Confidence interval
Also called confidence level, CI
The range your result is consistent with, and the confidence level is how often that kind of range would contain the truth.
For a symmetric interval, add and subtract the margin of error from the estimate: 62% ±5 gives 57% to 67%. The confidence level, often 90%, 95% or 99%, describes how often intervals produced by the method would contain the population value across repeated samples.
Raising the confidence level widens the interval. At the same sample size, 99% confidence buys certainty about the procedure by giving up precision about the number. Most published survey work uses 95% because it is the convention, not because it is optimal; what matters is that you say which one you used.
Report the interval alongside the estimate so readers can see its sampling uncertainty.
Where it goes wrong
Choosing the confidence level after seeing the data. Picking 90% because the result then looks conclusive is the same mistake as running the test again until it passes.