Skip to main content

Table 5 Marginal effects of multinomial Probit model for innovation choice (second model)

From: Innovation decision of Tunisian service firms: an empirical analysis

Variables Probit model Multinomial Probit model
New-to-market only New-to-firm only Both
dy/dx SE dy/dx SE dy/dx SE dy/dx SE
Internal knowledge sourcing
 Engaging in innovation activities (ENGAG) −0.193 0.120 −0.062 0.041 −0.029 0.023 0.091 0.048*
External knowledge sourcing
 Cooperation (COOPER) 0.191 0.087** −0.039 0.044 0.025 0.029 0.014 0.057
 International orientation (INTER) 0.040 0.020** −0.010 0.019 0.000 0.011 0.010 0.023
Absorptive capacity
 Education level (QUAL) 0.060 0.125 −0.041 0.085 0.164 0.087*** −0.122 0.124
 Group membership (APP GROUP) 0.057 0.046 −0.022 0.036 0.037 0.035 −0.014 0.056
Ressources
 Size (SIZE) −0.007 0.048 0.063 0.044 0.057 0.036 −0.121 0.056**
 Size-squared −0.003 0.006 −0.005 0.004 −0.005 0.004 0.010 0.006*
 Firm vintage (AGE) 0.009 0.005 −0.004 0.003 0.001 0.001 0.002 0.003
The aims of the innovation
 Replace obsolete services (SERV_OBS) −0.023 0.020 −0.002 0.013 −0.006 0.010 0.009 0.017
 Improve service quality (QUAL_SERV) 0.043 0.045 0.119 0.056** −0.021 0.021 −0.097 0.059*
 Extend the line of services (GAM_SERV) 0.020 0.022 0.038 0.024 0.021 0.014 −0.059 0.029**
 Sustain the market share (PART_MAR) 0.037 0.037 −0.125 0.056** 0.015 0.019 0.110 0.060*
 Reduce production cost (RED_COUT) 0.037 0.019* −0.019 0.019 −0.025 0.010** 0.044 0.023*
Log-likelihood −1526.3879 −4360.0491
Likelihood Ratio statistic (LR) 20814.832 6830.8306
Prob > LR [0.000] [0.000]
AIC 4627.886 8776.098
BIC 4664.217 8842.443
R squared 0.80 0.44
Number of observation 99 79
  1. Significance level: ***p < 1 %, **p < 5 %, *p < 10 %