In this blog post graphic methods are used to describe monthly industrial production time series in six countries.
Two types of a line graph could be used to show changes in monthly industrial production over time. The first displays both original and seasonally and calendar adjusted time series for six countries on a single graph. This graph type won’t be used because all twelve series have the same base (2015 = 100). That means the series would overlap each other and not much could be inferred from such graph.
The second type of graph displays each series on a separate panel. On such graph any persistent pattern related to trend or seasonal factors should be clearly visible.
Figure 1 shows line graphs of monthly industrial production in Bosnia and Herzegovina, Croatia, and Macedonia on the separate panels.
A couple of features of these series stand out. First, all three series show changes in the level. In case of Bosnia and Herzegovina, the shortest series of these three, there is an upward trend in the whole period. In case of Croatia and Macedonia we have a longer time series, including period before the great recession in 2007-2008. While in case of Croatia there is a long-term upward trend in the whole period until the global financial crisis, in case of Macedonia in the same period monthly industrial production shows cyclical pattern. The scale and timing of the great recession varied from country to country as well as the duration of recovering. In case of Croatia it took almost 5 years to reverse the negative trend in industrial production. In case of Macedonia the impact of financial crisis was not such severe and the industrial production picked up quickly.
Second, all three series show a persistent pattern of short-term volatility around the trend in the whole period. This short term volatility seems to be related to seasonal factors. While this seasonal pattern is quite stable in case of Croatia, industrial production in Bosnia and Herzegovina shows great variation in the whole period, and in the first five years only in case of Macedonia.
Figure 2 shows line graphs of monthly industrial production in Montenegro, Serbia and Slovenia.
Montenegro has the shortest series in Figure 2. There is no clear trend in the series and it seems that the industrial production indices vary around a constant level. Serbian industrial production series shows similar pattern as Macedonian production, though with greater volatility. This similarity will be clearly seen in the trend component when decomposing time series into the trend, seasonal and residual series. It seems that Slovenia among all six series shows persistent upward trend in both periods, before and after great financial crisis, less volatility and quick recovery after the great recession.
In the next blog post we will show results of seasonality analysis of industrial production series.