Dear Kate,
Thank you.
I shall read the book before troubling you (or the Rad Stats list) again
but did you mean to write
y= -4.941 + 3.539(prevalence of mental illness)
ie the regression of inequality on illness? Or vice versa?
Either way, it does not look like a (weighted?) least squares between
country regression line. It does not appear to go through the overall
mean.
Best wishes
Jane
> Jane,
>
> 1. It is a simple regression line, y= -4.941 + 3.539(prevalence of mental
> illness), data sources cited in book and website
> 2. It is the 20:20 ratio, ditto for data sources
> 3. We won't be revising our website, based on the overwhelmingly positive
> worldwide responses received so far.
>
> Cheers, Kate
> Kate E Pickett, PhD Department of Health Sciences University of York
> (01904) 321377
>
> [log in to unmask] wrote: Dear Kate, Thanks for this, which I now
> forward to the Radical Statistics list. If you would like to join it
> please go to our website www.radstats.org.uk for information. I realise
> that you are busy now but when you have time could you reply to my
> questions (copied below) and, in particular, consider revising the book's
> website. Many thanks Jane Dear Rad Stats Group (as
> the email I'm replying to was copied to you all), To answer more
> questions about the data/methods used in our book The Spirit Level and
> more criticisms of our choice to present simple charts within
> it, let me start by repeating what I said in previous message. Our book
> was written with the intention of making the evidence on the effects of
> inequality known to politicians and the wider public. The book presents
> evidence accumulated over a long period of joint academic endeavour and
> almost all the findings have been published previously in peer-reviewed
> journals with full descriptions of methods, results, statistical tests
> galore. Some of those papers have been more widely read than others, but
> with our book we were trying to reach beyond the academic journals and
> our statistical and epidemiological colleagues. (And apparently it is
> only since our work has been in the newspapers that it has
> reached many of you!) As our book has been printed three times
> in as many weeks, we are clearly reaching that broader
> audience. And most people we have encountered have told us how
> pleased they are to have charts they can understand. Not even the most
> dedicated statistician would include correlation coefficicents, p-values
> and descriptions of regression methods in an article they were writing
> for a newspaper. I'm sorry that you feel you will "fume" if
> you read our book - luckily there is an alternative (although you will
> miss out on the cartoons!): Pickett KE, Mookherjee J, Wilkinson RG.
> Teenage births and violence are related to income inequality among rich
> countries. American Journal of Public Health
> 2005;95:1181-1183. Pickett KE, Kelly S, Leach R, Brunner E,
> Wilkinson RG. Wider income gaps, wider waistbands? An ecological study
> of income inequality and obesity. Journal of Epidemiology and
> Community Health 2005;59: 670-674. Wilkinson RG, Pickett KE.
> Income inequality and health: A review and explanation of the evidence.
> Social Science and Medicine 2006; 62:1768-1784. Pickett KE, James O,
> Wilkinson RG. Income inequality and the prevalence
> of mental illness: A preliminary international analysis. Journal of
> Epidemiology and Community Health 2006;60:646-647.
> Wilkinson RG, Pickett KE. Health inequalities and the UK Presidency of
> the EU. Lancet 2006; 367:1126-1128. Wilkinson RG, Pickett KE. IQ and
> economic development: A response to Kanazawa. British Journal of Health
> Psychology, 2007;12(2)161-166. Wilkinson RG, Pickett KE. The problems
> of relative deprivation: why some societies do better
> than others. Social Science and Medicine. Social Science
> & Medicine 65 (2007) 1965–1978. Pickett KE,
> Wilkinson RG. Child well-being and income inequality in rich
> societies: Ecological cross sectional study. BMJ 2007;
> 335(7629):1080-1086. Wilkinson RG, Pickett KE. Income inequality and
> social gradients in health. American Journal of Public Health 2008 98:
> 699-704. Wilkinson RG, Pickett KE. The consequences of relative
> deprivation. In press: Annual Review of Sociology,
> 2009; 35. Best wishes, Kate E Pickett, PhD Department of Health
> Sciences University of York (01904) 321377
> [log in to unmask] wrote: Dear Kate, Thank you for the
> information below. I have some further questions: 1. What are the lines
> drawn on the graphs? On some graphs they could be the regression lines of
> Y (whatever) on X (income inequality), but on the mental illness vs
> income inequality graph it is clearly not the regression line. What is
> it? 2. Looking at the Infant deaths vs Income Inequality graph, it does
> not look as if you have plotted the 20:20 measure of income inequality.
> From the "Notes on the statistical sources used in the Spirit Level" the
> distance between UK (about 7) and US (about 8) should be about 1 unit and
> between UK and Sweden (
--
Mrs Jane Galbraith
Honorary Research Associate
Department of Statistical Science
University College London
Gower Street
London WC1E 6BT
[log in to unmask]
******************************************************
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.
*******************************************************
|
