These are the 5 main forms of Data Analysis
In this short article we are talking about the 5 different forms of data analysis. We’ll show how each of these increases in complexity and uncertainty. This isn’t to suggest that one form is better than the other rather that they each have a place in an analyst’s toolbox.
✔️ Descriptive: “what happened”
✔️ Inferential: “what about the rest”
✔️ Diagnostic: “what’s going on under the surface”
✔️ Predictive: “what is likely to happen next”
✔️ Prescriptive: “what should we do about it”
🔶𝐃𝐞𝐬𝐜𝐫𝐢𝐩𝐭𝐢𝐯𝐞 𝐀𝐧𝐚𝐥𝐲𝐬𝐢𝐬: This type of analysis is the most basic and common. From a technical point of view, it is the easiest to perform. There are a number of descriptive statistics that give us techniques to summarise a collection of data. (Ex. Counts, Min & Max, Sums, Ratios, Proportions and Percentages, Mean/Median/Mode, and Measures of dispersion (standard deviation & range))
🔶𝐈𝐧𝐟𝐞𝐫𝐞𝐧𝐭𝐢𝐚𝐥 𝐀𝐧𝐚𝐥𝐲𝐬𝐢𝐬: Like descriptive data analysis, inferential data analysis is concerned with what happened in the past. But unlike descriptive analysis, which involves data we have, inferential analysis also considers data we don’t have. This type of analysis comes into play when it’s impractical (due to excessive cost or length of time) to collect data on every single individual part of a population. Inferential analysis seeks to make statements about a population based on data collected from a sample.
🔶𝐃𝐢𝐚𝐠𝐧𝐨𝐬𝐭𝐢𝐜 𝐀𝐧𝐚𝐥𝐲𝐬𝐢𝐬: This type of analysis seeks to uncover patterns that lie beneath the surface , it attempts to answer the question “why is this happening?”
🔶𝐏𝐫𝐞𝐝𝐢𝐜𝐭𝐢𝐯𝐞 𝐀𝐧𝐚𝐥𝐲𝐬𝐢𝐬: This involves using historical data to make predictions about future outcomes
🔶𝐏𝐫𝐞𝐬𝐜𝐫𝐢𝐩𝐭𝐢𝐯𝐞 𝐀𝐧𝐚𝐥𝐲𝐬𝐢𝐬: This focuses our analysis on various courses of action we could take and potential outcomes that could occur. Prescriptive analysis seeks to answer the question “what should we do?”
These 5 types of analysis relate to one another. It is just like a patient visits a doctor’s office.
The doctor observes and measures the patient’s symptoms (this is like descriptive analysis) . The doctor then might need to make some inferences to other patients (inferential analysis.) The doctor probes further in an attempt to understand the cause of symptoms (diagnostic analysis.) The doctor makes some predictions on how the patient’s ailment will play out with and without an intervention (predictive analysis). Finally the doctor prescribes medication to improve the patient’s chance of recovery (prescriptive analysis.)