A Scientific Approach To Entrepreneurial Decision Making

Last registered on November 08, 2023


Trial Information

General Information

A Scientific Approach To Entrepreneurial Decision Making
Initial registration date
September 15, 2017

Initial registration date is when the trial was registered.

It corresponds to when the registration was submitted to the Registry to be reviewed for publication.

First published
September 16, 2017, 8:34 PM EDT

First published corresponds to when the trial was first made public on the Registry after being reviewed.

Last updated
November 08, 2023, 9:29 AM EST

Last updated is the most recent time when changes to the trial's registration were published.



Primary Investigator

ICRIOS, Bocconi University

Other Primary Investigator(s)

PI Affiliation
ICRIOS, Bocconi University

Additional Trial Information

Start date
End date
Secondary IDs
Prior work
This trial is based on or builds upon one or more prior RCTs.
In explaining the high rates of startup failures, the entrepreneurship literature has emphasized several factors, such as the size and characteristics of the founding team or the technology. This study focuses instead on the role of entrepreneurial decision-making, whose importance in affecting new venture performance has become increasingly important in entrepreneurship and strategic management research and practice. Our randomized controlled trial tests if, to what extent and under which conditions the adoption of a scientific approach to entrepreneurial decision making improves performance. By scientific approach to entrepreneurial decision making we mean that entrepreneurs should behave like scientists, accurately framing and identifying the problem they wish to address, articulating theories, defining clear hypotheses, conducting rigorous tests to prove or disprove these hypotheses, measuring the results of the tests, and making decisions based on these tools.
Building on a pilot study (RCT) conducted at Bocconi University involving 116 Italian founders of new startups we are conducting another RCT on 265 startups to identify the mechanisms that explain why a scientific approach to entrepreneurial decision making affects firm performance. We argue that entrepreneurial decision-making can benefit from the use of a scientific approach because entrepreneurs can recognize when their projects exhibit low or high returns, or when it is profitable to pivot to alternative ideas. In other words, entrepreneurs with thoroughly thought-through, validated “theories” of their business and hypotheses of what customers want that are soundly tested through experiments, are better able to mitigate their biases when they analyze market signals, reducing the likelihood of incurring in false positives and false negatives.
External Link(s)

Registration Citation

Camuffo, Arnaldo and Arnaldo Camuffo. 2023. "A Scientific Approach To Entrepreneurial Decision Making." AEA RCT Registry. November 08. https://doi.org/10.1257/rct.2205-4.0
Former Citation
Camuffo, Arnaldo and Arnaldo Camuffo. 2023. "A Scientific Approach To Entrepreneurial Decision Making." AEA RCT Registry. November 08. https://www.socialscienceregistry.org/trials/2205/history/200431
Sponsors & Partners

There is information in this trial unavailable to the public. Use the button below to request access.

Request Information
Experimental Details


Startups will receive 8 sessions of training plus coaching at Bocconi University, Milan. These sessions will include lecturettes and coaching by qualified mentors/instructors each working with a subset of the startup sample. Treated and control startups will receive the same amount of training on entrepreneurial decision making (on topics like business model canvas, customers' interviews, minimum viable products/services, concierge/prototype, etc.). The treated startups will be taught how to make entrepreneurial decisions according to a scientific approach.
Intervention Start Date
Intervention End Date

Primary Outcomes

Primary Outcomes (end points)
1. Revenue: our main dependent variable is the amount of revenues (in euros).
2. Dropout: this is a binary variable that takes value 0 until the firm drops out (they abandon the program and cease the startup), 1 in the time period in which the firm drops out, and it is a missing value thereafter. In order to avoid attrition biases, we will check that the entrepreneurs that leave the program will actually cease any entrepreneurial activity.
3. Pivot: this is the cumulative number of times in which a startup makes a major change to its business model. We defined a change to be major by analyzing whether the entrepreneur moved from the original idea to another idea that changed the core value proposition of the product or service.
Primary Outcomes (explanation)

Secondary Outcomes

Secondary Outcomes (end points)
Secondary Outcomes (explanation)

