❓ Hon Jim Scott requests the Minister table reviewer's comments on a report regarding air pollution and health outcomes. The Minister details the criticisms and explains that a re-analysis using a more robust method is underway.
AnsweredQoN 167Legislative Council
QuestionView source ↗
Further to Question on Notice 89 of Thursday, 21 June 2001 where I asked that the peer review be tabled, will the Minister table the reviewer’s comments?
AnswerView source ↗
Answered
18 September 2001
Responded by
Minister for Housing and Works representing the Minister for the Environment and Heritage
Response time
41 days
It should be noted that the level of criticism in the reviews is standard for peer review of scientific literature. Both reviewers indicated the APHEA 1 method used for statistical analysis of the time series data (daily health outcomes and daily air pollution measurements) have been superseded by more advanced statistical methods, principally the generalised additive modelling (GAM) approach. In addition the reviewers indicated there had been insufficient detail on the temporal filtering of the data, testing of different lag periods for various parameters, correction of meteorological parameters and insufficient detail provided on the outcome variables and their generation. In essence, this means the reviewers felt that more details on the statistical models needed to be included. The statistical analysis of these data is complex with hundreds of different variables being tested. Not all of the relevant analyses were originally placed in the report as reviewed by Professor Simpson and Dr Goldberg. In response to the reviewer's comments, the complexity and deficiencies of the traditional time series analysis, and in light of further developments in the statistical methodologies used to analyse air pollution data, a complete re-analysis has additionally been undertaken using the case-crossover method. The case-crossover design is more robust in considering the effects of transient risk factors (that is, changes in air pollution levels) for any acute event such as death or hospitalisation. At the time of peer review of the report, the method was not widely used, however in the intervening period it has become the method of choice, as it is less prone to the introduction of spurious associations due to the modelling undertaken in the APHEA approach. A revised report using the case-crossover analysis is being finalised for further peer review and includes the original analysis noting its limitations. It should be noted that the results obtained by both statistical analysis methods are similar. I understand from the Minister for the Environment and Heritage that Professor Nick de Klerk is happy to discuss the report with the Hon Jim Scott if necessary. See tabled paper.
Both reviewers indicated the APHEA 1 method used for statistical analysis of the time series data (daily health outcomes and daily air pollution measurements) have been superseded by more advanced statistical methods, principally the generalised additive modelling (GAM) approach. In addition the reviewers indicated there had been insufficient detail on the temporal filtering of the data, testing of different lag periods for various parameters, correction of meteorological parameters and insufficient detail provided on the outcome variables and their generation. In essence, this means the reviewers felt that more details on the statistical models needed to be included. The statistical analysis of these data is complex with hundreds of different variables being tested. Not all of the relevant analyses were originally placed in the report as reviewed by Professor Simpson and Dr Goldberg. In response to the reviewer's comments, the complexity and deficiencies of the traditional time series analysis, and in light of further developments in the statistical methodologies used to analyse air pollution data, a complete re-analysis has additionally been undertaken using the case-crossover method. The case-crossover design is more robust in considering the effects of transient risk factors (that is, changes in air pollution levels) for any acute event such as death or hospitalisation. At the time of peer review of the report, the method was not widely used, however in the intervening period it has become the method of choice, as it is less prone to the introduction of spurious associations due to the modelling undertaken in the APHEA approach. A revised report using the case-crossover analysis is being finalised for further peer review and includes the original analysis noting its limitations. It should be noted that the results obtained by both statistical analysis methods are similar. I understand from the Minister for the Environment and Heritage that Professor Nick de Klerk is happy to discuss the report with the Hon Jim Scott if necessary. See tabled paper.
