Hi Bailey,
No population standard deviation is given, so we have to use a t confidence interval:
CI=x-bar +/- t*SE
Let's break this down:
x-bar=sample mean
t*=t critical value, obtained from t table
SE=standard error, which is computed as:
SE=s/sqrt(n)
s=sample standard deviation
n=sample size
Let's compute our standard error right now:
s=6
n=21
SE=6/sqrt(21)
SE=1.31
Now, we also must find t*. To do this, we first need our degrees of freedom, computed as:
df=n-1
n=21
df=21-1
df=20
Now, go to the t-table, search for 80% confidence in column, 20 degrees of freedom in row:
t*=1.325
Returning to our initial equation:
CI=x-bar +/- t*SE
x-bar=37
t*=1.325
SE=1.31
CI=37 +/- (1.325*1.31)
CI=37 +/- 1.74
CI=(35.26, 38.74)
I hope this helps.