In: Statistics and Probability
Suppose I estimate μ, the mean of a population. I obtain estimate 6.5 and 95% confidence interval (4.5, 8.5).
A) Can I reject H0 : μ = 8 using at two-sided test at the 1% significance level?
a) Yes. b) No. c) Not enough information to decide.
B) Can I reject H0 : μ = 8 using at two-sided test at the 10% significance level?
a) Yes. b) No. c) Not enough information to decide.
C) Can I reject H0 : μ = 9 using at two-sided test at the 1% significance level?
a) Yes. b) No. c) Not enough information to decide.
D) Can I reject H0 : μ = 9 using at two-sided test at the 10% significance level?
a) Yes. b) No. c) Not enough information to decide.
Suppose I estimate μ, the mean of a population. I obtain an estimate of 6.5 and a 95% confidence interval (4.5, 8.5).
Here we calculated a 95 % confidence interval.
If the null hypothesis value is included in the confidence interval then we do not reject the null hypothesis at a 5% level of significance.
at a 1% level of significance ( 99% confidence interval will be wider than the 95 % confidence interval), it also includes the null hypothesis value so we can say that do not reject the null hypothesis.
at a 10% level of significance ( 90% confidence interval will be narrower than the 95 % confidence interval), it may or may not includes the null hypothesis value so we cannot make any conclusion from the 90% confidence interval.
But
If the null hypothesis value is not included in the confidence interval then we reject the null hypothesis at a 5% level of significance.
at a 1% level of significance ( 99% confidence interval will be wider than the 95 % confidence interval), it may include the null hypothesis value or may not include the null hypothesis so we cannot make any conclusion at 1% l.o.s.
at a 10% level of significance ( 90% confidence interval will be narrower than the 95 % confidence interval), it also does not includes the null hypothesis value so we can reject the null hypothesis at 90% confidence interval.
Result Table
Confidence interval | a | Include the null hypothesis value | Does not include null hypothesis value |
95 | 0.05 | do not reject Ho | Reject Ho |
90 | 0.10 | No conclusion | Reject Ho |
99 | 0.01 | do not reject Ho | No conclusion |
95 % Confidence interval is ( 4.5, 8.5 )
A) Can I reject H0: μ = 8 using at two-sided test at the 1% significance level?
u = 8 is in the confidence interval.so we do not reject Ho at a 5% level of significance.
So also at a 1% level of significance, we do not reject Ho.
Answer:- No
B) Can I reject H0 : μ = 8 using at two-sided test at the 10% significance level?
u = 8 is in the confidence interval.so we do not reject Ho at a 5% level of significance.
So also at a 10% level of significance, we cannot conclude anything.
c) Not enough information to decide.
C) Can I reject H0 : μ = 9 using at two-sided test at the 1% significance level?
u = 9 is not in the confidence interval.so we reject Ho at a 5% level of significance.
So also at a 1% level of significance, we cannot make any inference.
c) Not enough information to decide.
D) Can I reject H0 : μ = 9 using at two-sided test at the 10% significance level?
u = 9 is not in the confidence interval.so we reject Ho at a 5% level of significance.
So also at a 10% level of significance, we reject Ho.
a) Yes.