To prepare for an upcoming exam, we spent the week diving into hands-on data analytics under the guidance of Dr. Francis Okoye. As a result, we were able to cover a wide range of topics for revision. Many students are eager to learn as much as possible from the facilitator’s guidance. During the sessions, Dr. Okoye asked us about our challenges with data analytics, and of course, we listed them down. We focused on probability, linear programming, correlation, and regression.
Probability
Probability plays a crucial role in decision-making, as it helps executives navigate risk and uncertainty. It provides a numerical measure of the likelihood of an event occurring, with the total probability always equalling 1. A high probability value indicates a high likelihood of the event occurring, while a value close to 0 suggests it is unlikely. Probability is a measure of the likelihood of an event occurring, with a range of values from 0 to 1. In decision-making, probability plays a vital role in understanding the potential outcomes of a particular action or decision. For example, in the field of finance, the probability is often used to predict the likelihood of certain financial events occurring, such as stock prices or interest rates.
He, however, displays all such formulas and other mathematical models that can use in calculating probability. “But what’s important as executives, is to be able to interpret the result”, he said.
The facilitator also discussed important concepts such as population, experiment, sample space, event, and sample point of interest. We also learned about the probability distribution.
In our session, we covered the concept of probability distribution, which is a theoretical frequency distribution that is categorized into two types: discrete and continuous. A discrete probability distribution is used to calculate occurrences that have finite outcomes, such as binomial, Poisson, and Bernoulli distributions, all of which involve counting how many times an event occurs. During the session, we only focused on the binomial distribution, which has two possible outcomes, typically a finite set of outcomes such as zero or one. For instance, flipping a coin results in either heads or tails.
A continuous probability distribution, on the other hand, measures a range of data. Unlike discrete probability distribution, which determines “at a point,” continuous probability distribution deals with “within a range.” This type of probability distribution is used to analyze data that appears to be infinite in nature. An example of this is the normal distribution, which is a probability distribution in which the random variable X can take on any value. Since X assumes infinite values, we usually speak in terms of ranges of values.
To calculate the probability that X falls between two values (a and b), we use the formula F(x) = P(a <= x >= b), which equates to the area under the curve or bell shape from a to b. We also conducted some practical exercises during the session to further illustrate these concepts.
Additionally, we revisited Bayes theorem, which we previously discussed in detail in one of my earlier blogs, so there’s no need to repeat it here. Stay tuned for more insights in upcoming posts!
