STOCHASTIC

PROCESSES
Lecture 1
CC: Ms. Shiza Riaz Memon
What is Stochastic Process?
• Also called random process
• A stochastic process is a family or set of ordered random variables.
• The order is indicated by indexing each random variable in the family by a
subscript
• Usually the ordering is a result of the random variables being observed over time,
so xt is a random variable that models the value of the stochastic process at a
time t.
• The random variables in the set can be dependent on one another reflecting the
nature of the process being modelled.
Random Variable
• A random variable is a variable whose value is unknown or a
function that assigns values to each of an experiment's outcomes.
• A random variable can be either discrete (having specific values) or
continuous (any value in a continuous range).
• Why is it called a random variable?
• So the random variables are called random because the value of this
variable cannot be defined with certainty, we can only make a guess
and this guess is called the probability of having a particular value of a
random variable. In coin toss experiment, P(X=1) = 0.5.
Stochastic Process
• A stochastic Process is a collection of random variables {xt ; tET} defined on the same
probability space.
• Sample space is a collection or a set of possible outcomes of a random experiment.
• The set T is called the index set or time set or time domain
• For each tET , xt is a random variable and it denotes the state of the process at time t.
• The set of values that the random variables xt are capable of taking is called state
space of the process and is denoted by S.
• Let St be the set of all possible values of xt for tET.
• Normally, we have St=S (i.e independent of t),
• Otherwise, we take S= U (tET) St
Examples
• Example 1:
Let Xn be the temperature in Degree Celsius recorded in Karachi at 12 pm
on nth day. The state space of the stochastic process {Xn: n>/1} can be
taken to be S={20-45). Here T={1,2,3…..}.
• State Space is Continuous but Time is discrete. So this is discrete time
stochastic process
• Example 2:
Let Xn be the outcome of the nth toss of a six sided dice. The state space
of {Xn: n>1} is S={1,2,3,4,5,6}. Here T={1,2,3…} T is the toss not time.
• Both are discrete so this is Discrete time stochastic process
Examples
• Example 3:
A motor insurance company reviews the status of its customers
yearly, Three levels of discounts are possible (0%, 20%, 40%)
depending on the accident or claim record of the driver. Let Xn
denote the status of a customer after completion of the nth year. The
state space of the stochastic process {Xn: n>/0} is S={0,20,40}, Clearly
X0 denotes the status of a new customer and xo=0. Here T={0,1,2…..}
• State Space is discrete and time is also discrete.
Examples
• Example 4: Suppose a machine can be in two states: running or failed. Let Xt
be the state of the machine at time t. Then the state space of {Xt:t>/0} is
S={running, failed}. Here T=[0,infinity].
• State space is discrete but time is continuous
• One person cannot measure the state upto infinity but theoretically more
than 1 person can do this job.
• Example 5:
Let Xt be the state {w.r.t to Covid-19} of a person at time t. Then the state
space of {Xt:t>/0} can be S= {susceptible, infected, recovered, dead}. Here
theoretically we may take T=[0, infinity] but practically T may be [0,150] only.
• State space is discrete but time is continuous
Examples
• Example 6:
Let Xt be the temperature in degrees recorded at Karachi airport at
time t. Then the state space of {Xt: t>/0} can be S={20, 45]. Here T=[0,
to infinity]
• Both are continuous.
• Example 7:
Let Xt be the value of a stock at time t. Then the state space of {Xt:
t>0} is S={0, infinity}. Here T=[0, infinity]. In practice , the stock values
are discrete, being integer multiples of 0.01.
• Both are continuous
Possibilities of the State Space and Time
• Based on the nature of S and T, Stochastic Process can be classified as
follows:
• 1. Discrete Time and discrete state space.
• 2. Discrete time and continuous state space
• 3. continuous time and discrete state space.
• 4. Continuous time and continuous state space
Examples of Possible Stochastic Process
Activity:
Students are asked different processes that can be taken an example of
the possibilities of state space and time.
Applications of Stochastic Process
• Stochastic programs or processes are dynamics that form as a result of probabilistic variations or fluctuations.
