Question

A random-digit-dialing survey sampled 1750 adults and found that 1140 used some form of prescription medication. Of these 1140 adults who used prescription drugs, 940 said they are concerned about the current state of health care; 320 of the 610 nonusers said this, too.

The margin of error in your 90% confidence interval is approximately

1. Could cancer cells be selectively targeted by using antibodies recognizing a tumor-specific protein marker? Researchers grafted human cancerous cells onto 20 healthy adult mice and then randomly assigned 10 of these mice to be treated with tumor-specific antibodies. They found that only 1 of the 10 mice treated with antibodies developed metastases, whereas all 10 of the 10 mice in the control group developed metastases.

   We want to compare the proportions of mice developing metastases under the two conditions. Here, a large-sample significance  test is    

   	A.	appropriate because a total of 20 mice is large enough for any inference.
   	B.	not appropriate because the respective counts of successes and failures are not large enough.
   	C.	appropriate because the study was randomized.
   	D.	not appropriate because the experiment is not double-blind.

1 points   

QUESTION 7

1. Refer to question number 6.

   A plus-four 90% confidence interval for p_control - p_treatment (the difference in the proportions that develop metastases) is

   	A.	0.53 to 0.97.
   	B.	0.74 to 1.05.
   	C.	0.49 to 1.01.
   	D.	0.17 to 0.92.

Answer 1

first sample size,     n1=   1140
number of successes, sample 1 =     x1=   940
proportion success of sample 1 , p̂1=   x1/n1=   0.825

      
second sample size,     n2 =    610
number of successes, sample 2 =     x2 =    320
proportion success of sample 1 , p̂ 2=   x2/n2 =    0.525

Std error , SE =    SQRT(p̂1 * (1 - p̂1)/n1 + p̂2 * (1-p̂2)/n2) =     0.0231  

α=0.05
Z critical value =   Z α/2 =    1.6449   [excel function: =normsinv(α/2)
          
margin of error , E =   Z*SE =    0.0381 (answer)

-----------------------------------------------------------------------------------------------------------------------------------------------------