When I wrote first article about Statistics, Some people sent me message to continue that series. Now this is second part of series.

– Discrete Random Variable

– Continuous Random Variable

– Statistical Data

– Nominal, Ordinal, Interval and Ratio

These are the things I will tell you in second part.

**Discrete Random Variable** = If a set has a finite number of elements, or has an infinite countable number of elements, that set is a discrete set. The variable is a discrete random variable if the probabilities of the variable create form a discrete set.

Example :

- The probability of a person toss the coin until it reaches heads is an example of a countably infinite number.

**Continuous Random Variable** = If a set has uncountably infinite elements, that set is a continuous set. It is a continuous random variable if the possible values of a random variable form a continuous set.

Example :

- temperature of the classroom
- The weight of baby of newborn

**Statistical Data** = Statistical data are the raw material of statistical research. Data is formed when measurements are made and observations recorded.

Example of Data : The weights of animals, personal characteristics of people and ‘yes’ or ‘no’ answers to the question asked

Variables are measured for 4 situation:

- Nominal
- Ordinal
- Interval
- Ratio

**Nominal** = Statistics are concerned with numerical data, data such as ‘yes’, ‘no’ answers or marital status can be classified by numbers. For example, It can be defined as ‘yes’ 1, ‘no’ 0. Similarly, for marital status, married, single, widowed, divorced can be recorded as 1, 2, 3 and 4, respectively. In this way, categorical data is expressed as numerical data. Qualitative is information about properties that cannot be measured exactly. Marital status, gender, eye color are examples of qualitative data. It is expressed in quantitative, numerical data. Age, height, weight, pressure are examples of quantitative data. The numbers we obtain by making sense of the various categories in this way are expressed as nominal data. Although nominal data are numerical, they do not have any numerical characteristics. Mathematical operations will not be logical and suitable for such data.

**Ordinal** = **Ordinal** data has partial numerical properties. For example, in mineral science, the hardness of solids is sometimes determined by observing which one scratches which. If one mineral stone scratches another, that mineral stone is considered to be harder. However, ‘>’ is not always used to mean “greater than”. For example, it can mean “happier”, “more preferred”, “more difficult”.

**Interval** = If we can make meaningful differences with the data, but multiplication and division operations are not logical, this kind of data is **interval** data. In this example, we can show air temperatures as an example. We can write 107° > 86 ° and 81 °< 131 °. However, we can not say 68 ° – 63 ° = 121 ° – 116 °. In addition, The number 0 does not mean that there is no temperature. In this scale, there is no absolute 0 point, 0 does not mean absence.

**Ratio** = If we can make meaningful divisions with the data, this data is **ratio** data and this type of data can be encountered frequently in daily life. It includes all of the ordinary measurements such as length, height, amount of money, weight, volume, area, pressure, time. There is an absolute point, it expresses absence.

Thank you for reading from the beginning to the end. It is important for me that you give feedback for the continuation of my articles. Have a nice day

**References **:

–https://istatistik.ege.edu.tr/index.php

–http://globalaihub.com/r-for-machine-learningseries-1/

–http://globalaihub.com/what-is-the-difference-between-data-science-machine-learning-and-big-data/