Click here to load reader

Geographical Ways of looking at segregation Rich Harris, University of Bristol, UK School of Geographical Sciences & Centre for Market and Public Organisation

  • View
    213

  • Download
    0

Embed Size (px)

Text of Geographical Ways of looking at segregation Rich Harris, University of Bristol, UK School of...

  • Slide 1

Geographical Ways of looking at segregation Rich Harris, University of Bristol, UK School of Geographical Sciences & Centre for Market and Public Organisation Rich Harris, University of Bristol, UK School of Geographical Sciences & Centre for Market and Public Organisation Slide 2 Outline Focus on two opportunities Modelling micro data geographically Mapping school catchment areas to identify polarization Building geographical models Example of Geographically Weighted Regression Common framework for analysis R Open source software for computing and statistics http://cran.r-project.org/ Slide 3 Outline Focus on two opportunities Modelling micro data geographically Mapping school catchment areas to identify polarization Building geographical models Example of Geographically Weighted Regression Common framework for analysis Slide 4 School choice & Social segregation? Slide 5 Ethnic polarization? Slide 6 Geographical perspective Economic theory and government policy suggest schools operate within local markets to attract pupils and funding. However, there is a deficit of understanding about the scales and configurations of those admission spaces. Whilst competition for pupils and for school places is assumed to operate at some localised scale, the actual geographies of the markets, where they overlap and where they might be changing are generally unknown. Aim: To understand processes of polarization in the context of the local markets within which schools operate. Task: To use micro-data to model those markets Slide 7 The data PLASC Pupil Level Annual Census Returns Data on all pupils in primary (and secondary) schools in England 2005/6 data Information on state educated primary school students (5- 11 years old) 'Self-identified' ethnic category collected from parents when students enrol Also records postcode unit of pupils' homes Which they school they attend School type (selective? Faith school?) Measure of deprivation (take a free school meal)? Slide 8 Defining core catchments Imagine centring a polygon at (mid-x, mid-y) based on the residential postcodes of pupils attending a school Let the polygon grow outwards Slide 9 The direction of growth is determined as that which returns highest n1 / n2 where n1 is number of pupils in area going to the school n2 is all pupils in the area (go to any school) Measuring prevalence Slide 10 Continues until a certain proportion of all pupils who attend the school are enclosed p = 0.30 Slide 11 Continues until a certain proportion of all pupils who attend the school are enclosed p = 0.40 Slide 12 Continues until a certain proportion of all pupils who attend the school are enclosed p = 0.50 Catchment is then defined as the convex hull for pupils of school within the search area. Slide 13 London Slide 14 Evidence of polarisation Are particular social (ethnic) groups travelling further to school than they need to? Are there (primary) schools with an intake not representative of the local community? Are there (primary) schools with shared admission spaces but where one has a very different intake to the other? Study region: London Slide 15 Evidence of polarisation Are particular social (ethnic) groups travelling further to school than they need to? Are there (primary) schools with an intake not representative of the local community? Are there (primary) schools with shared admission spaces but where one has a very different intake to the other? Study region: London Slide 16 Defining Near Define as being near to a pupil any primary school that has a core catchment that includes the pupils residential postcode Here the pupil has three near schools Slide 17 Proportion attending any near school (target catchment p=0.50) LONDON Slide 18 Evidence of polarisation Are particular social (ethnic) groups travelling further to school than they need to? Are there (primary) schools with an intake not representative of the local community? Are there (primary) schools with shared