The article introduces a new model called the recursive multinomial probit model, which can help analyze relationships between different choices in innovation studies. This model is an extension of an existing model and allows for more than two possible outcomes in decision-making. The researchers used a Bayesian approach with Gibbs sampling to estimate the model's parameters and found that it performed well in simulations with artificial data. This new model has the potential to enhance the analysis of causal relationships in innovation research.