It is a range of values where any sample value are likely to fall into with certain probability. It is calculated based on some sample from the entire population. For example, we want to figure out the average height of women in the U.S.. Assume someone tell you that the 95% confidence interval is (5’2, 5’7), that means if we randomly pick one woman from the crowd, there is 95% chance that the height of this women is between 5’2 and 5’7. Or in other words, if we randomly pick 100 woman from the crowd, we are confident that the height of at least 95 of them are between 5’2 and 5’7.

When we want to generalize a statement for a big population, it's impossible to get the data from all the members. So we take a sample of the population and use the calculated sample parameter as a proxy for the population parameter.

When we want to generalize a statement for a big population, it's impossible to get the data from all the members. So we take a sample of the population and use the use sample statistic to estimate the population parameter. But different samples have different sample statistics. Which one is a good approximate for the population parameter? So we should come up with an interval to confidently say that the population parameter lies in it. This interval is called Confidence Interval.