admission spaces but where one has a very different intake to the other? Study region: London Slide 19 Pairwise Comparisons Look inside the catchments Expected intake Vs Actual ethnic profile of each school Compare the profiles of locally competing schools ones that overlap (strongly) in terms of their core catchment areas Slide 20 Visual Summary (LONDON) Consider those schools with highest expected % Black Caribbean Slide 21 Visual Summary (LONDON) Consider those schools with highest expected % Bangladeshi Slide 22 Outline Focus on two opportunities Modelling micro data geographically Mapping school catchment areas to identify polarization Building geographical models Example of Geographically Weighted Regression Common framework for analysis Slide 23 Example DataNumerator/DenominatorSource Y Higher education participation Successful entrants under 21 in UCAS data, for 20022005/ Census population 1417 2007 Index of Multiple Deprivation X1X1 No qualifications Adults aged 2554 in the area with no qualifications or with qualifications below NVQ Level 2, for 2001 /All adults aged 25 54. 2007 Index of Multiple Deprivation X2X2 No post 16 qualifications Those aged 17 still receiving Child Benefit in 2006/ Those aged 15 receiving Child Benefit in 2004. 2007 Index of Multiple Deprivation X3X3 Average KS4 Points Total score of pupils taking KS4 in 2004 and 2005 in maintained schools from the NPD / All pupils in their final year of compulsory schooling in maintained schools for 2004 and 2005 from PLASC. 2007 Index of Multiple Deprivation X4X4 Four or more cars Four or more cars in household / total households2001 Census X5X5 AsianTotal Indian, Pakistani, Bangladeshi people / total people2001 Census Slide 24 Example DataNumerator/DenominatorSource Y Higher education participation Successful entrants under 21 in UCAS data, for 20022005/ Census population 1417 2007 Index of Multiple Deprivation X1X1 No qualifications Adults aged 2554 in the area with no qualifications or with qualifications below NVQ Level 2, for 2001 /All adults aged 25 54. 2007 Index of Multiple Deprivation X2X2 No post 16 qualifications Those aged 17 still receiving Child Benefit in 2006/ Those aged 15 receiving Child Benefit in 2004. 2007 Index of Multiple Deprivation X3X3 Average KS4 Points Total score of pupils taking KS4 in 2004 and 2005 in maintained schools from the NPD / All pupils in their final year of compulsory schooling in maintained schools for 2004 and 2005 from PLASC. 2007 Index of Multiple Deprivation X4X4 Four or more cars Four or more cars in household / total households2001 Census X5X5 AsianTotal Indian, Pakistani, Bangladeshi people / total people2001 Census Slide 25 Global regression model (n = 31 378 ) Standard errort value Significan t at 0.01 ? (Intercept)3.6200.0213170.2Yes X 1 : No Qualifications-0.0270.0002-152.5Yes X 2 : No Post 16 Qualifications-0.0020.0001-15.1Yes X 3 : Average KS4 attainment0.0030.000252.6Yes X 4 : Four or more cars0.0180.000535.9Yes X 5 : Asian0.0120.000268.1Yes Slide 26 But Geographical variation in the Asian coefficient Slide 27 What is it? Extension of regression model Allows model to vary over space How it works... Geographically Weighted Regression Regression Point Data Points Slide 28 Summary of GWR model (global value) (u,v) Min (u,v) 1 st decile (u,v) 3 rd decile (u,v) Median (u,v) 7 th decile (u,v) 9 th decile (u,v) Max. (u,v) IQR (Intercept)3.620 X 1 : No Qualifications -0.027-0.047-0.036-0.032-0.030-0.027-0.023-0.0140.006 X 2 : No Post 16 Qualifications -0.002-0.008-0.003-0.002-0.001 0.0000.0050.002 X 3 : Average KS4 attainment 0.0030.0000.0010.0020.003 0.0040.0060.001 X 4 : Four or more cars 0.018-0.0130.0110.0160.0210.0270.0400.1010.014 X 5 : Asian0.012-0.156-0.0060.0090.0120.0150.0200.2170.008 Slide 29 Geographical variation in the Asian coefficient Slide 30 Outline Focus on two opportunities Modelling micro data geographically Mapping school catchment areas to identify polarization Building geographical models Example of Geographically Weighted Regression Common framework for analysis Slide 31 Framework for analysis R Open source software for statistical computing Available at CRAN http://cran.r-project.org/ WUN GIS Academy eSeminars about Spatial analysis in R http://www.wun.ac.uk/g gisa/ Slide 32 Thank you!

Search related