In essence, this means the reviewers felt that more details on the statistical models needed to be included. The statistical analysis of these data is complex with hundreds of different variables being tested. Not all of the relevant analyses were originally placed in the report as reviewed by Professor Simpson and Dr Goldberg. In response to the reviewer's comments, the complexity and deficiencies of the traditional time series analysis, and in light of further developments in the statistical methodologies used to analyse air pollution data, a complete re-analysis has additionally been undertaken using the case-crossover method. The case-crossover design is more robust in considering the effects of transient risk factors (that is, changes in air pollution levels) for any acute event such as death or hospitalisation. At the time of peer review of the report, the method was not widely used, however in the intervening period it has become the method of choice, as it is less prone to the introduction of spurious associations due to the modelling undertaken in the APHEA approach. A revised report using the case-crossover analysis is being finalised for further peer review and includes the original analysis noting its limitations. It should be noted that the results obtained by both statistical analysis methods are similar. I understand from the Minister for the Environment and Heritage that Professor Nick de Klerk is happy to discuss the report with the Hon Jim Scott if necessary. See tabled paper.
In response to the reviewer's comments, the complexity and deficiencies of the traditional time series analysis, and in light of further developments in the statistical methodologies used to analyse air pollution data, a complete re-analysis has additionally been undertaken using the case-crossover method. The case-crossover design is more robust in considering the effects of transient risk factors (that is, changes in air pollution levels) for any acute event such as death or hospitalisation. At the time of peer review of the report, the method was not widely used, however in the intervening period it has become the method of choice, as it is less prone to the introduction of spurious associations due to the modelling undertaken in the APHEA approach. A revised report using the case-crossover analysis is being finalised for further peer review and includes the original analysis noting its limitations. It should be noted that the results obtained by both statistical analysis methods are similar. I understand from the Minister for the Environment and Heritage that Professor Nick de Klerk is happy to discuss the report with the Hon Jim Scott if necessary. See tabled paper.
At the time of peer review of the report, the method was not widely used, however in the intervening period it has become the method of choice, as it is less prone to the introduction of spurious associations due to the modelling undertaken in the APHEA approach. A revised report using the case-crossover analysis is being finalised for further peer review and includes the original analysis noting its limitations. It should be noted that the results obtained by both statistical analysis methods are similar. I understand from the Minister for the Environment and Heritage that Professor Nick de Klerk is happy to discuss the report with the Hon Jim Scott if necessary. See tabled paper.
A revised report using the case-crossover analysis is being finalised for further peer review and includes the original analysis noting its limitations. It should be noted that the results obtained by both statistical analysis methods are similar. I understand from the Minister for the Environment and Heritage that Professor Nick de Klerk is happy to discuss the report with the Hon Jim Scott if necessary. See tabled paper.
I understand from the Minister for the Environment and Heritage that Professor Nick de Klerk is happy to discuss the report with the Hon Jim Scott if necessary. See tabled paper.
Both reviewers indicated the APHEA 1 method used for statistical analysis of the time series data (daily health outcomes and daily air pollution measurements) have been superseded by more advanced statistical methods, principally the generalised additive modelling (GAM) approach. In addition the reviewers indicated there had been insufficient detail on the temporal filtering of the data, testing of different lag periods for various parameters, correction of meteorological parameters and insufficient detail provided on the outcome variables and their generation. In essence, this means the reviewers felt that more details on the statistical models needed to be included. The statistical analysis of these data is complex with hundreds of different variables being tested. Not all of the relevant analyses were originally placed in the report as reviewed by Professor Simpson and Dr Goldberg. In response to the reviewer's comments, the complexity and deficiencies of the traditional time series analysis, and in light of further developments in the statistical methodologies used to analyse air pollution data, a complete re-analysis has additionally been undertaken using the case-crossover method. The case-crossover design is more robust in considering the effects of transient risk factors (that is, changes in air pollution levels) for any acute event such as death or hospitalisation. At the time of peer review of the report, the method was not widely used, however in the intervening period it has become the method of choice, as it is less prone to the introduction of spurious associations due to the modelling undertaken in the APHEA approach. A revised report using the case-crossover analysis is being finalised for further peer review and includes the original analysis noting its limitations. It should be noted that the results obtained by both statistical analysis methods are similar. I understand from the Minister for the Environment and Heritage that Professor Nick de Klerk is happy to discuss the report with the Hon Jim Scott if necessary. See tabled paper.
