What Is Data Analysis?

Data analysis is everywhere in the world. Governments are using data analysis to monitor the spread of the COVID-19 pandemic. Streaming sites leverage data to recommend new movies for you to watch. Shopping sites use data analysis to identify trends in what you purchase so that they can recommend other items you may want to buy.

But you may be wondering to yourself, what is data analysis, exactly? What are people doing when they say that they are analyzing data? Those are the questions we’re going to answer in this article, starting with the basics of what data analysis is.

What Is Data Analysis?

Data analysis is the process of finding insights from a dataset. Data analysts prepare a dataset for analysis, look at the dataset to identify patterns and trends, and come to conclusions based on what they find. Similarly, data analysts may look for data that supports or discredits a theory that they already have about a dataset.

Get offers and scholarships from top coding schools illustration

Find Your Bootcamp Match

  • Career Karma matches you with top tech bootcamps
  • Access exclusive scholarships and prep courses

By continuing you agree to our Terms of Service and Privacy Policy, and you consent to receive offers and opportunities from Career Karma by telephone, text message, and email.

 Data analysis is used in many sectors, including:

  • Healthcare
  • Government (local, state, federal, and international)
  • Social networks
  • Streaming sites
  • e-commerce websites

Data Analysis Techniques

Data analysis is an umbrella term to describe a number of different processes. These are:

  • Collection
  • Cleaning/processing
  • Analysis
  • Drawing conclusions
  • Presenting data

Data collection involves deciding what data you want to gather for a particular problem. A data analyst will ask: what do I need to answer the question at hand? This also involves deciding what data not to collect, and why. Data analysts must stay focused on the data that will help them reach a conclusion about a question or hypothesis. Once a decision has been made about what information to collect, that data must be gathered.

Next, a data analyst will clean the data. This involves removing any values which are formatted incorrectly or do not help the data analyst. For instance, a data analyst may exclude the results of certain questions in a survey if they are not useful. The data analyst will also remove any blank records, if appropriate.

The actual analysis process comes when the data has been correctly gathered and cleaned. A data analyst will look at a dataset and attempt to identify trends. This may involve using a programming language to find correlations. Data analysts often apply statistical techniques using a programming language to help them draw a conclusion about data.

Drawing conclusions comes next. A data analyst must ask: what does this data tell me? Once a trend has been identified, a data analyst must consider that trend in context and ask themselves whether the trend was expected or not, and what it means. Only after conclusions have been drawn can data be put into charts or a report to present to others.

Data Analysis Methods

Data analysts use a range of methods to analyze data. We shall focus on the four main ways of analyzing data: descriptive, prescriptive, predictive, and diagnostic.

Descriptive Data Analysis

Descriptive data analysis involves analyzing a dataset and reflecting on what has happened. No correlations are identified. Instead, an analyst will look for high-level insights into a particular problem. For instance, a social network may use descriptive analysis to find out how many people have viewed a particular user’s profile.

Prescriptive Data Analysis

Prescriptive analysis looks into the future based on data that has already been gathered. The data analyst must ask: from what I have seen, what would be the best next step to take? This type of data analysis usually plots out different future scenarios, helping a business see what might happen and when based on data it has collected.

Predictive Data Analysis

Predictive analysis aims to predict what might happen in the future. These analyses are based on the data that has been collected so they are not always accurate. Rather, they aim to help someone understand what might happen in the future based on trends that have been identified.

Consider a movie streaming site. The site may run a prescriptive analysis to see how viewership would increase if it started recording and releasing new comedy shows versus new thriller shows. The site would use data on comedy and thriller viewership changes as new content is released to determine the impact on viewership for each category should new content be released.

Diagnostic Data Analysis

Imagine if viewership on all movies dropped by 5% in one month. A data analyst would run a diagnostic data analysis to find out what has happened. Perhaps the analyst finds that the site was running significantly slower because it was overwhelmed by new users. From this analysis, the business could infer that improving its infrastructure is a good investment.

Diagnostic data analysis looks at a previous dataset to determine the cause of an issue—or a positive event—so the business knows what to do and what not to do to achieve a particular effect (e.g. an increase in customers or sales).

Data Analysis Examples

Data analysis is commonly used in corporate settings to inform decisions. For instance, say a soap manufacturer is trying to decide what ingredients it needs to buy.

The manufacturer could use its purchasing logs to identify which products are most popular and how many it has sold in the past. From this data, the company could make an informed decision about what ingredients it needs to buy without risking buying too much or too little.

Governments use data analysis to identify trends in different datasets. For instance, the U.S Bureau of Labor Statistics (BLS) has charts that show employment changes in particular industries. Without data analysis, this data would be just numbers, without any useful insight.

But data analysis is not just a skill used by businesses. You can use data science to learn more about the world, too. There are plenty of datasets available online that you can analyze to learn about topics you find interesting. For instance, you can use data on the BLS website to find out more about employment trends and unveil insights that are not readily available on pre-made charts.

Other examples of data analysis include:

  • Using a dataset on crime to identify which months have higher crime rates.
  • Using a dataset on the temperature in a city to see how it has changed over a period of twenty years.
  • Analyzing a dataset of customer survey responses to learn more about what customers like and dislike about a product.
  • Using data from a product to determine whether a feature is widely used or not.

A Summary of Data Analysis

Data analysis comes up in many scenarios where technology is involved. Using data analysis, businesses can make smarter decisions, governments can make sense of the data they collect, and individuals can learn more from raw data that other people have collected (or that they themselves have collected).

In the modern world, data analysis is a valuable skill. If you want to pursue a career in technology, a basic understanding of data analysis is incredibly useful. However, data analysis skills are not confined to technology jobs. A marketer may have a dashboard set up to evaluate data, for instance, although their approach may not be as technical as that of a programmer’s. Whatever the case, learning data skills will always come in handy!

Find the best data science bootcamps to get you hired.


Get matched to top data science bootcamps

By continuing you indicate that you have read and agree to Study Data Science Privacy Policy

Powered By
Career Karma



You don't have permission to register