Data sampling is a standard statistics technique used to select, process, and analyze a representative subset of a population. It is also used to identify patterns and extrapolate trends. Sampling is used, for instance, for political or opinion polls. If a researcher wants to determine the most popular way of commuting to work in the US, they won’t need to talk to every American citizen. Instead, they can select a representative group of 1,000 people, hoping it will be enough to make the results accurate.

In web analytics, sampling works similarly. Only a subset of your traffic is selected and analyzed, and that sample is used to estimate the overall results.

Sampling in analytics has its advantages and applies in certain situations. However, using it automatically without knowing the consequences of working on a sample may cause problems. These include report inaccuracy.

Read more:

What is data sampling and how does it work?

Raw data and sampled data: How to ensure accurate data

Compare 7 free web analytics platforms (product analytics included)


  • Duga Digital - success story - blog

    How Oxford Online Pharmacy increased data volume by 15% with Duga Digital and server-side Piwik PRO Analytics

    Duga Digital’s success story appears as part of our Partner Spotlight series. Oxford Online Pharmacy (OOP) is a family business going back three generations to 1925. Employing experienced pharmacists and healthcare professionals, OOP is committed to translating the values and heritage of the Oxfordshire-based bricks and mortar chemists, online.

    Read more

  • What is PII, non-PII, and personal data? [UPDATED]

    Personally identifiable information (PII) and personal data are two classifications of data that often confuse organizations that collect, store and analyze such data. Both terms cover common ground, classifying information that could reveal an individual’s identity directly or indirectly. PII is used in the US, but no specific legal document defines it. The legal system…

    Read more