|
Applied Statistics 2019 - Measuring and Analysing Time Series Data in Horizontal Time Dimension |
|
|
|
|
Sunday, 22 September 2019 |
The presentation of Professor Pavle Sicherl at the international statistics conference Applied Statistics 2019 at Bled (Ribno), organised by the Slovenian Statistical Society, was entitled Measuring and Analysing Time Series Data in Horizontal Time Dimension - Insights Beyond Conventional Static AnalysisTime distance method adds innovative parallel generic system for analysing indicators in both static and time dimensions relevant across many indicators and many domains.
|
|
Innovative framework for dynamic indicator analysis beyond GDP |
|
|
|
|
Monday, 25 September 2017 |
Summary and conclusions
Well-being and development embody multidimensional and long-term experience, going much beyond the GDP. The focus in the media is especially in GDP growth rates. Over time, UNDP, OECD, and European Commission have participated in the conferences, indicator developments, and policy discussions of 'Beyond GDP Initiatives'. In the article, the analyses of beyond the GDP indicators are enriched by the application of the dynamic time distance methodology to complement the results of the usual mostly static tools.
With time distance methodology, a new perspective related to time does not replace but rather adds a new dimension to existing analysis across many variables, fields of concern, and units of comparison. Section 3 deals with the broadened concept of measuring and evaluating the magnitude of inequalities in two dimensions. LEVEL-TIME matrix in section 4 is an additional option of visualisation of time series data which helped to establish that GDP underestimated the scale of damage of the financial crisis in the EU for selected indicators. Section 5 emphasises the function of the time distance tool for monitoring implementation of targets parallel to other methods, with application to about 150 cases of EU2020 targets; as well as to measuring implementation of the UN Millennium Developments Goals that can be used also for the UN initiative of the 2030 Agenda for Sustainable Development. This transparent and innovative method for monitoring implementation of targets at all levels is available but not yet utilised. It can bring a new easily understandable perception of the magnitude of the gap between the actual implementation and proclaimed targets at many levels: it can help governments, the civil society, and businesses in a broader understanding of continuous policy debate and necessary adjustments. The free software tool is available.
The empirical study exposes that GDP underestimated the scale of damage of the financial crisis as selected time matrices showed deterioration in many indicators: - Employment rate fell in 20 EU countries (71% of countries);
- Risk of poverty as percent of total population increased in 24 EU countries (86%);
- Income distribution worsened as Gini coefficient and income quartile share ratio increased in 25 EU countries (89% of countries);
- The most shocking conclusion is that the value of the share of growth fixed capital formation in GDP decreased in all 28 EU countries (100%!). This negatively affected the medium/long-term rate of growth of GDP.
Table 2 shows possible scheme and numerical values for analysing time distance deviations for implementation of five selected headline indicators towards the EU2020 for the entire EU and national targets. It is a clear example of simplicity with an overview of about 150 cases of EU2020 targets, showing the results of 5 selected EU2020 indicators, 28 countries, and the EU aggregate in one single table. Such time distance monitoring supervision could become a standard procedure in numerous other activities of the Commission on the national and local levels, e.g. monitoring and evaluation implementation of budgets, plans, projects, structural funds, etc.
|
|
SYSTEM FOR MONITORING IMPLEMENTATION OF TARGETS: Present MDGs and Post-2015 SDGs |
|
|
|
|
Tuesday, 14 July 2015 |
Results for 10 selected MDG indicators for Developing Regions, 7 world regions, China and India, and for 125-154 countries for four selected indicators
The Millennium Development Goals (MDGs) are coming towards conclusion and the international community is deciding on the scope and the timetable for a set of Sustainable Development Goals (SDGs). The study “SYSTEM FOR MONITORING IMPLEMENTATION OF TARGETS: Present MDGs and Post-2015 SDGs” includes three main parts:
1. Outline of time distance methodology, with S-time-matrix format to present data over many units and over time, two generic statistical measures S-time-distance and S-time-step. The new generic time distance approach, which is easy to understand and to communicate, offers a new view of reality that significantly complements existing mostly static measures of inequality in many domains. In the information age this new view of the existing databases should be evaluated as an important contribution to a more efficient utilisation of the existing data.
2. Empirical part uses the most recent data from the UN 2015 MDG Report Statistical annex and MDG database updated on July 6, 2015 and shows implementation of MDG targets for
a) 10 selected MDG indicators for Developing Regions, 7 world regions, China and India b) details for implementation of four MDG indicators for 125-154 countries, year by year.
