Hello John, I'd be interested in your first solution. 20 years ago too, that was the general question I answered for Bradford Council (resource distribution, not directly the value of statistics), but with two questions and two answers: (a) resources proportional to need in a population, (b) resources targeted at populations in most need. 

Ludi

> -----Original Message-----
> From: email list for Radical Statistics 
> [mailto:[log in to unmask]] On Behalf Of RADSTATS 
> automatic digest system
> Sent: 01 July 2008 00:02
> To: [log in to unmask]
> Subject: RADSTATS Digest - 26 Jun 2008 to 30 Jun 2008 (#2008-82)
> 
> There are 2 messages totalling 460 lines in this issue.
> 
> Topics of the day:
> 
>   1. How can we quantify the value of statistics? (2)
> 
> ******************************************************
> Please note that if you press the 'Reply' button your message 
> will go only to the sender of this message.
> If you want to reply to the whole list, use your mailer's 
> 'Reply-to-All' button to send your message automatically to 
> [log in to unmask]
> Disclaimer: The messages sent to this list are the views of 
> the sender and cannot be assumed to be representative of the 
> range of views held by subscribers to the Radical Statistics 
> Group. To find out more about Radical Statistics and its aims 
> and activities and read current and past issues of our 
> newsletter you are invited to visit our web site www.radstats.org.uk.
> *******************************************************
> 
> ----------------------------------------------------------------------
> 
> Date:    Mon, 30 Jun 2008 11:18:24 +0100
> From:    John Bibby <[log in to unmask]>
> Subject: Re: How can we quantify the value of statistics?
> 
> I agree with Ray's and Ursula's points, viz:
> 	1. Money is not the measure of everything (i.e. 'value' has many
> dimensions)
> 	2. "Who whom?" is important. (Thank you Mr Lenin!)
> 
> This is something I come back to every 20 years or so. In 
> 1990 it was = "How can we estimate the value of investment in 
>  .... IT systems in GP surgeries?"
> 
> Now (2008) my question relates to investment in better data 
> (thus = getting better estimates, thus improving all 
> decisions taken using that data). = My focus initially was on 
> ONE decision i.e. How to allocate budgets in proportion to 
> the (unknown) number of people in any area with a = 
> particular disease or trait.
> 
> I have a bit of a handle now on that one very narrow question 
> - I'll be = glad to send it to anybody who is interested. It 
> certainly needs further refining.
> 
> Thanks to all who have looked at this.
> 
> JOHN BIBBY
> 
> 
> All statements are on behalf of aa42.com Limited, a company 
> wholly owned = by John Bibby and Shirley Bibby. See 
> www.aa42.com/mathemagic and www.mathemagic.org
> 
> -----Original Message-----
> From: email list for Radical Statistics 
> [mailto:[log in to unmask]] = On Behalf Of Ursula Huws
> Sent: 26 June 2008 16:43
> To: [log in to unmask]
> Subject: Re: How can we quantify the value of statistics?
> 
> the question, surely, is: value to whom?=20 one could look at 
> the value of a statistics qualification to the statistician 
> by comparing the earnings of those with & without such 
> qualifications, controlling for other variables.=20 one could 
> similarly look at the value to companies by comparing the = 
> profits or market share or some other indicator of size of 
> those with and = without market research departments (or 
> using external consultants for this), = again controlling for 
> other variables.=20 one could perhaps look at the value to 
> the economy as a whole by = quantifying the outputs of 
> statistics-producing bodies (here again money would = 
> probably be the simplest measure) or perhaps, but this would 
> be trickier, track = down the sectors involved in producing 
> statistics & use the input output = tables from the national 
> accounts to compute what value is added to those = sectors 
> they supply.=20 as far as I am aware there is no easy way to 
> quantify general social = goods, though I expect with a bit 
> of ingenuity some proxies might be found for = some aspects 
> of social wellbeing or satisfaction that could be regarded as 
> outcomes of having accurate information. but this is a road 
> fraught with pitfalls as anyone who has looked at performance 
> measures in public = services can testify..