In essence, this means the reviewers felt that more details on the statistical models needed to be included. The statistical analysis of these data is complex with hundreds of different variables being tested. Not all of the relevant analyses were originally placed in the report as reviewed by Professor Simpson and Dr Goldberg. In response to the reviewer's comments, the complexity and deficiencies of the traditional time series analysis, and in light of further developments in the statistical methodologies used to analyse air pollution data, a complete re-analysis has additionally been undertaken using the case-crossover method. The case-crossover design is more robust in considering the effects of transient risk factors (that is, changes in air pollution levels) for any acute event such as death or hospitalisation. At the time of peer review of the report, the method was not widely used, however in the intervening period it has become the method of choice, as it is less prone to the introduction of spurious associations due to the modelling undertaken in the APHEA approach. A revised report using the case-crossover analysis is being finalised for further peer review and includes the original analysis noting its limitations. It should be noted that the results obtained by both statistical analysis methods are similar. I understand from the Minister for the Environment and Heritage that Professor Nick de Klerk is happy to discuss the report with the Hon Jim Scott if necessary. See tabled paper.
In response to the reviewer's comments, the complexity and deficiencies of the traditional time series analysis, and in light of further developments in the statistical methodologies used to analyse air pollution data, a complete re-analysis has additionally been undertaken using the case-crossover method. The case-crossover design is more robust in considering the effects of transient risk factors (that is, changes in air pollution levels) for any acute event such as death or hospitalisation. At the time of peer review of the report, the method was not widely used, however in the intervening period it has become the method of choice, as it is less prone to the introduction of spurious associations due to the modelling undertaken in the APHEA approach. A revised report using the case-crossover analysis is being finalised for further peer review and includes the original analysis noting its limitations. It should be noted that the results obtained by both statistical analysis methods are similar. I understand from the Minister for the Environment and Heritage that Professor Nick de Klerk is happy to discuss the report with the Hon Jim Scott if necessary. See tabled paper.
At the time of peer review of the report, the method was not widely used, however in the intervening period it has become the method of choice, as it is less prone to the introduction of spurious associations due to the modelling undertaken in the APHEA approach. A revised report using the case-crossover analysis is being finalised for further peer review and includes the original analysis noting its limitations. It should be noted that the results obtained by both statistical analysis methods are similar. I understand from the Minister for the Environment and Heritage that Professor Nick de Klerk is happy to discuss the report with the Hon Jim Scott if necessary. See tabled paper.
A revised report using the case-crossover analysis is being finalised for further peer review and includes the original analysis noting its limitations. It should be noted that the results obtained by both statistical analysis methods are similar. I understand from the Minister for the Environment and Heritage that Professor Nick de Klerk is happy to discuss the report with the Hon Jim Scott if necessary. See tabled paper.
I understand from the Minister for the Environment and Heritage that Professor Nick de Klerk is happy to discuss the report with the Hon Jim Scott if necessary. See tabled paper.
Explore WA Government Data
Search the full archive in the free dashboard, or query programmatically via API.
Explore more
Government Gazette
Appointments, regulatory notices, planning changes.
Hansard
Debates, questions, speeches and sentiment.
Tabled Papers
Reports and documents tabled in Parliament.
Committees
Committee profiles and recent reports.
Regulations
Subsidiary legislation with filters and summaries.
Bills
Proposed laws and parliamentary progress.
Acts
Current WA legislation and summaries.
Explanatory Memoranda
Bills with EMs (text/PDF) available.
Members
MP profiles, party breakdown and rankings.
Pollie Rankings
Data-driven rankings across 19 categories.
Amendment Chains
Track how schemes and regulations evolve over time.