### Table 3 Two-step Estimation of Equations (1), (2), and (3):

2000

"... In PAGE 20: ... Baseline Results Tables 3 and 4 present the results of our second-step regressions. Table3 gives a compact overview of all the specifications, showing only one number (with the associated p-value) from each regression: the sum of the N coefficients on the relevant monetary indicator. The table is divided into two panels: Panel A for C amp;I loans, and Panel B for total loans.... In PAGE 20: ... Second, we test in the same six ways whether the sum of the N apos;s is lower for the small banks than for the quot;big quot; banks--those in the top 1% of the size distribution. As can be seen from Panel A of Table3 , the overall results for C amp;I loans are strong. Consider first the results for the small banks.... In PAGE 22: ... If this is so, the effects that we are looking for will emerge more clearly with C amp;I loans. Table 4 presents the details of the individual regressions that make up Table3 . There are 6 panels, A through F, one for each combination of loan type and monetary indicator.... In PAGE 22: ... A couple of salient facts emerge. First, while we reported in Table3 only the sums of the five N coefficients... In PAGE 25: ...33 Table 5 presents an overview of the estimates of N generated by the one-step approach. As can be seen, the point estimates are generally quite close to those in Table3 . However, the standard errors are much reduced, leading to more strongly significant p-values.... In PAGE 26: ...n the first-step regressions. Everything else is exactly as before. Table 6 gives an overview of the results. As it turns out, the numbers are very similar to those in Table3 . Of course, we recognize that Table 6 does not by itself represent an ironclad argument against endogeneity concerns.... In PAGE 27: ...In Table 7, we reproduce all the numbers in Table3 for each of two sub-samples. A clear pattern emerges: the results are almost uniformly stronger and more statistically significant in the second sub-sample, which begins in 1986Q1.... In PAGE 27: ... A first step is to quantify how two equal-sized banks with different values of Bit respond to a shock. From Table3 , Panel A, the most conservative estimate of the sum of the N apos;s for small banks apos; C amp;I loans is -.0151.... In PAGE 28: ...36 That is, if both banks started with a level of C amp;I loans equal to $1000, then purely on the basis of liquidity differences, we would predict a $6 gap between the two banks a year after the funds rate shock. The estimates in Table3 are also consistent with a much larger cross-sectional effect. If we base our calculation on the bivariate small-bank/big-bank coefficient differential of -.... In PAGE 54: ...1% Notes: * The numbers in the first column are based on the two-step estimates reported in Table 3. ** The numbers in the second column are drawn from Kashyap and Stein apos;s (1995) estimates for the quot;small 95 quot; category as follows: a Table 4, Panel 1 b Table 4, Panel 2 c Table3 , Panel 1... In PAGE 54: ...1% Notes: * The numbers in the first column are based on the two-step estimates reported in Table 3. ** The numbers in the second column are drawn from Kashyap and Stein apos;s (1995) estimates for the quot;small 95 quot; category as follows: a Table 4, Panel 1 b Table 4, Panel 2 c Table 3, Panel 1 d Table3... ..."