> Ursula
> --------------------------------------------------------------
> ---------
> Ursula Huws
> Professor of International Labour Studies London Metropolitan 
> University and Director of Analytica Social and Economic Research
> web: www.analyticaresearch.co.uk
> tel: +44 20 7226 8411
> fax: +44 20 7226 0813
> mobile: +44 7711 3292 67
> --------------------------------------------------------------
> ---------
> To find out about the journal Work Organisation, Labour=20 
> and Globalisation visit www.cybertariat.com
> --------------------------------------------------------------
> ---------
> Announcing an important international conference 
> Fragmentation? The future of work in Europe in a global=20 
> economy, Final WORKS conference Rome - Italy, 8-9 October 
> 2008 For more information and registration details, visit 
> http://www.worksproject.be/Conference2/welcome.htm
> 
> -----Original Message-----
> From: email list for Radical Statistics 
> [mailto:[log in to unmask]] = On Behalf Of R.Thomas
> Sent: 26 June 2008 11:01
> To: [log in to unmask]
> Subject: How can we quantify the value of statistics?
> 
> . . asks John Bibby.
> 
> The most obvious answer is the price of newspapers.
> 
> Statistics of prices are the the most widely used statistics 
> because = they benefit buyers and sellers and so support the 
> operation of the market economy.  The best buy in Britain 
> must surely be the Financial Times at
> =A31.50 a time.   The FT gives an order of magnitude more 
> information on
> statistics of prices than any other newspaper. =20
> 
> Are there any other worthy answers?  =20
> 
> Or is the question just a glorification of money as the only 
> way in = which value can be quantified?
> 
> 
> Ray Thomas
> *************************
> 
> 
> -----Original Message-----
> From: email list for Radical Statistics 
> [mailto:[log in to unmask]] = On Behalf Of John Bibby
> Sent: Tuesday, June 24, 2008 2:54 PM
> To: [log in to unmask]
> Subject: Re: HSUG Seminar on Making Use of Health Information 
> - follows = on from previous email
> 
> 
> Does anyone know anything about=20
> 
> What we get for what we spend - on collecting data (i.e. the 
> value of information)?
> 
> How can we quantify the value of statistics?
> 
> JOHN BIBBY
> 
> --=20
> ? ????????? ?????????? ?????? SPAMfighter ??? ??????? 
> ?????????????.=20 ????????? ??????? 510 ??. ?????? ?????, 
> ?????????? ?? ?????????? = ???????.=20 ???????????? ??????? 
> ?????? ?? ????? ????? ????????? ? ?? ???????????
> ???????.=20
> ???????????:http://www.spamfighter.com/lru
> 
> ---------------------------------
> The Open University is incorporated by Royal Charter (RC 
> 000391), an = exempt charity in England & Wales and a charity 
> registered in Scotland (SC = 038302).
> 
> ******************************************************
> Please note that if you press the 'Reply' button your message 
> will go only to the sender of this message.
> If you want to reply to the whole list, use your mailer's 
> 'Reply-to-All' button to send your message automatically to 
> [log in to unmask]
> Disclaimer: The messages sent to this list are the views of 
> the sender = and cannot be assumed to be representative of 
> the range of views held by subscribers to the Radical 
> Statistics Group. To find out more about = Radical Statistics 
> and its aims and activities and read current and past issues 
> = of our newsletter you are invited to visit our web site = 
> www.radstats.org.uk.
> *******************************************************
> 
> ******************************************************
> Please note that if you press the 'Reply' button your message 
> will go only to the sender of this message.
> If you want to reply to the whole list, use your mailer's 
> 'Reply-to-All' button to send your message automatically to 
> [log in to unmask]
> Disclaimer: The messages sent to this list are the views of 
> the sender = and cannot be assumed to be representative of 
> the range of views held by subscribers to the Radical 
> Statistics Group. To find out more about = Radical Statistics 
> and its aims and activities and read current and past issues 
> = of our newsletter you are invited to visit our web site = 
> www.radstats.org.uk.
