Results from surveys or opinion polls often report a range of valuesthe sample statistic plus or minus a margin of error (the resulting range is called a confidence interval). This tells us that the range is likely to contain the population parameter. How much wiggle room we provide is based on how much confidence we wish to have that the range contains the actual population mean. A confidence level represents the middle of the area of the distribution curve where we accept the Null Hypothesis (H_o). The tails portion () represents the area where we reject H_o. The bigger Confidence level is selected (CL) the smaller is = 1 - CL. For CL=95% = 5% (0.05), for CL=99% = 1% (0.01).

Give an example of research where 90% Confidence Interval is appropriate. Then post another example of statistics that requires 99% Confidence Level. Explain your choice.