Each of us now leaves a trail of digital exhaust, an infinite stream of phone records, texts, browser histories, GPS data & other information that will live on forever. Every animate & inanimate object on earth will soon be generating data including our homes, our cars and yes even our bodies.
Importance of Data:
• An average person today processes more data in a single day that a person did in his lifetime in the 1500s.
• 571 websites are being created every minute of the day.
• The world’s data is doubling every 2 years.
If you can’t believe the data, how can you believe analytics? Data never sleeps.
Data is the basis for any kind of an analysis, so data is an essential part of quality analysis. Then again data alone cannot support better conclusion. To aid in better and enriched data representation data needs to be sorted and then analyzed. It’s for this reason you need to learn everything from data collection to data representation.
A lot has been said about data. Let’s first understand what is data?
Data is any fact or statistics which is collected together for future reference or analysis.
Let’s use examples to understand data and its usage in our real life:
1) In all major departmental /retail stores, most of the people avail loyalty card facility. Have you ever wondered why loyalty cards are provided to you? You shop, earn points and redeem them to get discounts. But there is a broader aspect to it. Whatever you are purchasing you are being mapped, tracked. Your purchase behavior and patterns are being recorded. Suppose you shop mostly on weekends, the backend data analyzer might customize exclusive offers for you on weekends so that you shop more, keep visiting the store again and again and do more repeat purchase! If you mostly purchase formal shirt with formal pants of the same brand and suddenly you switch to some other brands, you might be provided with different offers to get back to the previous brand or may be asked for your feedback. Whatever it may be, the idea behind it is to identifying the changing patterns. The logic behind these loyalty cards is pretty simple, to get all the details. The details that are punched, is data for the backend. From these data you can analyze your customer. This is where an analyst comes to the scene. To help the business grow, an analyst, analyses the data, reads them thoroughly, examines, executes and represents the data in a way which is systematic, meaningful and useful for any business to flourish. It helps in providing important insights about the business.
2) Have you ever realized that you are being tracked over the internet, yes the World Wide Web. For example, if you went to an e-commerce site to look for a particular phone model & ended up not buying it. You must have noticed the same mobile ads following you throughout the web even when you scour out different sites.
There are millions of zeta bytes of data waiting to be analyzed on a daily basis which is practically impossible to do it manually. It is thus why data analyzing tools are used.
Data Analyzing is a huge task and data are of different types, so different data types needs different treatments and for each of them specific data analyzing tools are used.
Types of Data Variables:
Data Variable type checking helps prevent errors and enhances reliability. Furthermore, data variables determine what operations are allowed on it because an operation allowed on one type might not be allowed on another. Now let’s have a look at the different types of data variables.
Arises from counting
Can take only a set of particular values including negative and fractional values
Example: Credit score, number of credit cards owned by a person, number of states in a country, charge on electron etc.
|• Binary (or Dichotomous)
Has only two categories
Example: yes/no, male/female, pass/fail etc.
Arises from measuring
Within a specified range, It can take any value
Example: Height, Amount of money, Age etc.
Has several unordered category
Examples: Type of bank account
Has several ordered category
Examples: questionnaire responses such as "strongly Like / … / strongly dislike".
Now that you have collected raw data and you have results from multiple trials of your experiment. How do you go from piles of raw data to summaries that can help you analyze your data and support your conclusions? Fortunately, there are mathematical summaries of your data that can convey a lot of information with just a few numbers. These summaries are called descriptive statistics. A good analyst is someone who can perform these tasks with complete perfection but Data Collection and Management Frameworkis equally important, which includes:
• Data collection mechanism
• Maintaining a data dictionary
• Missing value imputation
• Outlier treatment
Data being the foundation for all analysis, so it forms a major and vital step in data analysis. It is basically an elaborate process and has a lot of detailing and precision to it. EduPristine has a vast coverage of these topics, to learn more about it, write an email to us at firstname.lastname@example.org