Selecting the Right Data
When we’re analyzing data, it’s important to consider how we collect it. Here are some things to keep in mind:
How the data will be collected
- Decide if we’ll gather the data ourself or get it from someone else (and maybe buy it). When we collect the data ourself, it’s called first-party data.
Data sources
- If we’re not collecting the data ourself, we might get it from second-party or third-party data providers. Second-party data is collected by another group and then sold, while third-party data is sold by providers who didn’t collect it themselves.
Solving our business problem
- Make sure to choose data that can actually help answer our question or solve our problem. For example, if we’re looking at trends over time, use data that includes dates.
How much data to collect
- Decide on a reasonable sample size if we’re collecting our own data. Some projects may be fine with a random sample from existing data, while others might need more specific data to focus on certain criteria.
Time frame
- Think about how long we’ll need to collect data, especially if we’re tracking trends over a long period. If we need an answer quickly, we may have to use historical data that’s already available.
- Use the flowchart below to help with data collection, especially if time is a significant factor.
