New York Investment Network


Recent Blog


Pitching Help Desk


Testimonials

"I have been an investor for 2 years. Through this site I have managed to finance 4 projects. I am very pleased with my membership. "
Dave M.

 BLOG >> Recent

Computing the Likelihood of Startup Success [Bayesian Inference
Posted on April 16, 2013 @ 08:51:00 AM by Paul Meagher

There are many ways to compute a conditional probability such as P(H|E).

The simplest ways to compute P(H|E) is:

P(H|E) = P(H & E) / P(H)

In my last blog introducing Bayes Theorem, I showed how to re-arrange terms so that you could compute P(H|E) using a version of the conditional probability formula called Bayes Theorem:

P(H|E) = P(E|H) * P(H) / P(E)

I also showed that this equation could be further simplified to:

P(H|E) ~ P(E|H) * P(H)

Where the symbol ~ means "is proportional to". The equation says that the probability of an hypothesis given evidence P(H|E) is equal to the likelihood of the evidence P(E|H) given the hypothesis multiplied by a prior assessment of the probability of our hypothesis P(H). The likelihood term plays a critical role in updating our prior beliefs. So how is it computed and what does it mean? That is what will be discussed today.

Below I have fabricated a data table consisting of 10,000 startups classified as successful S (1200 instances) or unsuccessful U (8800 instances). In a previous blog, I reported a finding that claimed the success rate of first time startups is 12% which equates to 1200 instances out of 10,000. The data table also includes the outcome of two diagnostic tests. A positive outcome on both tests is denoted ++, while a negative outcome is denoted --. Each cell displays a joint frequency value and a corresponding likelihood value for the relevant combination of diagnostic tests and startup outcomes.


Tests
Outcome # Startups ++ +- -+ --
S 1200 650 (.54) 250 (.21) 250 (.21 50 (.04)
U 8800 100 (.01) 450 (.05) 450 (.05) 7800 (.89)
Total 10,000

Computing a likelihood from this data table is actually a simple calculation involving the formula:

P(E|H) = P(H & E) / P(H)

To calculate the likelihood of two positive tests given that a startup is successful P(E=++|H=S), we divide the joint frequency of the evidence E=++ when a startup is successful H=S (which is 650) by the frequency of startup success H=S (which is 1200). So 650/1200 is equal to .54 which is the value in parenthesis beside 650 in the table above. To calculate the likelihood of two positive tests given that a startup is unsuccessful P(E=++|H=U), we divide the joint frequency of the evidence E=++ when a startup is unsuccessful H=U (which is 100) by the frequency that a first time startup is unsuccessful H=U (which is 8800). So 100/8800 is equal to .01 which is the value in parenthesis beside 100 in the table above.

The likelihood calculation tells us which hypothesis makes the evidence most likely. In this case, the hypothesis that the startup is successful makes the positive outcome of our two diagnostic tests (E=++) more likely (.54) than the hypothesis that the startup is unsuccessful (.01). We can examine the likelihood values in each column to determine which hypothesis makes the diagnostic evidence more likely. You can see why the likelihood values are important in updating our prior beliefs about the probability of startup success. We can also appreciate why some would argue that likelihood values are sufficient for making decisions - just compare the relative likelihood of the different hypothesis given the evidence.

Permalink 

 Archive 
 

Archive


 October 2019 [1]
 September 2019 [1]
 July 2019 [1]
 June 2019 [2]
 May 2019 [2]
 April 2019 [5]
 March 2019 [4]
 February 2019 [3]
 January 2019 [3]
 December 2018 [4]
 November 2018 [2]
 September 2018 [2]
 August 2018 [1]
 July 2018 [1]
 June 2018 [1]
 May 2018 [5]
 April 2018 [4]
 March 2018 [2]
 February 2018 [4]
 January 2018 [4]
 December 2017 [2]
 November 2017 [6]
 October 2017 [6]
 September 2017 [6]
 August 2017 [2]
 July 2017 [2]
 June 2017 [5]
 May 2017 [7]
 April 2017 [6]
 March 2017 [8]
 February 2017 [7]
 January 2017 [9]
 December 2016 [7]
 November 2016 [7]
 October 2016 [5]
 September 2016 [5]
 August 2016 [4]
 July 2016 [6]
 June 2016 [5]
 May 2016 [10]
 April 2016 [12]
 March 2016 [10]
 February 2016 [11]
 January 2016 [12]
 December 2015 [6]
 November 2015 [8]
 October 2015 [12]
 September 2015 [10]
 August 2015 [14]
 July 2015 [9]
 June 2015 [9]
 May 2015 [10]
 April 2015 [10]
 March 2015 [9]
 February 2015 [8]
 January 2015 [5]
 December 2014 [11]
 November 2014 [10]
 October 2014 [10]
 September 2014 [8]
 August 2014 [7]
 July 2014 [6]
 June 2014 [7]
 May 2014 [6]
 April 2014 [3]
 March 2014 [8]
 February 2014 [6]
 January 2014 [5]
 December 2013 [5]
 November 2013 [3]
 October 2013 [4]
 September 2013 [11]
 August 2013 [4]
 July 2013 [8]
 June 2013 [10]
 May 2013 [14]
 April 2013 [12]
 March 2013 [11]
 February 2013 [19]
 January 2013 [20]
 December 2012 [5]
 November 2012 [1]
 October 2012 [3]
 September 2012 [1]
 August 2012 [1]
 July 2012 [1]
 June 2012 [2]


Categories


 Agriculture [71]
 Bayesian Inference [14]
 Books [15]
 Business Models [24]
 Causal Inference [2]
 Creativity [7]
 Decision Making [15]
 Decision Trees [8]
 Design [36]
 Eco-Green [4]
 Economics [12]
 Education [10]
 Energy [0]
 Entrepreneurship [59]
 Events [2]
 Farming [20]
 Finance [25]
 Future [15]
 Growth [18]
 Investing [24]
 Lean Startup [10]
 Leisure [5]
 Lens Model [9]
 Making [1]
 Management [9]
 Motivation [3]
 Nature [22]
 Patents & Trademarks [1]
 Permaculture [34]
 Psychology [1]
 Real Estate [2]
 Robots [1]
 Selling [11]
 Site News [15]
 Startups [12]
 Statistics [3]
 Systems Thinking [3]
 Trends [7]
 Useful Links [3]
 Valuation [1]
 Venture Capital [5]
 Video [2]
 Writing [2]