Cited by 13

### Table 3 Two-step Estimation of Equations (1), (2), and (3):

2000

"... In PAGE 20: ... Baseline Results Tables 3 and 4 present the results of our second-step regressions. Table3 gives a compact overview of all the specifications, showing only one number (with the associated p-value) from each regression: the sum of the N coefficients on the relevant monetary indicator. The table is divided into two panels: Panel A for C amp;I loans, and Panel B for total loans.... In PAGE 20: ... Second, we test in the same six ways whether the sum of the N apos;s is lower for the small banks than for the quot;big quot; banks--those in the top 1% of the size distribution. As can be seen from Panel A of Table3 , the overall results for C amp;I loans are strong. Consider first the results for the small banks.... In PAGE 22: ... If this is so, the effects that we are looking for will emerge more clearly with C amp;I loans. Table 4 presents the details of the individual regressions that make up Table3 . There are 6 panels, A through F, one for each combination of loan type and monetary indicator.... In PAGE 22: ... A couple of salient facts emerge. First, while we reported in Table3 only the sums of the five N coefficients... In PAGE 25: ...33 Table 5 presents an overview of the estimates of N generated by the one-step approach. As can be seen, the point estimates are generally quite close to those in Table3 . However, the standard errors are much reduced, leading to more strongly significant p-values.... In PAGE 26: ...n the first-step regressions. Everything else is exactly as before. Table 6 gives an overview of the results. As it turns out, the numbers are very similar to those in Table3 . Of course, we recognize that Table 6 does not by itself represent an ironclad argument against endogeneity concerns.... In PAGE 27: ...In Table 7, we reproduce all the numbers in Table3 for each of two sub-samples. A clear pattern emerges: the results are almost uniformly stronger and more statistically significant in the second sub-sample, which begins in 1986Q1.... In PAGE 27: ... A first step is to quantify how two equal-sized banks with different values of Bit respond to a shock. From Table3 , Panel A, the most conservative estimate of the sum of the N apos;s for small banks apos; C amp;I loans is -.0151.... In PAGE 28: ...36 That is, if both banks started with a level of C amp;I loans equal to $1000, then purely on the basis of liquidity differences, we would predict a $6 gap between the two banks a year after the funds rate shock. The estimates in Table3 are also consistent with a much larger cross-sectional effect. If we base our calculation on the bivariate small-bank/big-bank coefficient differential of -.... In PAGE 54: ...1% Notes: * The numbers in the first column are based on the two-step estimates reported in Table 3. ** The numbers in the second column are drawn from Kashyap and Stein apos;s (1995) estimates for the quot;small 95 quot; category as follows: a Table 4, Panel 1 b Table 4, Panel 2 c Table3 , Panel 1... In PAGE 54: ...1% Notes: * The numbers in the first column are based on the two-step estimates reported in Table 3. ** The numbers in the second column are drawn from Kashyap and Stein apos;s (1995) estimates for the quot;small 95 quot; category as follows: a Table 4, Panel 1 b Table 4, Panel 2 c Table 3, Panel 1 d Table3... ..."

Cited by 13

### Table 2: The next two steps in the analysis [31]

2001

"... In PAGE 7: ...2.4 Sorting for the purpose of categorisation The overall descriptions at the individual level were then sorted for the purpose of categorisation (see Table2 ). In this step, as in every step of the analysis described above, comparisons with the whole interview transcripts were also made.... ..."

Cited by 1

### Table 8: Transition from unemployment to employment. Naive probit Two-step probit Two-step heteroscedasticity ML

in Two-step

2001

"... In PAGE 13: ... This, however, may just be a spurious time dependence caused by the fact that it is difficult to completely control for heterogeneity. Table8 showstheestimatedcoefficientsandthecorrespondingp-values of t-test ofsignificance of the covariates in the binary model describing the transitions from unemployment to employment for the 4 different estimation procedures: the naive probit estimate that ignores the attrition problem... ..."

### Table 1. Two-Step and Systems Estimates of the AR(6) Price Equa- tion, 1958-90

"... In PAGE 6: ...ndex (1967 = 1.0). The estimation results are presented in tables 1 and 2. Table1 contains results for the autoregressive models of slaughter price for barrows and gilts. Table 2 contains parameter estimates for the risk-responsive sow farrowing equations for alternative specifications of the conditional variance process.... ..."

### Table 3 A ne registration parameters estimated by the two-step method (TS/B-sp).

1998

"... In PAGE 13: ... The table lists the distances between the query and database objects computed by four di erent schemes for comparison purposes: the uni ed matching (UM) scheme with the proposed shape similarity metric using all boundary points (UM=all BP ); UM scheme using the B-spline control points of the contours (UM=B ? sp); the two-step (T S) method using B-spline control points of the contours and the Hausdor distance (HD) metric after a ne registration (T S=B ? sp amp;HD); and the HD metric using all boundary points (HD=all BP ). Table3 includes the least squares estimates of the a ne parameters employed by the two step scheme. These parameters are used to register the database and query objects before computing the Hausdor distance between them.... ..."

Cited by 16

### Table 9 OLS and Two-step GMM estimates of investment model (i) (ii) (iii) (iv)

in Financial Liberalization and Financing Constraints: Evidence from Panel Data on Emerging Economies

"... In PAGE 23: ... The OLS results may, however, suffer from an endogeneity problem. We therefore estimate model (13) in levels using the aforementioned GMM techniques (see Table9 , Model 2). We only present two-step GMM estimates, since they are more efficient than one-step estimates, and since only the Sargan test of over- identifying restrictions is heteroskedasticity-consistent only if based on the two-step estimates.... In PAGE 24: ... Since the GMM level estimation does not show persistent serial correlation in the residuals it is not necessary to control for potential unobserved firm-specific effects by estimating the model in first-differences, especially since, as noted earlier, the difference estimator has some statistical shortcomings. We nevertheless present the estimates for model (13) in first-differences (see Table9 , Model 3). The model is supported both by a test for higher-order serial correlation and by the Sargan test for over-identifying restrictions.... In PAGE 25: ... This dummy variable is FLI5, which has been defined earlier. We have generated both OLS and GMM level estimates (see Table9 , Model 7 and 8), and find that, although firms have been severely financially constrained over the period, they have become less financially constrained as financial liberalization progresses. The estimated effect is economically significant.... In PAGE 26: ...effects (see Table9 , Model 9 and 10). Looking at the coefficients of the multiplicative terms, we find that financial liberalization has a different impact on firms of different size.... In PAGE 27: ... The OLS estimates are presented in Table 10 (Model 1). The results are similar to our basic specification that uses net sales to distinguish between firms of different size ( Table9 , Model 9). Only small firms benefit from financial liberalization.... ..."

