Multiple linear regression was used as the second method. It shows the differences between both political regimes using all the selected urban development
indicators in one calculation. The method determines which indicators have/had an
important or less important influence. The results of the method showed that all
used indicators reliably explain road traffic intensity with a coefficient of determination higher than 90 %. However, the statistical significance of many variables/
indicators was quite low. The behavior within the individual groups of cities were in
the framework of individual regimes similar and different than in other groups of
cities and regimes.
Multiple linear regression shows a complex dependency of all selected indicators. The disadvantage of the method is a limit of used independent variables given
by the number of input data of used cities; in other words, a sufficient number of
cities for this analysis is necessary for each set of indicators. The analyses were
again processed for the 1970–1990 and 1990–2005 periods. Four from six models
(small, medium, big cities for two periods) had all a level of significance of all
indicators higher than 0,05. Thus the indicators had a low significance. This method
brings interesting results showing the differences between the regimes especially in
statistical significance of individual indicators.
The last method – correlation allowed to find a dependency between road traffic
intensity and individual indicators regardless other indicators More information can
be found using average road traffic intensity. Correlation shows that there are great
differences between city groups. A significant impact of political change can be
found in all groups of cities but in the dependency of different land use areas as
well. The differences between the regimes using the correlation in big and medium
cities occur in all classes except for transportation areas, in small cities only for
residential and production areas. A relatively high number of correlation coefficients in the communist regime are very low and have an increasing trend either to
positive or negative values. It means that the dependency between the road traffic is
higher in the democratic regime than in the communist at average road traffic. This
dependency of maximum road traffic intensity is substantially lower than of the
average. It suggests that it is the land use of cities which raises the intensity
especially in the democratic regime in the country. Each of the methods presented
in this chapter proved to be a useful tool for analyzing the time series of more
variables and from a different point of view.
All the results of the analyses proved that political change followed by economical change has a very strong impact on road traffic intensity. Eighty to ninety per
cent of the road traffic intensity is formed by personal cars, motorcycles which
cover less than 3 %, and the rest is formed by heavy vehicles. The high increase of
the number of personal cars since early 1990s and developing residential areas
situated usually out of city centers deteriorated the traffic situation having a doubled
road traffic intensity if compared between 1970 and 2005. Both these features
reflect a different state of the society in the post communist period.
There is a large scale of indicators of various types which influence the changes
and development in urban areas. Geospatial science is the only really objective tool
which is able to store, analyze and model urban development based on historical
5 Influence of Political Regime Change to Land Use Development in Urban. . .
107
indicators in one calculation. The method determines which indicators have/had an
important or less important influence. The results of the method showed that all
used indicators reliably explain road traffic intensity with a coefficient of determination higher than 90 %. However, the statistical significance of many variables/
indicators was quite low. The behavior within the individual groups of cities were in
the framework of individual regimes similar and different than in other groups of
cities and regimes.
Multiple linear regression shows a complex dependency of all selected indicators. The disadvantage of the method is a limit of used independent variables given
by the number of input data of used cities; in other words, a sufficient number of
cities for this analysis is necessary for each set of indicators. The analyses were
again processed for the 1970–1990 and 1990–2005 periods. Four from six models
(small, medium, big cities for two periods) had all a level of significance of all
indicators higher than 0,05. Thus the indicators had a low significance. This method
brings interesting results showing the differences between the regimes especially in
statistical significance of individual indicators.
The last method – correlation allowed to find a dependency between road traffic
intensity and individual indicators regardless other indicators More information can
be found using average road traffic intensity. Correlation shows that there are great
differences between city groups. A significant impact of political change can be
found in all groups of cities but in the dependency of different land use areas as
well. The differences between the regimes using the correlation in big and medium
cities occur in all classes except for transportation areas, in small cities only for
residential and production areas. A relatively high number of correlation coefficients in the communist regime are very low and have an increasing trend either to
positive or negative values. It means that the dependency between the road traffic is
higher in the democratic regime than in the communist at average road traffic. This
dependency of maximum road traffic intensity is substantially lower than of the
average. It suggests that it is the land use of cities which raises the intensity
especially in the democratic regime in the country. Each of the methods presented
in this chapter proved to be a useful tool for analyzing the time series of more
variables and from a different point of view.
All the results of the analyses proved that political change followed by economical change has a very strong impact on road traffic intensity. Eighty to ninety per
cent of the road traffic intensity is formed by personal cars, motorcycles which
cover less than 3 %, and the rest is formed by heavy vehicles. The high increase of
the number of personal cars since early 1990s and developing residential areas
situated usually out of city centers deteriorated the traffic situation having a doubled
road traffic intensity if compared between 1970 and 2005. Both these features
reflect a different state of the society in the post communist period.
There is a large scale of indicators of various types which influence the changes
and development in urban areas. Geospatial science is the only really objective tool
which is able to store, analyze and model urban development based on historical
5 Influence of Political Regime Change to Land Use Development in Urban. . .
107