### Table 11 Augmented Dickey-Fuller Tests

"... In PAGE 28: ...36 1.00 Table11 reports t-statistics for Augmented Dickey-Fuller tests (see MacKinnon, 1991 ), along with the corrected critical values for our variables of interest. It suggests that the orders of integration of our variables are different between industries.... ..."

### Table 3: Results of the Dickey-Fuller Tests

"... In PAGE 12: ...ank of St. Louis (www.stls.frb.org/index.html).6 We constructed the price level as the ratio of nominal to real gdp. As shown in Table3 , augmented Dickey-Fuller tests including a time trend in the estimating equation indicated that the logarithms of M3 (m), real gdp (y) and the price level (p) do not act as trend stationary processes. In contrast, the 3-month T-bill rate (r) shows some evidence of stationarity.... ..."

### TABLE 4 RESULTS OF DICKEY-FULLER TEST

### TABLE 2 Results of Augmented Dickey Fuller Tests

### TABLE 1 Augmented Dickey-Fuller Tests

### TABLE 3 Augmented Dickey-Fuller Tests

### Table 4 Augmented Dickey-Fuller Statistics. Level Difference

1998

"... In PAGE 10: ... The Augmented Dickey-Fuller (ADF) (Dickey and Fuller (1979)) test was used to perform the unit root tests. Table4 shows the ADF statistics (with lags in brackets); these are carried out for both the level of the data and the first difference, including a constant term. The critical value at the 5% level is given at the bottom of the table.... ..."

Cited by 2

### Table 1 Studentized Statistics from Dickey-Fuller Regressions

"... In PAGE 5: ... Ng and Perron (1995), however, argue that t and F tests on the augmentation lag coefficients in the Dickey-Fuller regression are preferable, because they lead to less size distortion and comparable power. We report estimates of the augmented Dickey-Fuller regressions in Table1 . The analysis is conducted for the four real GNP variables discussed above and for k=1 through k=6.... ..."

### Table 4 Dickey Fuller Test Results for Presence of Unit Root apos;

"... In PAGE 16: ... Finally, if there is evidence of a unit root, and no evidence of a structural break in the series, we are unable to make a statistical conclusion regarding the effect of the policy on the stock market development indicator. Table4 show the results of the Dickey-Fuller tests. In every case, each of the three variations of the tests produce the same conclusions regarding the rejection (or quot;acceptance quot;) of a unit root.... In PAGE 16: ... In every case, each of the three variations of the tests produce the same conclusions regarding the rejection (or quot;acceptance quot;) of a unit root. In Table4 , a quot;YES quot; entry indicates the data do not reject the hypothesis of a unit root at the 0.05 significance level.... In PAGE 17: ...Table4 that show a quot;YES quot; entry, we test for a structul break. As in Perron (1989), we consider three different models for each indicator series.... ..."