who would claim the MO were wrong
if they got 3/3, because they missed the 2/3. So either way the doubters
will not be appeased!

Adrian
--
Adrian Shaw ais@
Adran Cyfrifiadureg, Prifysgol Cymru, aber.
Aberystwyth, Ceredigion, Cymru ac.
http://users.aber.ac.uk/ais uk

In message , Adrian D. Shaw
writes
Felly sgrifennodd Will Hand :
You're right of course Norman, but 1/1 (if indeed it pans out that way) is a
jolly good start for a 2/3 average :-)

I suspect there are people around here who would claim the MO were wrong
if they got 3/3, because they missed the 2/3. So either way the doubters
will not be appeased!

Adrian

I wasn't commenting on the forecast itself and I certainly wasn't
doubting it. I was commenting on the fact that the accuracy of a single
probability forecast cannot be assessed. The Met Office forecast covers
the possibility of a colder than average winter and also the possibility
of a warmer than average winter. Although the odds in the forecast are
more in favour of the former than the latter that doesn't mean that the
forecast would be incorrect if it turned out to be a warmer than average
winter.

If, over a representative sample of 2/3 probability forecasts the actual
event occurred 3 times out of 3 on average then the forecasting would be
considered fairly inaccurate.

Norman.
(delete "thisbit" twice to e-mail)
--
Norman Lynagh Weather Consultancy
Chalfont St Giles 85m a.s.l.
England

Felly sgrifennodd
Norman Lynagh :
If, over a representative sample of 2/3 probability forecasts the actual
event occurred 3 times out of 3 on average then the forecasting would be
considered fairly inaccurate.

Yes Norman - I certainly wasn't directing my comment at you. You are right
of course, and a representative sample would need far more than just three
members to have any statistical validity.

But I'm sure if someone really wanted to they could trawl through the
archives and find enough samples.

The media, however, would probably think the Met Office were wonderful in
such circumstances. Until the general public understand some basic
statistics (which I doubt will ever happen given that clearly even most of
the media don't, and are happy to keep the public in the dark), we're doomed
to have this sort of discussion all too frequently.

Adrian
--
Adrian Shaw ais@
Adran Cyfrifiadureg, Prifysgol Cymru, aber.
Aberystwyth, Ceredigion, Cymru ac.
http://users.aber.ac.uk/ais uk

Adrian D. Shaw wrote:



Until the general public understand some basic
statistics (which I doubt will ever happen given that clearly even most of
the media don't, and are happy to keep the public in the dark), we're
doomed to have this sort of discussion all too frequently.


Not much chance of the general public understanding basic statistics when my
HNC statistics instructor didn't have much of a clue.

--
Graham Davis
Bracknell

In article ,
Adrian D. Shaw writes:
Felly sgrifennodd Will Hand :
You're right of course Norman, but 1/1 (if indeed it pans out that way) is a
jolly good start for a 2/3 average :-)

I suspect there are people around here who would claim the MO were wrong
if they got 3/3, because they missed the 2/3. So either way the doubters
will not be appeased!

I haven't done the sums, but you would probably need 10-20 forecasts
before you could start to make a judgement of their accuracy.
--
John Hall "Never play cards with a man called Doc.
Never eat at a place called Mom's.
Never sleep with a woman whose troubles
are worse than your own." Nelson Algren

"Adrian D. Shaw" wrote in message
...
Felly sgrifennodd Adrian D. Shaw :
Felly sgrifennodd Stuart :
(suggest you go and read the original text, re-posted by Will recently

Do you have a link to this?

OK I went and found it, posted by Will on Jan 14th:

= Here is what the Met Office actually predicted, taken from their web
= site today 14/1/06

=" The Met Office continues to predict a two in three chance of a
= colder-than-average winter for much of Europe. If this holds true,
parts of
=the UK - especially southern regions - are expected to have temperatures
=below normal. There is also an indication for a drier-than-average
winter
=over much of the UK.

=The last eight winters have been relatively mild and perhaps have given
the
= impression that these are 'normal'. The balance of probability is for a
=winter colder than those experienced since 1995/6. "

The Met Office were dead right about the colder than average winter for
much
of Europe, which they predicted at 2/3 chance.

They did not, however, make ANY probability predicion regarding either the
length of, nor the severity of, any effect from this in southern UK.
There was (so I'm told; I was in central Europe at the time, suffering the
cold and enjoying the snow) a spell of cold weather in the south-east
recently, which I assume can be attibuted to the central European cold. So
they arguably got that right too.


Thanks for that Adrian, I must hold my hands up and say I was wrong.

This is the first time I have seen the Met Office's forecast issued last
Autumn, undoubtedly I was going of the media's interpretation of the Met
Office forecast that back in November were indicating a winter to end all
winters (along with no Gas, Bird Flue and electricity cuts.

I wonder if I will ever learn not to watch the news or read newspapers!

"Stuart" wrote in message
...

"Adrian D. Shaw" wrote in message
...
Felly sgrifennodd Adrian D. Shaw :
Felly sgrifennodd Stuart :
(suggest you go and read the original text, re-posted by Will recently

Do you have a link to this?

OK I went and found it, posted by Will on Jan 14th:

= Here is what the Met Office actually predicted, taken from their web
= site today 14/1/06

=" The Met Office continues to predict a two in three chance of a
= colder-than-average winter for much of Europe. If this holds true,
parts of
=the UK - especially southern regions - are expected to have temperatures
=below normal. There is also an indication for a drier-than-average
winter
=over much of the UK.

=The last eight winters have been relatively mild and perhaps have given
the
= impression that these are 'normal'. The balance of probability is for a
=winter colder than those experienced since 1995/6. "

The Met Office were dead right about the colder than average winter for
much
of Europe, which they predicted at 2/3 chance.

They did not, however, make ANY probability predicion regarding either the
length of, nor the severity of, any effect from this in southern UK.
There was (so I'm told; I was in central Europe at the time, suffering the
cold and enjoying the snow) a spell of cold weather in the south-east
recently, which I assume can be attibuted to the central European cold. So
they arguably got that right too.


Thanks for that Adrian, I must hold my hands up and say I was wrong.

This is the first time I have seen the Met Office's forecast issued last
Autumn, undoubtedly I was going of the media's interpretation of the Met
Office forecast that back in November were indicating a winter to end all
winters (along with no Gas, Bird Flue and electricity cuts.

I wonder if I will ever learn not to watch the news or read newspapers!


Stuart, take it in stages.

I gave up reading newspapers years ago. Don't miss them at all. I still watch
the TV news and listen to the radio, but leave the room and go on the Net when
the silly stuff comes on. Last year I gave up watching National TV weather
forecasts, preferring only to watch the local one. The InterNet is now my number
one source of information and I think it is brilliant!

Will.
--