In this blog I will explain step by step how to apply sample size formula on the specific problem. In order to determine how big your sample size should be for survey you need to understand how to apply the right formal in your calculation. In the business world having knowledge in this area will help you be more successful and can be crucial when conducting a survey.
I will use steps from The Marketing Research Toolbox: A Concise Guide for Beginners book to explain the process of calculating sample size in the practice problem from the book:
“To determine the effectiveness of an ad campaign for a new DVD player, management would like to know what percentage of the market has been made aware of the new product. The ad agency thinks this figure could be as high as 70 percent. In estimating the percent aware, management has specified a 95 percent confidence interval, and a precision of ±2 percent. What sample size is needed?”
In order to successfully calculate what sample size management should use to find out if customers are aware of new DVD player and effectiveness of their advertising campaign.
There are three steps we will go over which are mentioned in the book. First we need to square the Z value associated with the desired confidence interval. Second we need to multiply it by the population variance. Third we need to divide it by the square of the desired precision.
Now we will use following steps and apply them in our problem from the book. Management has decided they want confidence level of 95 percent looking at the page 30 says that in that case Z value is equal to 2. Next we need to find population variance and the formula for determining the variance is (Variance + proportion #1 x (1 – proportion #1)). In problem we are looking at variance is 0.70
Applying this formula calculation for variance equals 0.70 x (1 – 0.70) = 0.21. Now when we found all the number we need, we can calculate the sample size:
22 x 0.21 / (0.02) 2 = 2100
Based on our results our sample size should be 2100 people in order to achieve results management has set. I believe having confidence level of +- 2 in this particular problem and sampling 2100 people seems like a reasonable choice in order to find about what is awareness of costumers on new DVD player.