Basic Applied Statistics 200
Solutions to Midterm 1 Spring 2002

 (i) Method 1 because the values tend to be lower
 (ii) Method 2 because the stemplot has more spread
 (i) Method 1 looks perfectly symmetric
 (iv) neither has values far from the rest
 (ii) mean and standard deviation because it is symmetric
 13, 19 (3rd value), 24, 28 (8th value), 31
 (i) Method 1 (ranges from 11 to 27, not 13 to 31)

 0 is the mean of a standard normal distribution
 1 is the standard deviation of standard normal z
 .1003 are GREATER (.8997 would be less)
 practically no observations are this high
 .9772.8413=.1359
 look up .0404; the closest z is 1.75
 look up .9900 (because you want the HIGHEST 1%); the closest z is 2.33

 95% are within 2 s.d.s of the mean: 5.3 plus or minus 2(.2) goes
from 4.9 to 5.7
 z=(4.85.3)/.2=2.5; the proportion below is .0062
 no, not likely because the probability .0062 is so small
 for .25 below, z=.67, so x=5.3.67(.2)=5.166

 men who died (3160/2223) have the highest proportion
 332/706=.47
 332/1692=.20
 374/531=.704

 tip
 (i) increase (points slope up)
 (iii) rather strong (points are fairly tightly clustered)
 (v) +.83 because the relationship is fairly strong, but you
could take the square root of RSq=.686 to be sure
 (ii) same; r is independent of assignment of explanatory/response
 .35+.15(63.30)=9.19
 129.19=2.81
 (iii) it predicts 15% of the bill minus 35 cents (see regression
equation)
 (i) random scatter is a good thing in the residual plot
 (ii) decrease because it would make the clustering looser

 (iii) not enough replication; 5 each are small groups
 (i) no comparison is made
 (ii) no randomization; people chose what medication to take

 25 is the number actually examined
 observational study; the pediatrician does not manipulate any
variables, she only observes
[ Home
 Calendar
 Assignments
 Handouts
]
