• Andy Turner's MoSeS Progress Report 2006-11-21 Page

  • [An image of Andy Turner]

  • Introduction

    • This web page is a progress report for MoSeS for the period 2006-10-02 to 2006-11-21.
    • Contents:
      • Summary
      • Details
      • References
      • Validation and Metadata

  • Summary

    • During the reporting period the School of Geography Beowulf machine has been used intensively.
    • This use produced sequences of results for Leeds which were analysed iteratively.
    • Some problems were identified, some issues remain, but some major ones have been resolved.
    • The production of results has gone hand in hand with the development of methods and further output to analyse data and performance.
      • The production of Observed vs Expected plots and a Ordinary Least Squares Linear Regression has been largely automated via the use of JFreeChart and Jakarta Commons Math.
      • A comparison of tables CAS001 and CAS002 is interesting:
        • MoSeS CAS001vCAS002AgeGroupComparison Page
    • Next Steps:
      • Automate the mapping of results.
      • Documentation and new code release.
      • A re-examination of the GA optimisation.

  • Details

    • There were two types of two types of result:
      • Results were based on optimising with Age Group/Gender Variables.
        • OA level constraints and optimisation
          • ToyModel_SWR_OA_HSARHP_ISARCEP_0_10_10000_1_100_12_10_MarkOutput2OA_RegressionReport (Result at OA resolution)
          • ToyModel_SWR_OA_HSARHP_ISARCEP_0_10_10000_1_100_12_10_MarkOutput2MSOA_RegressionReport (Result aggregated to MSOA resolution)
        • ToyModel_SWR_MSOA_HSARHP_ISARCEP_0_10_10000_1_200_96_10_MarkOutput2MSOA_RegressionReport (Result aggregated to MSOA resolution) (Result at MSOA resolution - using constraints and optimisation at MSOA resolution)
      • Results were based on optimising with Age Group/Gender, Employment/Gender and Household Composition Variables.
        • OA level constraints and optimisation
          • Results for OA
          • Results aggregated to MSOA
        • MSOA level constraints and optimisation
    • Age80AndOver problem:
      • Results produced on 2006-11-15
        • ToyModel_SWR_OA_HSARHP_ISARCEP_0_100_10000_2_100_12_10_MarkOutput2MSOA_RegressionReport
        • ToyModel_SWR_OA_HSARHP_ISARCEP_0_100_10000_2_100_12_10_MarkOutput2OA_RegressionReport
      • Results produced on 2006-11-13
        • ToyModel_SWR_OA_HSARHP_ISARCEP_0_100_10000_2_100_12_10_MarkOutput2OA_RegressionReport
        • ToyModel_SWR_OA_HSARHP_ISARCEP_0_100_10000_2_100_12_10_MarkOutput2MSOA_RegressionReport
    • CAS002 wrong data problem:
      • A comparison of tables CAS001 and CAS002 confirmed that there was a problem with the loading of CAS002 data. The results are now sensible and interesting:
        • MoSeS CAS001vCAS002AgeGroupComparison Page

  • References

    • Andy Turner's MoSeS Home Page
    • Andy Turner's MoSeS Progress Report 2006-10-02 Page

  • Validation And Metadata

    • [Validate CSS]
    • This is Version 0.0.3 of this page published on 2006-11-21.
    • Page hosted on the School of Geography webserver at the University of Leeds.
    • Copyright: Andy Turner, University of Leeds