Table C.8:Standardized bias, baseline specification
Optimists Pessimists
Variable All Correct Incorrect All Correct Incorrect
Dep. var,t-1 1.8 1.6 1.8 -0.7 -0.7 -0.9
Dep. var,t-2 0.2 -0.2 -0.3 -1.7 -3.5 -2.5
Dep. var,t-3 0.8 0.7 0.1 -0.7 -2.8 -0.5
Production,t-1 1.3 0.1 -0.6 0.2 -0.3 -0.6
Production,t-2 1.1 0.3 -0.9 0.3 1.1 0.8
Production,t-3 -0.1 -0.2 -0.8 -0.9 -1.3 1.6
Prices,t-1 0.3 1.8 -0.0 0.3 1.5 0.1
Prices,t-2 1.0 -0.8 0.8 1.1 3.1 -0.1
Prices,t-3 0.8 1.5 0.1 0.3 2.0 -0.6
Demand,t-1 1.0 1.1 0.6 -1.1 -0.6 -1.5
Demand,t-2 1.1 2.0 -1.3 -1.5 -1.0 1.2
Demand,t-3 -0.1 -0.4 -0.8 -1.4 -1.7 1.6
Capacity,t-1 0.4 0.4 0.3 1.3 3.3 1.0
Capacity,t-2 0.4 0.6 0.5 0.8 3.1 1.3
Capacity,t-3 0.9 1.2 -0.1 0.3 3.1 0.6
Employees,t 0.2 -0.8 0.1 1.6 1.0 1.2
Avg. state of business, sector,t 0.9 1.8 -0.5 -0.5 -0.9 -0.3
State of business,t 0.4 -0.7 -0.5 0.9 2.0 1.2
State of business,t-1 0.5 -0.0 -0.7 0.7 1.0 1.0
State of business,t-2 0.6 0.6 -0.5 -0.2 0.9 1.8
State of business,t-3 0.0 0.1 -0.3 -0.4 -0.2 0.7
Orders,t 0.4 -1.4 -0.4 1.6 1.8 -0.4
Orders,t-1 2.0 2.1 -0.8 0.4 0.7 0.1
Orders,t-2 1.2 1.4 0.0 -0.3 -1.4 -0.6
Orders,t-3 1.1 0.9 0.0 0.6 -0.9 0.1
Foreign orders,t 1.1 -0.4 -0.4 -0.4 -2.1 -0.0
Foreign orders,t-1 1.9 1.0 -0.8 -0.5 -1.5 0.9
Foreign orders,t-2 1.1 0.6 -0.5 -1.0 -1.7 -0.6
Foreign orders,t-3 0.9 0.8 -0.1 -0.1 -2.1 -0.1
Debt share,t -2.1 -2.8 -1.2 -0.2 -4.5 -2.6
Financing coefficient,t -0.4 -0.7 -1.5 0.7 0.9 0.1
Notes:Table shows standardized bias which captures the difference in means between the treated and untreated groups. The standardized bias is the mean difference of each variable in the treated and untreated groups relative to the variances, details can be found in equation (3.4) in Section 3.3.
