When conducting surveys, one of the first steps is to determine your sample size. This is a technical term that refers to the number of respondents you need to statistically represent the population you are surveying.
In this post you will learn how to use Worthix's Survey Sample Size Calculator for CX surveying in a few simple steps, or if you enjoy hard work, find the correct way to calculate it by hand.
But first, let's address the importance of an appropriate sample size.
While conducting CX Surveys, in order for them to be statistically accurate, your sample size needs to be correct, especially if it is supposed to represent a larger population or data group.
For instance, let's say you decide to run a survey on the eating habits of females in California. You interview a total of 6 people, and 2 out of 6 say they are vegan. That means, according to your study, 1/3 of all females in California are vegan.
But let's say it has been pre-established that your population size is composed of 1,000 individuals and of those individuals, 20% is vegan.
Consider two sampling results:
This means the first study has an incorrectly high percentage, due to a poor sample representation, and as the sample size increases, we get closer to the true percentage.
Another thing you'll need to look out for is outliers. Outliers are abnormalities in the sample. They occur when a response deviates significantly from that which is established to be ‘standard’, or the average.
Determining Sample Sizes
Here are some of the items you must factor into determining sample sizes:
How to Use the Worthix Survey Sample Size Calculator
The Worthix Calculator was designed to be as easy as possible to use.
Simply insert the following numbers and percentages, based on the explanation above:
Click on 'calculate' and you've got your sample size.
The Math Behind the Science
When calculating survey sample sizes, you have two options. You can either calculate the sample size manually or use our Survey Sample Size Calculator. The calculator takes out all the brunt work, but if you really want to do it by hand, here's the math:
Start by establishing your Z-Score from your Confidence Level. Here’s a Z-Score cheat sheet, or just use this base:
Here’s what the formula looks like:
Parameters:
There's a video by Khan Academy on YouTube that does a great job walking you through the process.
The next step after securing your survey sample size is choosing a methodology for designing your questionnaire. Or, if you appreciate cutting-edge tech innovations, try a self-adapting, pre-programmed questionnaire.