A machine produces parts of which 0.5% are defective. If a random sample of ten parts produced by this machine contains two or more defectives, the machine is shut down for repairs. - Find the probability that the machine will be shut down for repairs based on this sampling plan.
N = 10, p = 0.005, q = 1 p = 0.995 P(x>1) = P(2) + P(3) + + P(10) = 1 [P(0) + P(1)] = 0.0011 = 0.11 % P(0)= 1*0.0050*0.99510=0.9511 P(1)=10*0.0051*0.9959=0.0478
- How many random parts do you have to pick to expect, on average, one defective part? n= /p = 1/0.005 = 200
Slide 1 305-262B Statistics and Measurement 030213
Example: Number of heads when tossing three coins: n=3, p=0.5, and thus = np = 1.5 = sqrt(3x0.5x0.5)=0.87
Slide 2
030213
But from before we also know that the mean = xP(x) = 0 P(0) + 1 P(1) + 2 P(2) + 3 P(3) =
3 1 1 3 1 = 0 + 1 0 2 1 2 2
3 3 0 3 1
3 1 1 3 1 1 + 2 + 3 2 2 3 2 2 2
3
1 2
1 1 1 12 = 0 + 3 + 2 3 + 3 1 = = 1 .5 2 2 8 2
Slide 5
030213
Waiting Times
Waiting time T (in minutes) is a continuous random variable: Random cant be predicted with certainty Continuous can take on any value on the continuous time-scale from 0 to 10 minutes. In its decimal representation, a value of T is an infinite sequence of digits, e.g. - sequences starting with 0 (0.198) represent waiting times of less than one minute - sequences starting with 1 (1.934) represent waiting times between one and two minutes, etc.
Slide 6 305-262B Statistics and Measurement 030213
Waiting Times
Not knowing anything about the exact arrival times, we might feel that the ten one-minute intervals (0 to 1, 1 to 2, etc) are equally likely. Also, we might feel that the ten 0.1 minute intervals within any particular one-minute interval are equally likely, and so on. the digits in the sequence defining a T-value are independent random digits. Probability that T starts out with the three digits 3, 6, and 4 is P(T=3.64) = P(1. Digit = 3, 2. Digit = 6, 3. Digit = 4) = P(1. Digit = 3) * P(2. Digit = 6) * P(3. Digit = 4) = (0.1)*(0.1)*(0.1) = (0.1)3
Slide 7 305-262B Statistics and Measurement 030213
Waiting Times
What is the probability of any particular value of T (e.g. 3.64000 or 1/3)?
P (T = 1 / 3) = lim P (T has 3 in its first n places) = lim(0.1) n = 0
n n
What is the probability that the wait is at least two minutes but less than four minutes?
P(2 T < 4) = P(T starts with 2 or 3) = 0.1 + 0.1 = 0.2
What is the probability that the wait is between 1.42 and 3.61 minutes? 3.61 1.42 P(1.42 < T < 3.61) = 219 (0.1) 3 = 0.219 = 10
Slide 8 305-262B Statistics and Measurement 030213
Slide 9
030213
Properties of F(x), the c.d.f of a continuous random variable: 1. F(-) = 0 and F() = 1 2. F(a) < F(b) whenever a < b 3. F(x) is continuous for all x
Slide 10
030213
Verify that F(x) = + 1/ Atan x is a c.d.f ! 1. F(-) = + 1/ (-/2) = 0 F(+) = + 1/ (+/2) = 1 2. d/dx (Atan x) = 1/(1+x2) > 0 -> monotonically increasing, and thus F(a) < F(b) whenever a < b 3. F(x) is continuous for all x CHECK !
Slide 11
030213
P ( a < T < b) =
ba 10
0 Slide 12
t 030213
f ( x)dx = 1 f (u )du
b
F ( x) =
Slide 14
030213
= var X = ( x ) f ( x)dx = E ( X ) =
2 2 2 2
f ( x)dx 2
= var X
030213
Slide 17
030213
Percentile Ranks
One important use of the standard normal distribution is for converting between scores from a normal distribution and percentile ranks.
Areas under portions of the standard normal distribution are shown to the above. About .68 (.34 + .34) of the distribution is between -1 and 1 while about .96 of the distribution is between -2 and 2.
Slide 20 305-262B Statistics and Measurement 030213
This graph shows the distribution of scores on the test. The shaded area is 2.3% of the total area. The proportion of the area below 70 is equal to the proportion of the scores below 70.
Slide 21 305-262B Statistics and Measurement 030213
Slide 22
030213
Slide 24
030213
Slide 25
030213
Slide 26
030213
Slide 28
030213