CHAPTER 3. FIRMEXPECTATIONS ANDECONOMICACTIVITY 132
Table C.9: Standardized bias, specification with radius r=0.01
Optimists Pessimists
Variable All Correct Incorrect All Correct Incorrect
Dep. var,t-1 1.3 2.4 1.9 -0.1 -1.1 -0.1
Dep. var,t-2 0.1 -0.9 -0.3 -1.8 -2.8 -2.2
Dep. var,t-3 0.1 0.8 0.5 -0.2 -2.6 0.6
Production,t-1 0.8 0.1 -1.6 0.3 0.1 -0.4
Production,t-2 0.8 -0.7 -0.3 0.9 2.3 2.4
Production,t-3 -1.0 -2.2 -0.8 -0.4 0.4 3.4
Prices,t-1 0.6 1.4 0.0 -0.2 3.6 -0.5
Prices,t-2 1.3 -0.6 2.0 0.8 4.7 1.0
Prices,t-3 0.7 1.2 0.1 -0.1 3.5 -0.5
Demand,t-1 0.9 1.6 -0.5 -1.3 -1.1 -1.6
Demand,t-2 0.9 0.8 -1.2 -0.3 -1.5 3.0
Demand,t-3 -0.4 -0.7 -0.5 -1.0 -1.6 3.5
Capacity,t-1 0.0 -0.7 1.2 2.8 4.3 1.4
Capacity,t-2 0.1 -0.6 1.5 2.3 3.7 1.1
Capacity,t-3 0.6 -0.6 0.8 1.7 3.8 0.5
Employees,t 0.7 -0.0 0.6 2.0 2.0 -0.3
Avg. state of business, sector,t 0.6 1.0 0.0 -0.7 -0.5 -1.0
State of business,t 0.8 -1.6 -0.8 1.9 3.6 1.5
State of business,t-1 0.5 -1.0 0.4 2.1 2.7 1.2
State of business,t-2 -0.0 -0.4 -0.2 1.4 1.7 1.9
State of business,t-3 -0.2 -1.4 0.7 0.7 0.4 1.0
Orders,t 0.7 -2.1 -0.8 2.0 3.6 0.5
Orders,t-1 1.5 0.5 -0.2 1.3 0.9 0.5
Orders,t-2 0.5 0.6 0.6 0.6 -0.1 -0.7
Orders,t-3 0.9 -0.2 1.1 1.8 0.5 -0.5
Foreign orders,t 1.3 -1.2 -0.9 0.5 -1.1 0.3
Foreign orders,t-1 1.6 -0.2 -0.4 0.3 -0.7 1.2
Foreign orders,t-2 0.9 -0.6 -0.9 0.0 -0.7 -1.4
Foreign orders,t-3 1.0 -0.4 0.1 1.1 -1.0 -0.9
Debt share,t -1.7 -0.9 -1.2 0.1 -5.2 -2.2
Financing coefficient,t -1.3 -0.6 -1.2 1.5 1.5 0.7
Notes:Table shows standardized bias which captures the difference in means between the treated and untreated groups. The standardized bias is the mean difference of each variable in the treated and untreated groups relative to the variances, details can be found in equation (3.4) in Section 3.3.
Table C.10: Standardized bias, specifications with ordered probit and state of business expectations
Ordered probit State of business exp.
Variable Optimists Pessimists Optimists Pessimists
Dep. var,t-1 -0.7 -0.2 2.0 -1.0
Dep. var,t-2 0.6 -3.6 1.4 -1.0
Dep. var,t-3 2.0 -0.3 0.4 -1.1
Production,t-1 -7.5 -12.8 -0.1 -1.1
Production,t-2 -1.4 -2.7 -0.9 0.0
Production,t-3 -0.3 -0.4 -0.9 -0.2
Prices,t-1 -2.8 -2.5 0.0 -0.2
Prices,t-2 -1.9 -0.7 -0.5 0.1
Prices,t-3 -0.5 -0.3 -0.1 0.5
Demand,t-1 -4.3 -5.1 0.7 -1.5
Demand,t-2 -1.8 -2.2 -0.2 -0.4
Demand,t-3 -0.4 -1.1 -0.8 -0.9
Capacity,t-1 -6.5 -6.2 -0.8 -1.2
Capacity,t-2 -5.1 -3.2 -0.9 -0.8
Capacity,t-3 -4.6 -3.0 -0.8 -0.9
Employees,t -0.2 -0.3 -0.1 1.4
Avg. state of business, sector,t -0.6 -2.8 -0.4 -0.5
State of business,t -6.7 -5.0 -0.7 0.2
State of business,t-1 -3.5 -1.2 -1.0 0.2
State of business,t-2 -2.6 -0.2 -0.7 -0.0
State of business,t-3 -2.8 0.8 -0.3 -0.0
Orders,t -8.6 -6.3 -1.2 0.1
Orders,t-1 -4.3 -5.0 -0.4 -0.7
Orders,t-2 -4.3 -3.8 -0.4 -0.9
Orders,t-3 -3.9 -1.6 -0.2 -0.9
Foreign orders,t -5.2 -2.3 -0.7 -1.2
Foreign orders,t-1 -2.6 -1.9 -0.5 -1.8
Foreign orders,t-2 -2.5 -1.6 -0.6 -1.8
Foreign orders,t-3 -2.5 0.2 -0.2 -1.1
Debt share,t -0.5 2.5 -1.2 -0.4
Financing coefficient,t -0.4 1.7 0.6 0.6
Notes: Table shows standardized bias which captures the difference in means between the treated and untreated groups. The standardized bias is the mean difference of each variable in the treated and untreated groups relative to the variances, details can be found in equation (3.4) in Section 3.3.