It provides new parallel system of monitoring implementation of targets based on deviations of actual values from the line to the target, thus complementing (not replacing) the existing mostly static measures of inequality and of implementation of targets. Expressed in time units, S-time-distance is easily understood by policy makers, managers, media and general public, thus being an excellent presentation tool for policy analysis and debate. It can help us to form a new perception of the magnitude of the gap between the implementation and proclaimed targets for a given indicator as well as across more indicators. 3. This study offers a system for time distance monitoring implementation of targets for many domains and levels (global, regional, national, local, business). The detailed application to current MDGs could be immediately applied for the post-2015 SDGs targets when they are determined. It can be with the help of Sustainable Development Solutions Network facilities further refined and distributed to complement existing methods of monitoring implementation. We added complementary possibility to look at indicator differences in the parallel universe of time, adding new vocabulary in the semantics of discussing and analysing differences in the real world. Free web monitoring tool is provided. SDG initiative is an important field where this additional dimension could be fruitfully applied making some aspects more transparent and understandable to people as the main potential beneficiaries and participants in the implementation. Printed version is available on Amazon.com FULL TEXT: |
|
Time distance monitoring of implementation of targets |
|
|
|
|
Wednesday, 18 June 2014 |
Test application for EU2020 targets by countries and free software tool
Monitoring implementation of targets is an integral part of policy making at many levels and in many domains. The innovation is that implementation of targets is described in two dimensions: static deviation from the line to target at a given point in time and S-time-deviation at a given level of the indicator. Describing the implementation of targets as leading or lagging in time against the line to well-known targets is a very useful application in the policy debate that enhances knowledge, giving data a value beyond spreadsheets. Expressed in time units, S-time-distance is easily understood by policy makers, managers, media and general public thus being an excellent presentation tool for policy analysis and debate. It can help us to form a new perception of the magnitude of the gap between the implementation and proclaimed targets for a given indicator as well as across more indicators.
We measure deviations in two dimensions. Firstly, one can measure the difference in variables at a given point in time. And secondly, discrepancies in time (either time lead or time lag) are measured. Monitoring implementation in time is like comparing train or bus arrivals with the timetable provided for each mode of transport. The statistical chart uses the same identifiers as Formula 1 on TV: drivers who score a minus at time distance are shown in green to signify that they are ahead in time.
The table for EU 28 countries for 2013 (or 2012) shows the results from 2010 on. Yet the summary results confirm the earlier conclusions. For the headline indicator employment rate 20 countries are behind the schedule, 11 of them had in 2013 values below those in 2010 starting year. For 11 countries there was no progress in the 2010-2013 period for employment rate. The earlier graph that contained also the worse years of the financial crisis showed even a more serious situation. The time distance method, either for monitoring or for benchmarking in the time perspective, brings the second dimension of deviations or disparities that the present state-of-the-art is neglecting.
For early leavers nine countries were in 2013 already better than their 2020 targets, this holds true for tertiary attainment for 10 countries; with only six countries being behind the schedule for both indicators. The headline indicator renewable energy also more countries are ahead of schedule than behind it, but with fewer cases that already reached the 2020 targets. R&D in GDP indicates a different picture, with 9 countries ahead and 16 countries behind the schedule; overall it is closer with the employment rate situation than with the other three indicators.
The average for EU28 S-time-distance deviations express the situation with being ahead or behind the track to 2020 targets in simple terms: employment rate is more than 3 years behind, R&D 1.2 years behind, renewably energy 0.6 years, early leavers 2.1 years and tertiary attainment 2.4 years, ahead of the line to the 2020 target.
Software for time distance monitoring of targets from your own data:
|
|
MDG implementaion by Gaptimer Progress Chart 2013 |
|
|
|
|
Wednesday, 14 August 2013 |
Latest update of the article in the Guardian by Professor Pavle Sicherl available also in the wikiprogress ProgBlog
UNDP Report 2013 in the two page summary overview started the first sentence on the first indicator: ‘The world reached the poverty reduction target five years ahead of schedule.’ The first row of the Gaptimer MDG Progress Chart also shows that the 2015 poverty reduction targets have already been achieved even earlier in three world regions (also China was an excellent performer with time lead of even 13 years, reaching the 2015 target in 2002). This is an update of the publication in The Guardian by Professor Pavle Sicherl based on the older data from the 2012 MDG report and reported ealier on this web page. Monitoring implementation with time distance deviation is like comparing train or bus arrivals with the respective timetables. In the context of the MDGs, it amounts to comparing the time of actual implementation with the time stipulated by the schedule to the 2015 target. We are therefore measuring the gap in time.
 Source: Own calculations based on data from UN, The Millennium Development Report 2013, New York © P. Sicherl, 2013
In general the Gaptimer MDG Progress Chart presents in a single
table at a glance results for 100 cases across 10 MDG indicators and 10 units
(7 world regions, Developing Regions, China,
and India)
expressed in time lead or time lag providing stories of the situation from the
novel time perspective. There are many green colour fields indicating cases
where targets have been reached or indicators are ahead of the line to target,
to show the many positive developments in the developing countries. The
situation differs among the world regions, but the overall situation shows that
the number of cases ahead of the line to target (21+15) is exceeding the number
of cases behind (18+14). In absolute terms progress has been made in all
selected indicators and in all world regions (though it has been quite uneven
across regions as well as across countries within the regions). Furthermore,
for countries with delays the application of the overall MDG targets at the
regional and national cases may be unrealistic.
For more
detailed analysis, below we provide Excel files of results of time distances in
which time lead or time lag from the line to the respective MDG 2015 targets
are shown for 112-137 developing countries respectively for the five selected
indicators. This monitoring method can be applied much more widely. Firstly,
world regions can be exchanged with countries, regions within countries, or
socio-economic groups, sectors, etc. Secondly, units could be products of an
enterprise, budget activities or operational projects, etc., and with e.g.
relevant KPIs as horizontal entries.
EXCEL FILES of S-time-distances for selected
developing countries: IND4.1 Under-five mortality rate 2011.xls
IND5.1 Maternal mortality ratio 2010.xls
IND7.8t improved drinking water 2011.xls
IND7.9t improved sanitation 2011.xls
IND8.16 Internet users 2012.xls
Links to wikiprogress:
|
|