> *******************************************************
> 
> ******************************************************
> Please note that if you press the 'Reply' button your message 
> will go only to the sender of this message.
> If you want to reply to the whole list, use your mailer's 
> 'Reply-to-All' button to send your message automatically to 
> [log in to unmask]
> Disclaimer: The messages sent to this list are the views of 
> the sender and cannot be assumed to be representative of the 
> range of views held by subscribers to the Radical Statistics 
> Group. To find out more about Radical Statistics and its aims 
> and activities and read current and past issues of our 
> newsletter you are invited to visit our web site www.radstats.org.uk.
> *******************************************************
> 
> ------------------------------
> 
> Date:    Mon, 30 Jun 2008 12:34:19 +0100
> From:    Paul Bivand <[log in to unmask]>
> Subject: Re: How can we quantify the value of statistics?
> 
> In relation to the particular problem - The education 
> department (then DfES= , now DIUS) modelled basic skills 
> needs and ESOL needs down to local author= ity and ward 
> levels based on a Skills for Life Survey and census. They 
> desc= ribe the methodology here: 
> http://www.dfes.gov.uk/readwriteplus_skillsforli=
> fesurvey/methodology.shtml
> 
> These figures have certainly been used by local authorities 
> etc in bidding = for challenge funds. Not quite so sure as to 
> whether they are part of the L= SC's skills for life funding 
> distribution methods.
> 
> I rather find the estimation of 83.6% of those of Indian 
> ethic identificati= on, 97.7% of Bangladeshi and 93.2% of 
> Pakistani as in need of english as a = second language 
> education distinctly over the top - they may speak their ow= 
> n language at home but actually some of them may be perfectly 
> good english-= speakers (considering as some of my family 
> though not me are tri-lingual).
> 
> Paul Bivand
> 
> ---------------------------------------------------------
> Paul Bivand
> Head of Analysis and Statistics
> Direct Line: 020 7840 8335
> 
> Inclusion
> 3rd floor, 89 Albert Embankment, London SE1 7TP
> Tel: 020 7582 7221
> Fax: 020 7582 6391
> Inclusion website: www.cesi.org.uk
> 
> Consider the environment - do you really need to print this email?
> 
> The contents of this e-mail and any attachment(s) are 
> intended solely for t= he use of the addressee. If you are 
> not the intended recipient please retur= n the e-mail to the 
> sender and delete from your mailbox.
> 
> The Centre for Economic & Social Inclusion is a company 
> limited by guarante= e. Registered in England & Wales number 
> 2458694. Registered address: 89 Alb= ert Embankment, London SE1 7TP
> 
> 
> 
> > -----Original Message-----
> > From: email list for Radical Statistics 
> > [mailto:[log in to unmask]] On Behalf Of John Bibby
> > Sent: 30 June 2008 11:18
> > To: [log in to unmask]
> > Subject: Re: How can we quantify the value of statistics?
> >
> > I agree with Ray's and Ursula's points, viz:
> >         1. Money is not the measure of everything (i.e.
> > 'value' has many
> > dimensions)
> >         2. "Who whom?" is important. (Thank you Mr Lenin!)
> >
> > This is something I come back to every 20 years or so. In 
> 1990 it was 
> > "How can we estimate the value of investment in .... IT 
> systems in GP 
> > surgeries?"
> >
> > Now (2008) my question relates to investment in better data (thus 
> > getting better estimates, thus improving all decisions taken using 
> > that data). My focus initially was on ONE decision i.e. How to 
> > allocate budgets in proportion to the
> > (unknown) number of people in any area with a particular disease or 
> > trait.
> >
> > I have a bit of a handle now on that one very narrow question
> > - I'll be glad to send it to anybody who is interested. It 
> certainly 
> > needs further refining.