CHAPTER 3. FIRMEXPECTATIONS ANDECONOMICACTIVITY 134
Figure C.3: Histogram of the density of the propensity scores
(a)Correct optimists
0.1.2.3.4Fraction
0 .2 .4 .6 .8 1
untreated treated
Propensity score
(b)Correct pessimists
0.1.2.3.4.5Fraction
0 .2 .4 .6 .8 1
untreated treated
Propensity score
(c)Incorrect optimists
0.1.2.3Fraction
0 .2 .4 .6 .8 1
untreated treated
Propensity score
(d)Incorrect pessimists
0.1.2.3.4Fraction
0 .2 .4 .6 .8 1
untreated treated
Propensity score
Notes: Histograms show the propensity scores for treated and untreated firms respectively, estimated as described by equation (3.3). In Panel (a) treated firms are correct optimists, Panel (b) treated firms are correct pessimists, in Panel (c) treated firms are incorrect optimists, and Panel (d) treated firms are incorrect pessimists.
Figure C.4:Standardized bias, before and after matching, correct and incorrect firms
(a)Correct optimists
0 50 100
capacity, t-1 capacity, t-2 employees, tcapacity, t-3 financing coefficient, tdebt share, tprices, t-3prices, t-2 avg. state of business, tstate of business, t-3state of business, t-2state of business, t-1state of business, tforeign orders, t-3foreign orders, t-2foreign orders, t-1foreign orders, tproduction, t-3production, t-2production, t-1demand, t-3demand, t-2dep. var, t-3demand, t-1dep. var, t-2dep. var, t-1orders, t-3orders, t-2orders, t-1prices, t-1orders, t
Standardized % bias across covariates Unmatched
Matched
(b)Correct pessimists
-150 -100 -50 0
dep. var, t-1 production, t-1demand, t-1dep. var, t-2orders, t state of business, tproduction, t-2demand, t-2dep. var, t-3orders, t-1 state of business, t-1foreign orders, tproduction, t-3demand, t-3orders, t-2 state of business, t-2orders, t-3 state of business, t-3foreign orders, t-1 avg. state of business, tfinancing coefficient, tforeign orders, t-2foreign orders, t-3employees, tdebt share, tcapacity, t-1capacity, t-2capacity, t-3prices, t-1prices, t-2prices, t-3
Standardized % bias across covariates Unmatched
Matched
(c)Incorrect optimists
-20 0 20 40 60 80
capacity, t-1 capacity, t-2 capacity, t-3 employees, torders, t-3orders, t-2orders, t-1 foreign orders, t-3 foreign orders, t-2 state of business, t-3 financing coefficient, tstate of business, t-2state of business, t-1foreign orders, t-1production, t-3prices, t-3prices, t-2orders, t avg. state of business, tstate of business, tforeign orders, tproduction, t-2production, t-1debt share, tdemand, t-3demand, t-2demand, t-1dep. var, t-3dep. var, t-2dep. var, t-1prices, t-1
Standardized % bias across covariates Unmatched
Matched
(d)Incorrect pessimists
-100 -80 -60 -40 -20 0
dep. var, t-1 demand, t-1 dep. var, t-2orders, t production, t-1 state of business, tforeign orders, tdep. var, t-3demand, t-2orders, t-1 state of business, t-1production, t-2orders, t-2prices, t-1 state of business, t-2foreign orders, t-1demand, t-3 avg. state of business, tfinancing coefficient, tstate of business, t-3foreign orders, t-2foreign orders, t-3production, t-3employees, tdebt share, tcapacity, t-1capacity, t-2capacity, t-3orders, t-3prices, t-2prices, t-3
Standardized % bias across covariates Unmatched
Matched
Notes: Figure shows standardized bias for the matching of correct and incorrect optimists and pes-simists. The standardized bias measures the mean difference of each variable in the treated and un-treated groups, as described by equation (3.4) in Subsection 3.3.2.
