Data Analysis

#learning #codenewbie

Data Analysis is an important aspect of every sector. Organizing and thinking about data is important as one understands what the data does and doesn't contain. What exactly is data analysis? This entails scrutinizing raw data to draw some conclusions from the information retrieved.

Types of data analysis

Prescriptive Analysis
Diagnostic Analysis
Statistical Analysis
Predictive Analysis
Text Analysis

1. Prescriptive Analysis

This type of analysis combines the insight from all analyses done previously. This helps to determine which action to take in a current problem. This analysis is more efficient as data performance is improved and it helps to analyze current problems and make decisions.

2. Diagnostic Analysis

This analysis answers the question 'Why?'. This helps to find the cause from the insight found in Statistical Analysis. This analysis is useful for identifying behavior patterns. If a new problem arises, then one can have a look at this analysis to help find similar patterns of that problem.

3. Statistical Analysis

This type of analysis is done using past data in the form of dashboards and it answers "What happens?". The process includes collection, analysis, interpretation, presentation, and data modeling. A set or sample of data can be analyzed using this method. In statistical analysis, there are two main categories used i.e., descriptive and inferential. In descriptive analysis, a sample of or complete numerical data is summarized and used to calculate the mean and deviation for continuous data and frequency and percentages for categorical data. In inferential analysis, a sample from complete data is used and different summaries are made by selecting different samples.

4. Predictive Analysis

This type of analysis answers the question 'What will happen?'. This question is answered using previously collected data. Predictions of future outcomes are made using current or past data. For instance, current data indicates that the use of AI is high and is expected to increase over the years. Most people have found AI tools efficient and time-saving. This accuracy is measured and it depends on how much detailed the information collected is.

5. Text Analysis

This is also called data mining. This is mostly used to analyze a pattern in large datasets utilizing databases or data mining tools such as SQL. This analysis helps in transforming raw data into useful data i.e., business information.

Data Analysis Process
The process of analyzing data comprises data collection, data processing, data cleaning, data analysis and finally communicating the results. From the first process, data collection entails collecting information from all relevant sources to help in answering a problem and evaluating outcomes. Data cleaning is crucial in data analysis as it helps to identify and correct errors. This process is the detection of coding errors and correcting them. Two types of data cleaning processes are applied, code cleaning and contingency cleaning. These are very important and shouldn't be ignored as this might lead to the production of misleading data. Then, data analysis is done after data cleaning.

Data Analysis Tools

Data Analysis tools help in interpreting data for easy understanding. Different tools are used to analyze data, some of which require little coding such as R in data mining and Python, Tableau, and Power BI in data visualization.
R programming language is used for statistical computing and graphics supported by the R Foundation for Statistical Computing. This language is widely used by statisticians and data miners for software development and data analysis. This language helps in manipulating data and helps in presenting information in numerous ways.
Tableau offers free software that links information sources, which is then communicated with a customer or social media.
Python is a user-friendly and open-source language that can be read, written, and maintained. It was created by Guido Van Rossum in the 1980s and it supports both functional and structured techniques of programming. It contains several libraries for machine learning, such as Keras, Tensor Flow, Scikitlearn, etc. Besides, data visualization is possible using Seaborn, Box, and Scatter Plots.

Importance of data analytics for businesses

Positive impact on businesses has been noted as data analysis improves efficiency. This helps to evaluate employee performance.
A deeper understanding of the market is enabled. Huge datasets are collected and analyzed due to the development of algorithms today. Data collection is conducted in a raw form from a wide variety of people, which helps with feedback for the formation of better marketing strategies.
Data analytics helps in faster and better decision-making. Deadlines are met with ease as high-speed in-memory analytics save time.
Data analytics is powerful as new products/services are formed. With the data collected, it is easier to decipher the needs of consumers and this ensures the formation of new products/ services that align with the values of the target market.
Industry knowledge is enabled. Data analysis helps to predict the future trend of a certain industry as it shows the kind of present economy. Also, new opportunities for businesses are developed as brands are built.