A bond analyst is analyzing the interest rates for equivalent municipal bonds issued by two different states.
a) At α = 0.05, is there enough evidence to conclude that there is a difference in the interest rates paid by the two states?
State A:
Sample size 60
Mean interest rate (%) 3.2
Population variance .02
State B:
Sample size 60
Mean interest rate (%) 3.4
Population variance .05

Respuesta :

Answer:

[tex]z=\frac{(3.2-3.4)-0}{\sqrt{\frac{0.141^2}{60}+\frac{0.224^2}{60}}}}=-5.85[/tex]  

The p value can be calculated with this probability:

[tex]p_v =2*P(z<-5.85)=4.91x10^{-9}[/tex]  

The p value for this case is a value very low and near to 0 so then we have enough evidence to reject the null hypothesis and we can conclude that the true means for this case are significantly different

Step-by-step explanation:

Information provided

[tex]\bar X_{1}=3.2[/tex] represent the mean for sample A

[tex]\bar X_{2}=3.4[/tex] represent the mean for sample B  

[tex]\sigma_{1}=\sqrt{0.02}= 0.141[/tex] represent the sample standard deviation for A

[tex]s_{2}=\sqrt{0.05}= 0.224[/tex] represent the sample standard deviation for B

[tex]n_{1}=60[/tex] sample size for the group A

[tex]n_{2}=60[/tex] sample size for the group B  

[tex]\alpha=0.05[/tex] Significance level provided

z would represent the statistic

Hypothesis to test

We want to verify if that there is a difference in the interest rates paid by the two states, the system of hypothesis would be:  

Null hypothesis:[tex]\mu_{1}-\mu_{2}=0[/tex]  

Alternative hypothesis:[tex]\mu_{1} - \mu_{2}\neq 0[/tex]  

The statistic for this case since we know the population deviations is given by:

[tex]z=\frac{(\bar X_{1}-\bar X_{2})-\Delta}{\sqrt{\frac{\sigma^2_{1}}{n_{1}}+\frac{\sigma^2_{2}}{n_{2}}}}[/tex] (1)  

Replacing the info given we got:

[tex]z=\frac{(3.2-3.4)-0}{\sqrt{\frac{0.141^2}{60}+\frac{0.224^2}{60}}}}=-5.85[/tex]  

The p value can be calculated with this probability:

[tex]p_v =2*P(z<-5.85)=4.91x10^{-9}[/tex]  

The p value for this case is a value very low and near to 0 so then we have enough evidence to reject the null hypothesis and we can conclude that the true means for this case are significantly different