Understanding the margin of error in simulations
Margin of error is the degree of error occurred in market research due to random sampling of surveys. A higher margin of error is associated with a greater deviation of the estimated value from the population value and consequently makes the results less reliable. Margin of error is important in market research because it demonstrates the confidence level which researchers should have in the data obtained from surveys (e.g. an margin of error equal to 5% indicates that the estimated value deviates ±5% from the population value)
Due to budget and time constraints, the standard level of confidence used in market research is 90%. The subsequent table exhibits the margin of error percentages for a certain survey sample size and an respective large population size (usually < 50,000):
| Survey Sample Size | Margin of error in percentage (Absolute) |
|---|---|
| 2,000 | 2 |
| 1,500 | 3 |
| 1,000 | 3 |
| 900 | 3 |
| 800 | 3 |
| 700 | 4 |
| 600 | 4 |
| 500 | 4 |
| 400 | 5 |
| 300 | 6 |
| 200 | 7 |
| 100 | 10 |
| 50 | 14 |
As shown by the table above, the margin of error decreases as the sample size increases. Therefore, the larger the sample size becomes, the smaller the percentage change in margin of error.
Viewing confidence intervals
The simulator can also display the confidence intervals of preference shares for each product concept. To check these intervals, right-click on the chart and click on .
