# Summary Statistics : Data And Methods

908 Words4 Pages
3. DATA AND METHODS
3.1. Data
The study is completely based on secondary data for the period of 1991 to 2016. The data on unemployment rate are compiled from World Bank. On the other hand data on inflation rate are collected from (http://www.inflation.eu/inflation-rates/india/inflation-india.aspx). The statistical software Eviews7 have used for statistical calculations. The detail descriptions of the variables are shown in table 1:
Table 1: Summary Statistics
Variables Description Mean (SD)
Inflation rate (INF) Inflation rate is defined as the annual percent change in consumer prices compared with the previous year's consumer prices 7.70 (3.19)
Unemployment rate (UNP) The unemployment rate is the percentage of the total workforce that is
…show more content…
4. RESULTS
The objective of this study is to investigate the causality relationship between inflation and unemployment in India. For this purpose we have used the standard econometric model of granger causality. But, before estimating the granger causality we must have check the stationary property of the variables. This is because if the variables are non-stationary then, the granger causality test may give misleading results. To test the stationary property of variables, we have used Phillips and Perron (1988). The result of unit root test is shown the table 2:
Table 2: Phillips-Perron test for unit root
Variables Level 1st difference
Inflation rate (INF) -11.61 (P=0.18) -29.09*** (P=0.00)
Unemployment rate (UNP) -10.97 (P= 0.13) -32.03*** (P=0.00)
Source: author’s calculation; Note: *** represent the 1 percent level of significance.
The above table shows the result of Phillips-Perron test unit root test. It seen from the table that, the null hypothesis of unit roots is not rejected for both the variables i.e. inflation rate and unemployment rate. This indicates that both variables are not stationary at level. However, inflation rate and unemployment rate are found to stationary after first difference. Since the variables are stationary at first difference, they can be further tested for co-integration. We have used Johansen Co-integration Test to find the Co-integration.
Table 3: Johansen tests