Data Organization

What is Organisation of Data?

Imagine a room full of files and documents kept together in an unorganised manner and you’ve been asked to find one particular file as an urgency. How would it be if you go to a library to find a particular book of a genre you have in your mind and the librarian asks you to find it yourself from 50,000 books kept on 500 different shelves. Anything messier makes the work harder and waste most of your time. Data organization is a tool which helps to organize and classify data sets to make them more useful. With the help of this method many IT experts have been able to apply this primarily to physical records, although there is no doubt that some types of data organization can also be applied to digital records. In fact, there are still many other ways through which IT professionals work on the principle of data organization which under  the more general heading are classified as "data management." 

Another essential component of enterprise data organization is the analysis of both relatively structured and unstructured data. Structured data holds data in tables that can be easily integrated into a database and can be further  fed into analytics software or any other particular applications. Unstructured datas are considered raw and unformatted, just like in a simple text document, where information is scattered throughout random paragraphs. Thanks to few experts who have developed tech tools and resources to handle relatively unstructured data. These datas are integrated into a holistic data environment.

To make better use of the data assets, businesses adopt data organization strategies. Data assets hold a very valuable position in the world as it is held by enterprises across many different industries. Data organization is considered  as a component of a comprehensive strategy which helps to  streamline business processes whether it be getting better business intelligence or generally improving a business model.

Organisation Of Data In Statistics?

Organisation of data in statistics is a tool or you can say, a process, that organizes the collected factual materials which are considered necessary in the scientific community to validate research findings. Research datas are the ones that are collected, observed or created for the purpose of analysis to produce original research results. But why are they so important that one who acknowledges it is always benefited? 

Here is why They are Important:

  • Datas are intended to showcase facts which will become meaningless if not properly preserved and interpreted. 

  • The collection of data and it’s analysis acts as a right hand for the researcher. It helps them to discover answers to their research questions and hypothesis. In some cases, it even predicts future outcomes.

Ways of Organisation of Data in Statistics In Research

There are three ways to organize data in a research 

  1. Frequency Distribution Table 

  2. Stem And Leaf Diagram

  3. Chart

Frequency Distribution Table: 

In order to construct a frequency table, we need to follow few steps, they are:

Step 1: Construct a table of three columns. In the first column, all the data values are to be written in ascending order. 

Step 2: In the second column, we need to go through the list of data values and and place one tally mark at an appropriate place for every data value. Once 5 tally marks are reached, draw a diagonal line through the first four tally marks. This process will be continued until all the datas  values in the list are tallied. 

Step 3: The number of tally marks are to be counted for each data value and write it in the third column.

Types Of Frequency Distribution

A. Categorical / ungroup: This helps to determine the order to list the categories. The total number of occurrences of each category is listed thereafter.

Example: The following data represents the score of 10 students: 8, 6, 4, 5, 8, 9, 10, 10, 6.

Now, construct a table with three columns. The 1st column represents what is being arranged in ascending order. The lowest mark is 4. So, we have to start from the 1st column as shown below. The second column is tally and the third column is frequency. 


SCORES

TALLY

FREQUENCY

4

I

1

5

I

1

6

II

2

7

0

0

8

III

3

9

I

1

10

II

2


B. Group: A group can be defined as data being organized into groups known as classes. There are few things to remember before constructing a table. They are, 

  1. Classes between 5 - 20 are to be used

  2. Classes are mutually exclusive

  3. All the classes are to be included even if the frequency is zero. 

  4. Width for all the classes would be same

  5. Convenient numbers for the class limit are to be used

  6. The sum of the frequency is the total data set

  7. There should be enough classes for all the datas

  8. If the class has no data, use zero rather than leaving it blank. 

Example: The following data represents the ages of 20 respondents 

21, 26, 18, 45, 32, 41, 42, 22, 28, 26,

33, 20, 26, 44, 46, 21, 24, 36, 39, 30.

 

1. Determine the highest and lowest value and then compute the range: 

                Range = Highest value - Lowest Value

I.e., range = 46 - 18 = 28.


2. Decide the number of classes you want to have.


3. Compute the class width or class interval.

            Class Interval = Range/ # of classes

I.e., class interval = 28/5 = 5.6 or 6.


4. Lower class limit (smallest number of each class) and upper class limit (largest number of each class) needs to be mentioned. 

Example: LCL = 18, 24, 30, 36, 42.

                UCL = 23, 29, 35, 41, 47. 


5. Class boundaries - these are the number that separates the classes from one another by subtracting .5 to lower limit and add .5 to upper limit of each class. 

Example: (LL) 18 - .5 = 1.5 (class boundary) and (UP) 23 + .5 = 23.5 (class boundary)

And thus plot the table as this: 

Stem And Leaf Diagram: 

This method is used to organize statistical data to help us to see values according to their size and order them accordingly. Here, each data value is split into a stem and a leaf. The leaf is the digit to the right while the stem is the remaining digits to the left. For example, in the number 243, the stem is 24 and 3 is the leaf. 

Graph or Chart: 

A graph or a chart condense large amounts of information into easy-to-understand formats that clearly and effectively communicate important points 

FAQ (Frequently Asked Questions)

Question 1: What are the Different Types of Chart?

Answer 1: There are four different types of chart, they are:

  1. Bar chart

  2. Pie chart 

  3. Line chart

  4. Histogram

Question 2: What are the Ways to Format a Chart?

Answer 2 : To make your chart look good, always keep few things in your mind, they are: 

  1. Keep it simple with only essential information. 

  2. Give your chart a title to convey the purpose.

  3. Specify the units of measurement on the x and y axis.

  4. Label each part of your chart.