• It has many applications in the financial sector, characterized by uncertainty in several areas, including
securities performance, market volatility, inflation rates, epidemic modeling for diseases like coronavirus,
comprehension of disease transmission, traffic simulations, and electrical engineering communications and
signal processing. More stochastic processes and their applications are discussed below:
• Many financial planners and managers use it to predict security and market behavior.
• Traffic simulations are done using it.
• One also uses it in epidemic modeling, like in coronavirus.
• It also gets applied in mobile cellular networks, communications, and signal processing of electrical
engineering.
• Finding the present guidelines for when and how much to order would be a stochastic process.
• The corporation would have to modify and reevaluate these procedures until they produce a more favorable
result if they are not successful—if a company frequently had too much or too enough inventory.
• In condensed physics, one uses it to describe a phenomenon accurately.
Examples
• The second example comprises a bus BlueCouch which takes students to and from the
dormitory complex, allowing the student’s union to arrive many times during the day. Bus
BlueCouch has an intake capacity of 50 students at one go. If the student’s number is fifty or
little lesser, then the bus makes them board it. However, when the number of students
exceeds 50, then only fifty students will get to board the bus, and the remaining will wait for
the next round of the bus.
• One can see that the number of students waiting for the empty bus to board its destination
takes the form of a random process. Moreover, when one counts the time of bus arrival, then
the number of students in a queue for bus arrival also forms a random process. Furthermore,
when one considers the number of students in the queue for a bus at any given the time of
day has the continuous space parameter. Hence, in this case, also, the process describes a
distinct state of the random process concerning continuous time.
• Lastly, in this example, the nth student reaching the bus stop has a certain time associated
with them. Thus, the nth student waiting time also forms a continuous-state random process.
Stochastic Modelling
• Stochastic modeling develops a mathematical or financial model to simulate an entire system and derives a set of
possible outcomes with its probability distribution.
• The stochastic modeling definition states that the results vary with conditions or scenarios.
• The modeling consists of random variables and uncertainty parameters, playing a vital role.
• It brings the probability factor in the calculation, which determines every possible outcome.
• For the probability determination of each result, the inputs are given variation from time to time.
• Thus, it contributes to the computation of probability distributions which are mathematical functions that reflect the
similarity of different outcomes.
• For example:
• The stochastic prototype provides several outcomes, and it is applied commonly in analyzing investment returns.
• First, it studies the market volatility based on the uncertain input and probability of various returns.
• Thus, stochastic modeling in finance helps investors discern the unknown outcomes that usually do not consider in
the analysis.
• The variable is generally time-series data depicting the difference between historical data, and the final distribution
result describes the inputs’ randomness.
Stochastic vs. Deterministic Modeling
• The prime difference between stochastic and deterministic
representation is noticeable in the name itself.
• The word “stochastic” indicates a random probability distribution,
whereas “deterministic” indicates the absence of randomness.
Monte Carlo Simulation
• The Monte Carlo simulation is a probabilistic model that can include
an element of uncertainty or randomness in its prediction.
• When you use a probabilistic model to simulate an outcome, you will
get different results each time.
• For example, the distance between your home and office is fixed.
• However, a probabilistic simulation might predict different travel
times by considering factors such as congestion, bad weather, and
vehicle breakdowns
Uses of Stochastic Modeling
• The application of stochastic modeling has a broad scope and importance in different fields and areas of
study. Some of the prominent uses of it are as follows:
• Investment decisions: Stochastic modeling in finance is predominantly associated with investment
decision-making. It is used in financial analysis to decide on investment decisions, return on investment,
etc. The model provides the probable outcomes corresponding to various scenarios.
• Agriculture: The model is used in the agriculture field for effective decision-making during uncertain
situations. For example, its application in farmland and irrigation management increases farmers’ profit.
• Weather forecasting: The application of stochastic approaches in substantial weather and climate
prediction prototype is proven, and stochastic predictands can correct many of the inaccuracies in the
other frameworks.
• Manufacturing: Stochastic replicas of a wide range of manufacturing systems are used for practical
examination purposes.
• Biochemistry and Systems Biology: Stochastic kinetic methods are used to structure the dynamics of
biochemical and biological networks.