> >
> > Thanks to all who have looked at this.
> >
> > JOHN BIBBY
> >
> >
> > All statements are on behalf of aa42.com Limited, a company wholly 
> > owned by John Bibby and Shirley Bibby. See 
> www.aa42.com/mathemagic and 
> > www.mathemagic.org
> >
> > -----Original Message-----
> > From: email list for Radical Statistics 
> > [mailto:[log in to unmask]] On Behalf Of Ursula Huws
> > Sent: 26 June 2008 16:43
> > To: [log in to unmask]
> > Subject: Re: How can we quantify the value of statistics?
> >
> > the question, surely, is: value to whom?
> > one could look at the value of a statistics qualification to the 
> > statistician by comparing the earnings of those with & without such 
> > qualifications, controlling for other variables.
> > one could similarly look at the value to companies by comparing the 
> > profits or market share or some other indicator of size of 
> those with 
> > and without market research departments (or using external 
> consultants 
> > for this), again controlling for other variables.
> > one could perhaps look at the value to the economy as a whole by 
> > quantifying the outputs of statistics-producing bodies (here again 
> > money would probably be the simplest measure) or perhaps, but this 
> > would be trickier, track down the sectors involved in producing 
> > statistics & use the input output tables from the national 
> accounts to 
> > compute what value is added to those sectors they supply.
> > as far as I am aware there is no easy way to quantify 
> general social 
> > goods, though I expect with a bit of ingenuity some proxies 
> might be 
> > found for some aspects of social wellbeing or satisfaction 
> that could 
> > be regarded as outcomes of having accurate information. but 
> this is a 
> > road fraught with pitfalls as anyone who has looked at performance 
> > measures in public services can testify..
> > Ursula
> > --------------------------------------------------------------
> > ---------
> > Ursula Huws
> > Professor of International Labour Studies London Metropolitan 
> > University and Director of Analytica Social and Economic Research
> > web: www.analyticaresearch.co.uk
> > tel: +44 20 7226 8411
> > fax: +44 20 7226 0813
> > mobile: +44 7711 3292 67
> > --------------------------------------------------------------
> > ---------
> > To find out about the journal Work Organisation, Labour and 
> > Globalisation visit www.cybertariat.com
> > --------------------------------------------------------------
> > ---------
> > Announcing an important international conference Fragmentation? The 
> > future of work in Europe in a global economy, Final WORKS 
> conference 
> > Rome - Italy, 8-9 October
> > 2008 For more information and registration details, visit 
> > http://www.worksproject.be/Conference2/welcome.htm
> >
> > -----Original Message-----
> > From: email list for Radical Statistics 
> > [mailto:[log in to unmask]] On Behalf Of R.Thomas
> > Sent: 26 June 2008 11:01
> > To: [log in to unmask]
> > Subject: How can we quantify the value of statistics?
> >
> > . . asks John Bibby.
> >
> > The most obvious answer is the price of newspapers.
> >
> > Statistics of prices are the the most widely used 
> statistics because 
> > they benefit buyers and sellers and so support the operation of the 
> > market economy.  The best buy in Britain must surely be the 
> Financial 
> > Times at
> > =A31.50 a time.   The FT gives an order of magnitude more 
> information on
> > statistics of prices than any other newspaper.
> >
> > Are there any other worthy answers?
> >
> > Or is the question just a glorification of money as the only way in 
> > which value can be quantified?
> >
> >
> > Ray Thomas
> > *************************
> >
> >
> > -----Original Message-----
> > From: email list for Radical Statistics 
> > [mailto:[log in to unmask]] On Behalf Of John Bibby
> > Sent: Tuesday, June 24, 2008 2:54 PM
> > To: [log in to unmask]
> > Subject: Re: HSUG Seminar on Making Use of Health Information
> > - follows on from previous email
> >
> >
> > Does anyone know anything about
> >
> > What we get for what we spend - on collecting data (i.e. 
> the value of 
> > information)?
