"n=40 \\\\\n\n\\bar{x}=146 \\\\\n\ns=12 \\\\\n\nH_0: \\mu=150 \\\\\n\nH_1: \\mu \u2260150"
When dealing with a large sample of size n >30 from a population which need not be normal but has finite variance, we can use the central limit theorem to justify using the test for normal populations. Even when "\\sigma^2" is unknown we can approximate its value with "s^2" in the computation of the test statistic.
Test-statistic:
"Z= \\frac{\\bar{x}- \\mu}{s \/ \\sqrt{n}} \\\\\n\nZ= \\frac{146-150}{12 \/ \\sqrt{40}}= -2.1 \\\\\n\n\u03b1=0.05"
Two-tailed test
"Z_{crit}=1.96"
The decision rule is: Reject H0 if Z ≤ -1.96 or if Z ≥ 1.96.
"Z= -2.1 < Z_{crit} = -1.96"
Reject H0.
There is enough evidence to conclude that the companies claim is NOT realistic at the 0.05 significance level.
Comments
Leave a comment