Abstract
The present research works with yearly data on backward looking measures of inflation i.e. GDP deflator series for Bulgaria, Czech Republic, Estonia, Hungary, Kazakhstan, Kyrgyzstan, Latvia, Lithuania, and Slovakia. Because of the data limitations in the transition economies annual series are converted to smooth quarterly series before they are employed for inflation prognosis using state space models. The results show statistically significant evidence of time-varying volatility in Bulgaria, Czech Republic, Estonia, Hungary, Kazakhstan, Kyrgyzstan, Latvia, Lithuania, and Slovakia using critical values obtained from χ 3 2 distributions. The results also show that the non-normality hypothesis cannot be rejected in all the series using critical values due McCulloch (J Bus Econ Stat 15:74–81, 1997). The efficiently estimated inflation forecast range between 0.925 for Bulgaria to 99.106 for Latvia. The estimated value of the characteristic exponent α of 2.000 for Hungary, and for the other countries having α equal to 1.999 shows tendency toward normal behavior in exception of Bulgaria, where α equals 1.861.