Research question and objective of the study

In the former analysis of road safety trends in Poland - due to the unavailability of traffic data, and to the occurrence of two economic breakdowns in 2001 and 2007 onwards - researchers tomed to economic factors to explain the simultaneous decrease that occurred in the trend of the number of fatalities in Poland - as in other countries in Europe. Variables such as the GDP and unemployment rate have been used for modeling changes in the number of fatalities in the short- or medium term 

1 The traffic volume is often used as the best estimate of risk exposure at national level, although it does not account for the exposure of non-motorized road users. 

The following part of this ehapter is organized as follows the current state of knowledge on the short-term relationship between economic conditions and road mortality at national level is first reealled in seetion 4.2 the econometric approach adopted for estimating that link is then deseribed in section 4.3 an analysis of the dataset used for Poland is given in seetion 4.4, the modehng results are given and discussed in sections 4.5 and 4.6 and finally, section 4.6 provides a brief conclusion and recormnendations for future work. 

The state of knowledge eovers both the mechanisms of the process that links the economic conditiorrs to road mortality at national level in the short or mediitm term, and their qrrantifieationby means of appropriate modeling. 

The structural time series analysis methods also referred to as state-space methods [HAR 86, COM 07] have been used more and more for modeling the aggregate number of fatalities at national level [DUP 07], The approach that the authors adopt is innovative, as usually such analyses are led on an annual basis - in order to explain and forecast long-term changes in the aggregate number of fatalities at national level [LAS 01]). On the contrary, short-term changes can only be modeled on an infra-annual basis similar but uncompleted approaches were taken on a quarterly basis - without the inclusion of exogenous variables [COM 2007] and on a monthly basis - without the inclusion of economic variables [BER 13]. 

---