Welcome to The Explorer

The Premier Online Knowledge Base for Information and
Statistics About Social Good

Browse The Explorer

Six Types of Analytics


Six Types of Analytics

Social good sector organizations are increasingly turning to analytics to improve decision making. In the frenzy of your day-to-day work, you may rely on systems like a constituent records management (CRM) software to run queries for you and analyze critical metrics. Different types of analytics can help you derive meaning from the volumes of data you process each day. Read on to learn more about the six types of analytics social good organizations can rely on to improve their efforts.

Source: Target Analytics, Six Types of Analytics

top

Data

Data includes any information, quantities, facts, and statistics that you collect throughout your day-to-day work. By having this information, you can answer questions like “Did it happen?” While data is the foundation for more complex statistical analysis, like statistical modeling, it comes in different forms and requires some measure of application before being used to its full effect. For example, raw data is the data that has not been changed since being acquired. By contrast, clean data is raw data that has been modified in order to be analyzed. Raw data often contains errors, such as typos and outliers, that prevent proper analysis, and modifying data can help mitigate this. Clean data often increases the reliability with which you run queries and benchmark your performance.


top

Descriptive

Descriptive analytics give you insight into past events. They are used to answer questions like “What happened?” They often involve an examination of your raw data to describe an event that has occurred. By looking into what happened, you can learn from past outcomes and understand how they could affect the future. Much of the data you possess may be descriptive; examples of this data type include wealth screenings, a donor’s giving history, consumer demographics, or even social media profiles. Descriptive data is often used to develop a donor profile or segment individuals by shared traits. By digging into your data, you can use descriptive analytics to pull reports or run queries about your fundraising metrics.

top

Diagnostic

Diagnostic analytics allow you to answer questions like “Why did it happen?” Similar to a root term, this is a “diagnosis” of your descriptive analytics that allows you to pinpoint information and understand why something occurred. At this point, you are scanning for patterns in your data to get at the root cause underlying an occurrence. You are uncovering connections that you might not have previously seen to prepare yourself to move forward.

top

Predictive

Predictive analytics allow you to answer questions like “What’s likely to happen?” These analytics help you understand the likelihood of a future outcome. While no figure can predict anything with a 100% degree of certainty, predictive analytics allow you to forecast just how likely it is that something will occur. When applied, predictive data can help you see the answers to questions like “Who will respond to my appeal?” or “Who will give a major gift?”

Many organizations use predictive modeling, which is rooted in statistical analysis, in fundraising to target their best prospects and prioritize them ahead of others to strengthen a fundraising strategy. This is often an effective tool to jumpstart a new fundraising campaign or strengthen existing programs.


top

Prescriptive

Prescriptive analytics allow you to answer questions like “What should we do next?” By simulating a situation, prescriptive analytics are used to advise you on possible outcomes and help you form a strategy moving forward. This type of analytics moves past predictive and descriptive analytics by counseling you on a course of action. For example, through your prescriptive analysis, you’ll be able to optimize tasks like assigning a major gift officer to a certain prospect, knowing when to contact an individual within their solicitation process, or targeting direct mail at a specific segment of donors. The insights gleaned allow you to take a very specific action while knowing that it is statistically likely to be the best approach.

top

Proactive

Proactive analytics combine the insights you’ve gleaned from your predictive models and prescriptive analysis in order to answer questions like “What can you do for me?” By being proactive about the insights you’ve gained, you can act based on knowing what might happen in the future. This is an intuitive step in analytics. After all, you engage in proactive analytics daily by filling up your tank before driving on empty. This same methodology applies to your organization, allowing you to be proactive about an outcome you are aware of.


top