# Data Analysis Methods and Areas of Usage

Data analysis is one of the most important research techniques of today. The records of the behaviors of each area of life constitute the data. How this data is analyzed, which does not mean much on its own, is gaining great importance in this case. Information of data analysis methods and areas of usage will help you to gain the best results.

**Quantitative and Qualitative Data**

In order to determine the most accurate analysis method for the available data, it is necessary to understand what kind of data that we have. Data is divided into two types: quantitative data and qualitative data. Quantitative data are mathematical data. They express their values with numbers. The number of students enrolled each year in different departments of a university, the increase in the student quota, the number of graduates each year, the passing note in courses are all quantitative data.

Qualitative data expresses information more verbally. The data such as observation notes about the daily lives of the students in a department of a university, interviews with the graduates and recordings of the work experiences are considered as qualitative data. Although qualitative data are more verbal and narrative, they can also be analyzed by quantitative methods. Back to the same example, in interviews with a university’s graduates, the frequency of using the words ”leadership“ or “teamwork” can be analyzed by using quantitative methods.

**Data Analysis Methods**

The most accurate data analysis method is the best answer to your needs. To find the right method, you need to determine where and for what purpose you want to use this data. Let’s take a look at some of the preferred data analysis methods and areas of use in many different sectors.

**Time Series:** One of the most common **methods of data analysis** is the time series method. The time series identifies the variability of a variable within a given time. For example, the monthly distribution of a business’s profit rate is an example of a time series.

**Ranking**: One of the most common methods of data analysis is ranking. Here, the ratio of two different variables to each other is examined. For example, the sales amount of each salesperson in a store is analyzed by the ranking method.

**Part of the Whole: **We all remember math lessons. Slice graphs were one of the most fun problem types to solve. Pie charts help us understand the percentage of a data. For example, the costs of a restaurant can be reflected in the slice chart as we face. Different elements such as operating costs, food costs, taxes and rent can be shown as percentages.

**Deviation:** One of the most widely used data analysis methods is the distribution of frequencies generated by using bar graphs. The monthly click rate of a website can be analyzed by this method. The horizontal row shows time and the vertical row shows clicks. Bars can show the clicking per month. In addition, data from different social media platforms can be added next to the bars related to websites.

**Distribution Graph:** Sometimes it is possible to examine the relationship between the two events with a scatter graph. For example, let’s say we have created a graph to examine the relationship between inflation and unemployment. We can put the inflation into perpendicular orbit and the unemployment in horizontal orbit and explain the correlation between them.

**Geographical Distribution Graph**: In some fields, the distribution of data in a geographical area is necessary for the analysis of the data. The easiest way to achieve this is to create a cartogram. The cartogram shows us how a data is distributed to a particular geographic region. An example of this can be a company’s logistics operations on a map.

**Considerations in Data Analysis**

You have determined what you want to analyze the data for. If you choose the method you choose, there are some points to choose. Author Jonathan Koomey listed the points that data analysts should pay attention to as follows;

- Before starting the analysis, inspect the raw data in your hand to eliminate any abnormalities. Sometimes some abnormalities that occur during data recording, and these may cause the analysis method not to give the correct result. Data analysis prior to the actual analysis helps to prevent this situation.
- During this preliminary examination, check if there is a relationship that can be seen between the numbers. For example, the increase in the annual perpetuity of a percentage can usually be seen even before the analysis starts. In this case, you can compare the results of the analysis with this first assumption to have a safe result.
- Maintain important calculations. How many pieces will you divide the data you have? How many rows and columns do you need for this? Be sure to calculate these points correctly before starting the data analysis.
- Round the figures to facilitate analysis. This is an important point, especially for analyzes that are involved in fractured results. For example, in an analysis of the distribution of the national income rate over the years, it is useful to round the figures after the comma. Of course this situation should be stated at the end of the analysis.
- If any of your data gives you the sum of multiple data, make sure that it is a subtotal.

The methods of data analysis are directly related to the areas of use.