### Table 9 OLS and Two-step GMM estimates of investment model (continued) (v) (vi) (vii) (viii)

in Financial Liberalization and Financing Constraints: Evidence from Panel Data on Emerging Economies

"... In PAGE 23: ... The OLS results may, however, suffer from an endogeneity problem. We therefore estimate model (13) in levels using the aforementioned GMM techniques (see Table9 , Model 2). We only present two-step GMM estimates, since they are more efficient than one-step estimates, and since only the Sargan test of over- identifying restrictions is heteroskedasticity-consistent only if based on the two-step estimates.... In PAGE 24: ... Since the GMM level estimation does not show persistent serial correlation in the residuals it is not necessary to control for potential unobserved firm-specific effects by estimating the model in first-differences, especially since, as noted earlier, the difference estimator has some statistical shortcomings. We nevertheless present the estimates for model (13) in first-differences (see Table9 , Model 3). The model is supported both by a test for higher-order serial correlation and by the Sargan test for over-identifying restrictions.... In PAGE 25: ... This dummy variable is FLI5, which has been defined earlier. We have generated both OLS and GMM level estimates (see Table9 , Model 7 and 8), and find that, although firms have been severely financially constrained over the period, they have become less financially constrained as financial liberalization progresses. The estimated effect is economically significant.... In PAGE 26: ...effects (see Table9 , Model 9 and 10). Looking at the coefficients of the multiplicative terms, we find that financial liberalization has a different impact on firms of different size.... In PAGE 27: ... The OLS estimates are presented in Table 10 (Model 1). The results are similar to our basic specification that uses net sales to distinguish between firms of different size ( Table9 , Model 9). Only small firms benefit from financial liberalization.... ..."

### Table 9 OLS and Two-step GMM estimates of investment model (continued) (ix) (x)

in Financial Liberalization and Financing Constraints: Evidence from Panel Data on Emerging Economies

"... In PAGE 23: ... The OLS results may, however, suffer from an endogeneity problem. We therefore estimate model (13) in levels using the aforementioned GMM techniques (see Table9 , Model 2). We only present two-step GMM estimates, since they are more efficient than one-step estimates, and since only the Sargan test of over- identifying restrictions is heteroskedasticity-consistent only if based on the two-step estimates.... In PAGE 24: ... Since the GMM level estimation does not show persistent serial correlation in the residuals it is not necessary to control for potential unobserved firm-specific effects by estimating the model in first-differences, especially since, as noted earlier, the difference estimator has some statistical shortcomings. We nevertheless present the estimates for model (13) in first-differences (see Table9 , Model 3). The model is supported both by a test for higher-order serial correlation and by the Sargan test for over-identifying restrictions.... In PAGE 25: ... This dummy variable is FLI5, which has been defined earlier. We have generated both OLS and GMM level estimates (see Table9 , Model 7 and 8), and find that, although firms have been severely financially constrained over the period, they have become less financially constrained as financial liberalization progresses. The estimated effect is economically significant.... In PAGE 26: ...effects (see Table9 , Model 9 and 10). Looking at the coefficients of the multiplicative terms, we find that financial liberalization has a different impact on firms of different size.... In PAGE 27: ... The OLS estimates are presented in Table 10 (Model 1). The results are similar to our basic specification that uses net sales to distinguish between firms of different size ( Table9 , Model 9). Only small firms benefit from financial liberalization.... ..."

### Table 5: Two-step GMM estimation results of the CIR model Parameters United States Germany Japan United Kingdom

"... In PAGE 21: ... Furthermore, even with such large measurement errors, the overidentifying restriction indicate that the two-factor CIR model is rejected for each of the four countries. The two-step GMM estimates of the CIR model are shown in Table5 and are in general comparable with the one-step estimates. For the USA, the estimates more or less correspond to the two-factor results of Chen and Scott (1993).... ..."