CHAPTER 3. FIRMEXPECTATIONS ANDECONOMICACTIVITY 136
Figure C.5:Variance ratio of residuals, before and after matching, correct and incorrect firms
(a)Correct optimists
0 .5 1 1.5 2
employees, t avg. state of business, tfinancing coefficient, tstate of business, t-1state of business, t-2state of business, t-3state of business, tforeign orders, t-3foreign orders, t-1foreign orders, t-2foreign orders, tproduction, t-3production, t-2production, t-1debt share, tcapacity, t-3capacity, t-2capacity, t-1demand, t-2demand, t-1demand, t-3dep. var, t-1dep. var, t-2dep. var, t-3orders, t-1orders, t-3orders, t-2prices, t-3prices, t-2prices, t-1orders, t
Variance ratio of residuals
Unmatched Matched
(b)Correct pessimists
0 1 2 3
employees, torders, t state of business, tforeign orders, t-1foreign orders, t-2foreign orders, torders, t-1 state of business, t-1foreign orders, t-3orders, t-2 state of business, t-2demand, t-1orders, t-3 state of business, t-3debt share, tdemand, t-2 avg. state of business, tfinancing coefficient, tproduction, t-1production, t-2production, t-3demand, t-3dep. var, t-1capacity, t-1capacity, t-2capacity, t-3dep. var, t-2dep. var, t-3prices, t-3prices, t-2prices, t-1
Variance ratio of residuals
Unmatched Matched
(c)Incorrect optimists
0 .5 1 1.5 2 2.5
employees, t avg. state of business, tfinancing coefficient, tstate of business, t-3state of business, t-2state of business, t-1state of business, tforeign orders, t-3foreign orders, t-2foreign orders, t-1foreign orders, tproduction, t-3production, t-2production, t-1debt share, tcapacity, t-3capacity, t-2capacity, t-1demand, t-3demand, t-2dep. var, t-1demand, t-1dep. var, t-2dep. var, t-3orders, t-3orders, t-2orders, t-1prices, t-2prices, t-3prices, t-1orders, t
Variance ratio of residuals
Unmatched Matched
(d)Incorrect pessimists
0 .5 1 1.5 2
financing coefficient, tstate of business, t-1state of business, t-2state of business, t-3state of business, tforeign orders, t-1foreign orders, t-3foreign orders, t-2foreign orders, temployees, tdebt share, tcapacity, t-3capacity, t-2orders, t-1orders, t-2orders, t avg. state of business, tproduction, t-3production, t-2production, t-1capacity, t-1demand, t-2demand, t-3demand, t-1dep. var, t-1dep. var, t-2dep. var, t-3orders, t-3prices, t-3prices, t-2prices, t-1
Variance ratio of residuals
Unmatched Matched
Notes: Figure shows variance ratios for the matching of correct and incorrect optimists and pessimists.
The variance ratio measures the difference between the variances orthogonal to the propensity score.
Details on this measure can be found in Subsection 3.3.2. Variance ratios below 0.8 and above 1.25 (dashed lines) are considered “of concern”; ratios below 0.5 and above 2 (grey solid lines) are considered
“bad” according to Rubin (2001).