Experimental Design

Experimental Design
The RCT focuses on nascent startups. We do not restrict to particular industries. We advertise the program through digital channels as a general course overseeing all the important aspect of new venture creation. The course is free of charge in order to ensure participation of firms with limited financial resources. Startups receive training at Bocconi University, Milan, Italy. The same amount of training is offered to both treatment and control groups in order to ensure that there was no other effect in the treatment than a scientific approach to entrepreneurial decision-making. 7 instructors/coaches have been trained to deliver the training using standard materials, purposely designed. Each instructor/coaches teaches two classes (one subgroup of treated startups and one subgroup of control startups). The Bocconi University research team designs, coordinates and oversees all the activities, ensuring that the learning modules and coaching activities are appropriately carried out by the instructors/coaches.
Experimental Design Details
Before starting the training program we ask to all the applicant startups to send us a pitch of their business idea and the vitae of the founders. On the basis of this information, we categorized them across stages of development, industries and regions of origin. Out of the 300+ applicants to the program, we select 265 startups early stage. These are admitted to the program conditional aupon they abide by the program rules and take a detailed survey (batteries of variables for randomization balance checks)
Participating startups are informed that Bocconi University is investigating the determinants of the success of startups, so we were providing management advice and training to the firms and collecting performance data. In other words, they knew that they were participating in an activity in which we were offering a service free of charge in exchange for monitoring their actions for educational and research purposes. Also we told them that there were two groups of startups with some differences in the content of the training program. However, they did not know whether they were part of the treatment or control group.
In order to avoid contamination, treated and control startups are taught/coached in different time slots of the same day (morning and afternoon). All communications to the two groups of startups are distinct. Individual level, team level and performance data are gathered periodically by a team of 15 research assistants following a purposely defined research protocol. Data gathering also includes startups’ learning and behavioral monitoring (level of adoption of a scientific approach to entrepreneurial decision making), conducted via phone interviews every other week.
Randomization Method
Pure parallel randomization, done in office by a computer using STATA. After being randomly assigned into treatment and control group, 14 subgroups of startups (7 for the treatment and 7 for the control groups) were created and randomly matched with the instructors/coaches so that each instructor/coach teaches to two subgroups -of approximately 18 startups- one of treated and one of control startups. Subgroups were created subsetting the sample (treatment and control groups) into 14 groups (to be allocated randomly to the 7 instructors/coaches) and within categories as well (to have balanced subgroups). Randomization checks: reduced-form ordinary least squares (OLS) regressions of startup characteristics on a dummy for the allocation in the treatment or control group.
Randomization Unit
The unit of randomization is the individual startup.
Was the treatment clustered?

Experiment Characteristics

Sample size: planned number of clusters
not clustered.
Sample size: planned number of observations
265 startups X 18 (points in time) = 47700 observations
Sample size (or number of clusters) by treatment arms
265 Startups (132 in the treatment group; 133 in the control group)
Minimum detectable effect size for main outcomes (accounting for sample design and clustering)
We perform sample size calculations using STATA. This RCT would like to test if a scientific approach to entrepreneurial decision making increases the average revenues of a treated start-up by 10 times compared with the control group (based on the average revenues of 29.4 euro that we observed last year). We do not anticipate the standard deviation of revenues to be larger than what we observed last year (16925). We estimate the sample size required to detect the anticipated difference by using a 5% level two-sided test with 80% power. Based on our calculations, the sample size required for this study is 215. Given that there are 265 start-ups participating in our trial, the power of the study is estimated to be 0.87. We also calculate the minimum detectable standardized difference given the requested power and sample size is 0.17, which corresponds to average revenues of roughly 2950 euros.

Institutional Review Boards (IRBs)

IRB Name
Ethics Committee of Università Commerciale Luigi Bocconi
IRB Approval Date
IRB Approval Number
Analysis Plan

There is information in this trial unavailable to the public. Use the button below to request access.

Request Information


Post Trial Information

Study Withdrawal

There is information in this trial unavailable to the public. Use the button below to request access.

Request Information


Is the intervention completed?
Intervention Completion Date
December 16, 2017, 12:00 +00:00
Data Collection Complete
Data Collection Completion Date
March 31, 2019, 12:00 +00:00
Final Sample Size: Number of Clusters (Unit of Randomization)
257 start-ups
Was attrition correlated with treatment status?
Final Sample Size: Total Number of Observations
250 start-ups
Final Sample Size (or Number of Clusters) by Treatment Arms
125 start-ups in the treatment group and 125 start-ups in the control group
Data Publication

Data Publication

Is public data available?

Program Files

Program Files
Reports, Papers & Other Materials

Relevant Paper(s)

This paper studies the implications of an approach in which managers and entrepreneurs make
decisions under uncertainty by formulating and testing theories such as scientists do. By
combining the results of four Randomized Control Trials (RCTs) involving 754 start-ups and smallmedium enterprises and 10,730 data points over time, we find that managers and entrepreneurs
who adopt this approach terminate more projects, do not experiment with many new ideas, and
perform better. We develop a model that explains these results.
Camuffo, A., Gambardella, A., Messinese, D., Novelli, E., Paolucci, E., & Spina, C. (2021). A scientific approach to innovation management: theory and evidence from four field experiments.
Identifying the most promising business ideas is key to the introduction of novel firms, but
predicting their success can be difficult. We argue that if entrepreneurs adopt a scientific approach
by formulating problems clearly, developing theories about the implications of their actions, and
testing these theories, they make better decisions. In particular, this approach helps entrepreneurs
make more precise predictions of the value of their idea and to spot new ideas with higher
expected returns. We also examine the mechanisms with which the scientific approach works.
Specifically, we posit that scientific entrepreneurs are more precise initially, and less precise later
on because they envision new version of their business idea that are worth assessing. Using a field
experiment with 250 nascent entrepreneurs attending a pre-acceleration program, we provide
evidence consistent with these mechanisms. We teach the treated group to formulate the problem
scientifically and to develop and test theories about their actions, while the control group follows a
standard training approach. We collect 18 data points on the decision-making and performance of
all entrepreneurs for 14 months. Results show that increased precision in the assessment of the
value of the business idea of treated entrepreneurs raises the probability that they close their startups. Scientific entrepreneurs are also more likely to see new opportunities with higher positive
outcomes which prompt them to pivot to these new ideas and perform better.
Camuffo, A., Gambardella, A., & Spina, C. (2020). Small changes with big impact: Experimental evidence of a scientific approach to the decision-making of entrepreneurial firms.

Reports & Other Materials