stats-hypothesis testing

[Dia]

1)an analyst using a simple random sample obtaines a 99% confidence interval for mean monthly income y with the results: Rs 3200 =<mean of y<= Rs 10000. if he had used 90% confidence instead then the interval would be:

a. shorter and would involve a larger risk of being an incorrect interval estimate  
b.  longer and would involve a smaller risk of being an incorrect interval estimate  
c.  shorter and would involve a smaller risk of being an incorrect interval estimate  
d.  longer and would involve a larger risk of being an incorrect interval estimate  
 
is it a?

2) the alternative hypothesis is that a process is producing more than the maximum allowable proportion of defective items. a type I error would be to conclude tht the process is

a. producing too many defects when it actually isnt
b. not producing too many defects when it is not
c. producing too many defects when it actually is
d. not producing too many defects when it actually is

hey i was thinking a for this as well
                                   
thanks in advance.

[neha]

question1:
as the level of significance increases, the width of the interval decreases along with the higher probability of error, so i too think it should be (a)

question2:
here the null hypothesis will take the form p<or=  maximum allowable proportion of defective items, a type I error which is the probability of rejecting the null hypothesis when it is actually true should be  producing too many defects when it actually isnt , as we are rejecting the null hypothesis when its true. so it should be (a).