How to make comparisons of indicators more understandable to policy
makers, managers, media and to general public by complementing with the time distance
Two obvious generic directions of time series comparison - by time and by level
Besides the levels of the variable (indicator) the two most widely used measures for
comparisons are growth rate and static difference between two or more units. However, at
the same level of generality there exist two companion generic statistical measures S-time-
distance and S-time-step as a special category of time distances defined by the level of
the variable. The first measures the distance (proximity) in time between the points in time
when the two series compared reach a specified level of the indicator X; the second is an
additional measure of dynamics measuring time that was needed to reach the next level of X.
The time distance approach brings about two persuasive advantages for extensive practical
use. Expressed in time units it is intuitively understood by policymakers, professionals,
managers, media and the general public, facilitating their subjective perception about their
position in this additional dimension. Another technical and presentation advantage is that
time and time distance is comparable across variables, fields of concern, and units of
comparison. This makes it an excellent analytical, presentation and communication tool.
This innovation opens the possibility for simultaneous two-dimensional comparisons
of time series data in two specified dimensions: vertically (standard measures of static
difference) as well as horizontally (Sicherl time distance), providing a new dimension
of analysis to a variety of problems. The following examples do not deal here with the
calculation of time distances but focus only on the examples how the visualisation of the
time distance results can complement the visualisation of other statistical measures like static
indexes to provide a broader understanding in the dynamic context.
Empirically, the degree of disparity may be very different in static terms and in time
distance, which leads to new conclusions and semantics important for policy considerations.
Therefore, we need both dimensions, especially when we compare indicators across
different domains. The few examples here show the visualisation of time matrix
transformation of the usual time series database (i.e. time when a specified level of the
variable was achieved in each compared unit), followed by examples for S-time-distance and
S-time-step for life expectancy over OECD countries.
Visualisation with the help of selected types of time distance graphs (or S-time-distance
and S-time-step tables as well) can be included in publications or in the respective web
pages of statistical offices, international and national organisations, NGOs, by media to
enhance knowledge and understanding. Seeing with new eyes and telling new stories can
facilitate stakeholders to build their perceptions and decisions. Faster application of this
complementary methodology by potential imaginative users in numerous fields can be
helped by developing of the necessary software.
The full text includes both schematic tables for transformation of conventional time series
tables into corresponding time distance companions and the respective empirical examples.