Page 47 - ES 2020-21_Volume-1-2 [28-01-21]
P. 47

30      Economic Survey 2020-21   Volume 1



              is likely to be found even when the time-series for the two variables are independent of each
              other, thus leading to spurious estimates of the correlation between the two variables. They
              also illustrated that the regression residuals are likely to be autocorrelated, as evidenced by a
              very low value for the Durbin-Watson (DW) statistic.
              Granger and Newbold (1974) present strong evidence that regressions involving random walks
              are spurious when performed on the levels, but not on the differences. Therefore, instead of
              levels, using first difference i.e., ∆y  = y  – y  avoids the problem of spurious correlations.
                                                        t-1
                                                    t
                                                t
             1.44  Table 1 shows the negative relationship between the month-on-month change in economic
             indicators with the month-on-month change in stringency index, thereby corroborating that the
             lockdown negatively impacted economic activity contemporaneously.

                     Table 1: Contemporaneous Impact of Stringency Index on Economic Indicators
                   Dependent         Electronic toll   Electronic toll   Number of
                 Variable (MoM          (ETC)             (ETC)            E-Way        Value of E-way
                                                                                             Bills
                    Change)            collection         Count             Bills
                Stringency Index       -0.528***        -0.703***          -0.239           -0.203*
                 (MoM Change)
                                        (0.135)          (0.156)           (0.158)          (0.121)
                    Constant          0.0760***         0.0875***         0.123***         0.104***
                                       (0.0258)          (0.0298)         (0.0306)          (0.0233)
                       R 2               0.123            0.158            0.015             0.019

             Source: Survey Calculation
             Note: Standard errors in parentheses. * p < 0.10, ** p < 0.05, *** p < 0.01.

             1.45  To capture the lagged impact of stringency on economic indicators, a three-month moving
             average of stringency index has been used. The Survey see that the month-on-month change in
             the three-month moving average of the stringency index has a  positive relationship with the
             growth in each of the economic indicators (Table 2). Thus, the initial stringent lockdown has
             supported a V-shaped recovery across all the economic indicators (Figure 27 and 28).

                 Table 2: Impact of 3-Month Moving Average of Stringency Index on Economic Indicators
                   Dependent                                             Number of
                                         ETC
                                                          ETC
                 Variable (MoM         collection         Count            E-Way        Value of E-way
                                                                                             Bills
                    Change)                                                 Bills
               3_MA_Stringency
              Index (MoM Change)       0.560***         0.739***          0.678***         0.458***
                                       (0.0877)          (0.0981)         (0.0970)          (0.0766)

                    Constant           0.191***         0.240***          0.207***         0.167***
                                       (0.0179)          (0.0200)         (0.0206)          (0.0163)
                       R 2               0.274            0.345            0.248             0.194

             Source: Survey Calculation
             Note: Standard errors in parentheses. *  p < 0.10, ** p < 0.05, *** p < 0.01.
   42   43   44   45   46   47   48   49   50   51   52