**Distributional analysis**

Distributional analysis is the process of studying how often values occur in a set of data or in a population. It can be determined in both categorical and numerical data. When you organize the distribution of a categorical data, you see the percentage or the number of individuals in each category of data. Similarly, when you organize numerical data, you see the values in ascending or descending order or any other format you choose to arrange your data in. In other words, to understand a distribution, the values can be:

- Organized in percentages
- Ordered from the largest to the smallest or vice versa
- Grouped into various categories
- Put in charts and graphs to determine the variability in the data

## Types of distributions in data analysis

There are dozens of statistical distributions for numerical and categorical data. Here are some of the most common:

**Bernoulli distribution**: This distribution is used in determining probability. It has only two likely outcomes: – success (1) and failure (0) and a single trial, for instance “heads” or tails”. In Bernoulli technique, tossing a coin can record the number of times the coin lands on heads and the number of times it lands on tails. You can also use the method to find out how many girls or boys are born every day. The results from Bernoulli trials are usually determined as a success or failure. However, success does not mean the test is successful neither does failure means that the test has been a fail. Success in this case refers to the outcome you want to track and failure refers to the outcome you are not interested in. For example, you may want to find out the number of times a tossed coin lands on heads, so you call the heads a “success” and the tails a “failure”. The Bernoulli distribution leads to many other probability distributions including:- Geometric distribution
- Binomial distribution
- Negative binomial distribution

If you are finding the Bernoulli principle challenging, you can always hire one of our distribution analysis online tutors for professional expository services.

**Uniform distribution**: This is also known as a rectangular distribution, and it usually has a constant probability. The distribution is displayed in two parameters;*a*(the minimum) and*b*(the maximum). When you roll a six-sided die, the outcomes are always 1 to 6. The likelihood of landing any number between 1 and 6 is equal. Unlike Bernoulli distribution where you only have two probable outcomes, in a uniform distribution, you have six equal chances.**Binomial distribution**: This distribution is almost similar to Bernoulli distribution, only that for you to figure out the likelihood of an event to happen, you will need to do the trial for a given number of times. If a coin is tossed once, the likelihood of getting heads is 50%. If the same coin is tossed 20 times, the likelihood of getting heads is close to 100%. Each observation is independent, meaning, it does not affect the outcome of the next trial. Binomial distribution is very common in statistical analysis today. It can easily be used to determine the probability of events that have two possible outcomes. For instance, if a new drug has been introduced to treat a disease, only two outcomes are possible; either the drug is successful (cures the disease) or (it is a failure) does not cure the disease. Similarly, if you buy a lottery ticket, only two outcomes are possible; either you are going to win the money or you are not going to win the money. Generally, binomial distribution can be used in any event that can be only a success or failure.**Normal distribution**: Also known as the bell curve, a normal distribution is a distribution that occurs normally or naturally. For instance, when displaying results for an exam, you find that most students will score an average grade of C, while a small number will score an average grade of D or B. An even smaller number will score an A or an F. This usually creates a distribution that closely looks like a bell and hence the name “bell curve”. The normal distribution curve is symmetrical, meaning, 50 % of the data falls to the left of the average (mean) and the other 50 % falls to the right. For more information about normal distribution curves or for professional aid on the same, liaise with our distributional analysis assignment help experts.