Answers

What is data cleansing?

____________________

You can think of data cleansing (or data scrubbing) as the "quality control" phase of research data analysis. Before you can analyse quantitative data, you must identify and fix errors in the dataset.

This involves removing duplicate entries, correcting typos (like "220" instead of "22"), and handling missing information.

In real-life terms, it is like sorting through a bag of fruit before baking a pie; you need to toss out the bruised bits and remove the stems, so they do not ruin the final product.

Why is data cleansing necessary in quantitative studies?

In research, the results or findings or conclusions are only as good as the data that produced them.

This is often called "Garbage In, Garbage Out." Cleansing is vital because it ensures accuracy, reliability, and credibility.

One extreme outlier (like a participant accidentally entering their birth year as "2026") can completely skew or alter your average (mean) and lead to false conclusions.

Clean data ensures that if someone else repeats a study, they would get the same results.

Using "messy" data can make statistical tests invalid, produce false findings, and lead to claims that are misleading and not credible.

Cleansed data produce valid conclusions.

For a more detailed exploration of data cleaning (especially in the context of Health Analytics), watch our short videos: