Interval Estimate
Interval Estimate
The confidence level of an interval estimate of a parameter is the probability that the interval
estimate contains the parameter. It describes what percentage of intervals from many different
samples contain the unknown population parameter.
The critical values, also known as confidence coefficients, are the z-values that is used in
describing the characteristics of a target population. When σ is known, z-values are used. Note
that these values are constant at those given confidence levels.
The margin of error is the maximum difference between the observed sample mean and the true
value of the population mean. It is expressed as:
E=z σ
2
( )
σ
√n
Note that we only use this formula for the margin of error if we know the value ofσ .
X −E< μ< X+ E
Example:
1. A random sample of 50 students was asked about how much their allowance is every
day. The average allowance of the sample is found to be P400 and the population
standard deviation is P150. Find the interval estimate of the population mean a using
95% confidence level.
Solution:
E=z σ
2
( √σn )
¿ 1.96
( )
150
√ 50
¿ 41.578
X −E=400−41.578
¿ 358.422
X + E=400+41.578
¿ 441.578
So, putting this concept in the context of the word problem, we are saying that we are 95% sure
that the average
Allowance of the students is between P358.42 and P441.48. We rounded it off in two decimal
places since the problem deals with money.
Reminder:
Having 99% confidence level is not necessarily better than having a 95% confidence level. In
99% confidence level, we are 99% sure that the population mean is in that interval, but the
tendency is that we will have a longer interval compared to a 95% confidence level. If we have a
longer interval, it is harder to estimate the actual population mean since we are dealing with
more numbers. In 95% confidence level, we are only 95% sure, but the interval is much shorter
and more precise.
Main point:
The interval estimate tells us a range of values where the population mean may be located. At
95% confidence level, we are 95% sure that the population is inside that interval estimate. The
same thing can be said for 90% confidence level and 99% confidence level.
At 99% confidence level, we become more certain but we are increasing the length of the
interval. At 95% confidence level, we become less sure but the interval becomes more precise
because we shorten the interval.