Skip to main content

Table 8 Regression model including the number of reputable investors backing the startup by type

From: Signals in equity-based crowdfunding and risk of failure

Parameters Full model No industry dummies Minimal AIC Logit
Degree 0.35* (0.62) 0.25** (0.55) 0.28*** (0.48) − 0.19 (0.12)
Equity offered 0.86*** (0.06) 0.89** (0.05) 0.88*** (0.04) − 0.02** (0.009)
#BA 0.93 (0.05) 0.97 (0.04) 0.98 (0.04) 0.02 (0.03)
#VC 1.58 (0.30) 1.34 (0.27) 1.38 (0.26) 0.08 (0.06)
#Other investors 1.57 (0.40) 1.33 (0.37) 1.45 (0.36) 0.08 (0.08)
#Invest5k 1.05*** (0.02) 1.04*** (0.01) 1.04*** (0.01) 0.01** (0.005)
#Updates 0.97 (0.06) 0.99 (0.05) 0.99 (0.05) − 0.0025 (0.01)
Start campaign 1.10 (0.17) 0.94 (0.15)   − 0.07*** (0.03)
Venture age 0.72* (0.19) 0.85 (0.14) 0.85 (0.13) − 0.02 (0.03)
Positive sales 1.00 (0.58) 1.09 (0.52)   
#Investors 1.00 (0.00) 1.00 (0.00)   
Funding amount 1.09 (1.07) 1.00 (0.87)   
Target attainment 0.48 (0.64) 0.40 (0.56) 0.48 (0.54) − 0.26** (0.13)
Big city 0.57 (0.55) 0.60 (0.54)   
Business value 0.89 (0.09) 0.90 (0.08) 0.90 (0.06) − 0.03 (0.02)
Industry experience 0.50* (0.39) 0.62 (0.36) 0.56 (0.36) − 0.20** (0.09)
Management size 0.90 (0.15) 0.91 (0.14)   
Entrepreneurial company 2.97* (0.61) 3.51** (0.58) 2.96* (0.57) 0.37** (0.18)
Follow-up campaign 6.04** (0.82) 4.51* (0.79) 4.26** (0.73) 0.09 (0.18)
Industry dummies Yes No Yes Yes
Observations 88 88 88 88
Concordance 0.773 0.731 0.757 0.815
R2 0.120 0.091 0.104 0.306
  1. The values in the first three models of the table are the estimated hazard ratios, the standard errors of the natural logarithm of the hazard ratios are given in parentheses. The full model includes all variables. In “no industry dummies” industry dummies are excluded. “Minimal AIC” represents a model obtained by stepwise exclusion of variables, so that the AIC is minimized but all variables of interest for our hypotheses are included. “Logit” contains the estimated AMEs (standard errors in parentheses) using a logit model and the variables of Minimal AIC plus Start campaign. We use McFadden’s R-squared for the Cox models and Tjur’s R-squared for the logit model. Number of events: 38 failures
  2. *p < 0.1; **p < 0.05; ***p < 0.01