Thursday, March 14, 2013

Relationships and statistics

Real life relationships would be much more easier if we could treat it in our mind as a markov process.

In probability theory, A stochastic process is a collection of stochastic variables, which is often used to represent the evolution of some random(stochastic) value, or system, over time.

A stochastic variable is a variable whose value is subject to variations due to chance. Thats why its also called a random variable.

Consider a person's relationship curve with another person is a random variable.
When you get related to a another person(friendship, workcolleague, team-mate,spouse,anyother), the relationship curve involving either of you with others in the network on either side becomes a stochastic/random process with a conditional probability which represents the evolution of the state of your relationship with the others in the family over time and is dependent on the relationship value of the other person involved at any given time.

If this stochastic process can become memory-less process, i.e. a Markov process, where the future state of this system is dependent only on current state and not on the states that existed prior to current state,
i.e. if the future of your relationship with anyone in the network is purely based on current relationship state(good/bad) and not based on previous history of actions,


then by controlling current state, you can ensure that the future states will always be good.


The above is the result of studying NLP course by Columbia University in the state of New York via coursera.