Macro Editing Workshop Held in September 2006
The Editing Re-engineering Team was formed in 2003 to help business collections improve their editing practices and to provide tools to support them. This task is proving to be difficult and complex as editing is not an 'exact' science. For example, it is relatively simple to algebraically describe estimation techniques which can be applied to many different collections. Given an input file of microdata, estimation will transform them into estimates as specified. Editing, on the other hand, is less straight-forward.
Editing involves detection, resolution, and treatment. Firstly, anomalies must be detected. These can range from unit records through to estimates. Once an anomaly is detected, it must be determined whether some form of remedial action is required (resolution). The last step involves the application of the method chosen to treat the anomaly. The treatment will depend on the source of the problem which could be anything from erroneous source data, to incorrect or poor estimation or imputation, to problems in the data processing system, to incorrect auxiliary data, or even to badly defined concepts.
The editing team has developed a general editing framework which encompasses the editing of unit records (micro editing) through to the editing of estimates (macro editing). The framework and associated editing solutions need to fit within the evolving business collection end-to-end framework and infrastructure. The team's approach has been to progress the work via collaborative arrangements between the editing re-engineering, business collection, methodology, and IT areas. While progress is being made on the micro editing front, work needs to start on the macro editing front in order to integrate with the end-to-end progress. As a start, a workshop on macro editing was held in Canberra on 12 September 2006 involving all stakeholders.
Business collection areas presented graphical drill-down tools, macro editing reports and databases, ideas for future tools, and assessments of systems currently in use. Technical Services Division (TSD) staff presented sessions on SAS Business Intelligence and data visualisation tools. Methodology Division (MD) staff outlined an example of best practice macro editing for aggregates which involved a combination of subjective and objective detection techniques and interactive drill-down functionality. MD and TSD staff jointly demonstrated the use of graphics in macro editing using SAS Insight. Macro significance scores were used as the basis of the objective component while the interactive functionality of SAS Insight was utilised for the subjective component. The editing team led the two final sessions which aimed to:
Participants were asked to fill in a questionnaire indicating their preferences for various macro editing functionalities and system components. The feedback from these questionnaires and discussion at the workshop indicate that:
- identify the key features required for future corporate macro editing tools; and
- establish main priorities for macro editing tools in preparation for a business case for the end-to-end Program Board.
For further information, please contact Lynne Bismire on (02) 6252 5644 for general editing re-engineering issues and the business case. For methodological issues, please contact Keith Farwell on (03) 6222 5889, and for computing and IT issues, please contact Cathie Guilfoyle on (02) 6252 5027.
Email: email@example.com; firstname.lastname@example.org; email@example.com
- a detection tool based on both objective and subjective methods received the highest importance rating;
- for the subjective aspect of the tool, areas want the flexibility to choose different ways to set up and display their data;
- editors must be able to dynamically drill down to resolve anomalous aggregates;
- it was essential that functionality existed to facilitate a compositional breakdown of aggregates, followed by rankings of the top contributors within these components;
- it was desired that errors at the unit level should be able to be corrected directly in Blaise;
- staff want to be able to see the impacts of macro editing changes in real time; and perhaps the most surprising result,
- there was a strong desire to have a tool to document the results of investigations or actions taken in respect of macro level anomalies.