> >
> > How can we quantify the value of statistics?
> >
> > JOHN BIBBY
> >
> > --
> > ? ????????? ?????????? ?????? SPAMfighter ??? ??????? ?????????????.
> > ????????? ??????? 510 ??. ?????? ?????, ?????????? ??
> > ?????????? ???????.
> > ???????????? ??????? ?????? ?? ????? ????? ????????? ? ?? 
> ???????????
> > ???????.
> > ???????????:http://www.spamfighter.com/lru
> >
> > ---------------------------------
> > The Open University is incorporated by Royal Charter (RC 
> 000391), an 
> > exempt charity in England & Wales and a charity registered 
> in Scotland 
> > (SC 038302).
> >
> > ******************************************************
> > Please note that if you press the 'Reply' button your 
> message will go 
> > only to the sender of this message.
> > If you want to reply to the whole list, use your mailer's 
> > 'Reply-to-All' button to send your message automatically to 
> > [log in to unmask]
> > Disclaimer: The messages sent to this list are the views of 
> the sender 
> > and cannot be assumed to be representative of the range of 
> views held 
> > by subscribers to the Radical Statistics Group. To find out 
> more about 
> > Radical Statistics and its aims and activities and read current and 
> > past issues of our newsletter you are invited to visit our web site 
> > www.radstats.org.uk.
> > *******************************************************
> >
> > ******************************************************
> > Please note that if you press the 'Reply' button your 
> message will go 
> > only to the sender of this message.
> > If you want to reply to the whole list, use your mailer's 
> > 'Reply-to-All' button to send your message automatically to 
> > [log in to unmask]
> > Disclaimer: The messages sent to this list are the views of 
> the sender 
> > and cannot be assumed to be representative of the range of 
> views held 
> > by subscribers to the Radical Statistics Group. To find out 
> more about 
> > Radical Statistics and its aims and activities and read current and 
> > past issues of our newsletter you are invited to visit our web site 
> > www.radstats.org.uk.
> > *******************************************************
> >
> > ******************************************************
> > Please note that if you press the 'Reply' button your 
> message will go 
> > only to the sender of this message.
> > If you want to reply to the whole list, use your mailer's 
> > 'Reply-to-All' button to send your message automatically to 
> > [log in to unmask]
> > Disclaimer: The messages sent to this list are the views of 
> the sender 
> > and cannot be assumed to be representative of the range of 
> views held 
> > by subscribers to the Radical Statistics Group. To find out 
> more about 
> > Radical Statistics and its aims and activities and read current and 
> > past issues of our newsletter you are invited to visit our web site 
> > www.radstats.org.uk.
> > *******************************************************
> >
> 
> ******************************************************
> Please note that if you press the 'Reply' button your message 
> will go only to the sender of this message.
> If you want to reply to the whole list, use your mailer's 
> 'Reply-to-All' button to send your message automatically to 
> [log in to unmask]
> Disclaimer: The messages sent to this list are the views of 
> the sender and cannot be assumed to be representative of the 
> range of views held by subscribers to the Radical Statistics 
> Group. To find out more about Radical Statistics and its aims 
> and activities and read current and past issues of our 
> newsletter you are invited to visit our web site www.radstats.org.uk.
> *******************************************************
> 
> ------------------------------
> 
> End of RADSTATS Digest - 26 Jun 2008 to 30 Jun 2008 (#2008-82)
> **************************************************************
> 
> 

******************************************************
Please note that if you press the 'Reply' button your
message will go only to the sender of this message.
If you want to reply to the whole list, use your mailer's
'Reply-to-All' button to send your message automatically
to [log in to unmask]
Disclaimer: The messages sent to this list are the views of the sender and cannot be assumed to be representative of the range of views held by subscribers to the Radical Statistics Group. To find out more about Radical Statistics and its aims and activities and read current and past issues of our newsletter you are invited to visit our web site www.radstats.org.uk.
*******************************************************