Voxco logo white

Understanding sample size:
How to ensure your survey delivers better results

Market research 04 12
See what question types are possible with a sample survey!

01

What is sample size?

Sample size is the amount of responses that have been completed by respondents to your survey. It is termed as a sample as it is a representative ‘sample’ of your target audience. Respondents can be chosen at random, or selected after careful consideration (factors that determine this can include: race, gender, income, education level, etc.)

Sample sizes are required because it is not possible to survey each and every person in your target demographic. Which is why you need to select a sample that represents that demographic as closely as possible. However the issue with determining sample size is – how big of a sample do you need?

Understanding sample size: How to ensure your survey delivers better results cx personalization

Get started with Voxco’s Market Research Toolkit.

Market Research trends guide + Online Surveys guide + Agile MArket Research Guide + 5 Market Research Templates 

Download Marketing Toolkit

02

How do you determine the right sample size?

If your sample size is too large, the complexity of your research increases considerably which in turn makes it more expensive. It is hard to justify the additional expense. 

On the other hand, if your sample size is too small, then your research can be influenced by outliers and anomalies and you don’t get an accurate view of your target audience. Which is why you need to keep a few factors in mind while determining sample size. 

If you already have the key details on hand, then you can use our sample size calculator to figure what sample size you should be targeting.

If you’re starting from scratch, the following tips should come in handy:

Consider the right variables

Factor in population size 

This is an estimate of the total number of people you are trying to understand. For example, if you were to take a random sample of people across a country, then that country’s total population is your population size.

Confidence level in sampling

This is a percentage which represents how confident you are that the population would select an answer within a predefined range. A 97% confidence level implies that you are 97% sure that results will be between x and y numbers (these are parameters decided by you).

Margin of error

This is also a percentage, and it represents how much one can expect the results of your survey to represent the views of the local population. The lower the margin of error, the more accurate your survey will be.

Calculating your sample size

Determine your z-score

Your confidence level needs to be represented by a z-score. There are common z-scores for commonly used percentages which is as follows:

90% – Z Score = 1.645

95% – Z Score = 1.96

99% – Z Score = 2.576

If your confidence level happens to be different, there are multiple tools available on the internet which can help you calculate your z-score.

Use the formula for sample size

You can use the following formula to manually calculate your sample size:

Understanding sample size: How to ensure your survey delivers better results cx personalization

This formula can be used if your population size is very large or unknown. 

[Free Webinar Recording]

Want to know how to increase your survey response rates?

Learn how to meet respondents where they are, drive survey completion while offering a seamless experience, Every Time!

03

What to keep an eye out for when calculating sample size

A few things researchers need to keep in mind while figuring out their sample:

  • If you wish to increase the sampling confidence level, you’ll need to increase your sample size
  • To achieve a lower margin of error, your sample size must increase as well.

Read more

External Validity

External Validity

External Validity Transform your insight generation process Use our in-depth online survey guide to create an actionable feedback collection survey process. Download Now SHARE THE

Read More »

Hindol Basu 
GM, Voxco Intelligence

Webinar

How to Derive the ROI of a Customer Churn Model

30th November
11:00 AM ET