Building Discrete Distributions

Building Discrete Distributions 1
Data Analysis
Name
Institution
Date
Professor

Building Discrete Distributions 2
1.0 Definition of Terms.
As an analyst, a prerequisite is to understand the different probabilistic distributions. Here we are
going to survey one major distribution branch, from the two groups, Discrete and Continuous.
First, before understanding the term Discrete Probability Distribution, we need to understand the
meaning of the term random variable.
A random variable says x, is a numerical description of the outcome of a random experiment that
by chance can assume different values (Forsyth, 2018). Discrete Random Variables thus will
refer to random variables that usually assume a finite number of terms with intervals in between.
For instance, a randomly selected number of hours is a discrete random variable in this case, with
n=10. Now, a probability distribution is a schedule of distribution of probabilities in terms of the
values recorded. This is denoted by P(X=x) where X is the observation and x are the numbers of
times of occurrence. Thus, it goes without saying that a Discrete Probability Distribution is a
Schedule or Chart or Function describing the distribution of different probabilities over
the values of a discrete random variable.
1.1 Procedures.
From the three major categories of Discrete Probability distribution, which include, Subjective,
Relative (from past data) and classical methods. Here we will use an empirical Discrete
Distribution can thus be the center stage of this analysis. The steps to be followed to build up the
distribution include the following.
Definition of the random variable in the process.
Construction of a Frequency distribution table.

Building Discrete Distributions 3
We then need to calculate the Relative Frequency of each observation set.
Ascertain whether the Probabilities are all less than or equal to zero, and also check
whether the summation of all the probabilities equals to 1.
Next step is to visualize the Distribution using a Histogram.
We lastly can make the predictions of the future events given the previous information.
2.0 Definition of Problem Statement Under Analysis.
From the dataset, it has been realized that the call category table has discrete values which have
been coded for various categories of calls made to the call center. It, therefore, calls for deep
analysis to the purpose as to why many calls are made to the call center and how they are
distributed. This can be used to come up with a predictive model to see what the main reasons
people make calls is going to be for a certain time or place. The second issue under investigation
is to know how the number of calls that were answered in a sample hour varied depending on the
day of the week.
2.1 Constructing Discrete Distributions from the Dataset.
While using excel, we can easily use the inbuilt features to sort the data into discrete appearance.
We use the advanced filters to come up with events and the count-ifs formula to come up with
the number of times they are appearing. This creates a relative frequency when we take the
frequency of an event divided by the sample space. For this case, the sample space is constant
and is 500. This is a combination of all the ten samples recorded staff each depending on the
category. The above is for the third tabulation. However, for the first table, the descriptive