You are on page 1of 5

# Chapter 6 A. Continuous Random Variable a. A random variable that results from measurement i.

It assumes any values contained in a line of interval 1. Not countable ii. Ex: 1. Height of a person 2. Time taken to complete an exam 3. Amount of milk in a gallon 4. Spinner 5. Number of cars sold (discrete r.v.) iii. All variables involving money are considered to be continuous r.v., even though money can be counted b. The Spinner i. Can take any value between 0 and 1 B. Probability Distribution of c.r.v. Height Frequency (f) Relative Frequency 60 X < 61 90 .018 61 X < 62 170 .034 62 X < 63 460 .092 63 X < 64 750 .150 64 X < 65 970 .194 65 X < 66 760 .152 66 X < 67 640 .128 67 X < 68 440 .088 68 X < 69 320 .064 69 X < 70 220 .044 70 X < 71 180 .036 n = 5000 Sum = 1.0 a. Histogram & Polygon i. Histogram = bars formed at points ii. Polygon = Line formed from points iii. P.D.F. or Density Curve 1. Smooth curve formed from polygon b. Goal i. To find the probability that falls into a certain interval in the continuous random variable 1. It is calculated by area under a probability distribution a. Probability = Area c. p.d.f. of c.r.v. i. The probability that the c.r.v. X assumes a value in any interval lies in the range 0 to 1 ii. The total probability under a density curve is equal to 1 1. Probability P(a x b) a. Shaded area is between 0 and 1 b. Area under the curve from point a to b 2. Fully shaded area is 1 or 100% 3. P(65 x 68) a. From 65 to 68 4. P(x = 67) = 0 (no area) 5. P(65 < x < 68) a. Between 65 and 68 6. P(a x b) = P(a < x < b) C. The Normal Distribution

a. Normal Probability Distribution Curve i. If a continuous random variable X is normally distributed or has a normal
distribution, then its curve is bell shaped and symmetric such that 1. The curve is symmetric about the mean 2. The total area under the curve is 1 3. The two tails of the curve extend indefinitely 4. f(x) = [ 1 / ( 2)]e (x- / ) a. f(x) = normal curve and - < x < b. = mean c. = standard deviation d. 3.14159 e. e 2.71828 5. mean locates center of distribution 6. St. deviation describes shape of distribution ii. Fully shaded area is 1 or 100% iii. Half shaded area is .5 or 50% iv. When mean is constant and st. deviation alters, the arc of the curve changes 1. If mean is constant a. Lower deviation with high arc b. Higher deviation with low arc v. When st. deviation is constant and mean alters, the position of the curve changes 1. If st. deviation is constant a. Negative mean means further left position b. Positive mean means further right position D. Standard Normal Probability Distribution a. A special case of the Normal distribution with a mean = 0 and a st. deviation = 1 i. f(z) = [ 1 / (2)]e (z / 2) a. f(z) = normal curve and - < z < b. = mean c. = standard deviation d. 3.1416 e. e 2.7183 ii. Standard curve has = 0 and = 1 iii. Fully shaded area is 1 or 100% iv. Half shaded area is .5 or 50% b. Z values or Z scores i. The units marked on the horizontal axis of the standard normal curve are denoted by z and are called Z values or Z scores 1. The area or probability under the standard normal curve can be obtained from Table 4 of the Appendix C c. Finding the Area or Probability under the curve i. Table 4 deals with P(Z z) for any value of z 1. Shaded area is equal to P(Z z) ii. Table 4 has limited values of z (-3.49 ~ +3.49) iii. Ex: 1. Find the area under the st. normal curve to the left of z = 1.95 a. That is to find the P(z 1.95) i. .9744 2. Find the area under the st. normal curve from z = -2.17 to z = 0 a. That is to find the P(-2.17 z 0) i. P(-2.17 z 0) = .5 - P(z < -2.17), since half of the area under the curve, P(z 0) is 0.5 b. .5 - .0150 = .4850

E.

Find the area, under the st. n.c., that z is greater than 2.32 a. That is to find the P(z > 2.32) i. P(z > 2.32) is same as the 1.0 - P(z 2.32) since the total area under the curve is 1.0 ii. P(z 2.32) = .9898 1. So 1 - .9898 = .0102 4. Find the probability P(1.19 < z < 2.12) where z has a st. n.d. a. P(1.19 < z < 2.12) = P(z < 2.12) - P(z 1.19) i. .9830 - .8830 = .1 5. Find the probability P(-1.56 < z < 2.31) where z has a st. n.d. a. P(-1.56 < z < 2.31) = P(z < 2.12) - P(z -1.56) i. .9896 - .0594 = .9302 6. Find the probability P(z > -.75) where z has a st. n.d. a. 1 - P(z -.75) = 1 - .2266 = .7734 7. Find the probability P(z < 5.67) where z has a st. n.d. a. P(z < 3.49) = .9998 is the largest possible i. Then P(z < 5.67) should be larger than .9998 b. Convention: i. We assume that P(z ) = 1 if is larger than or equal to 3.5 c. SO, P(z < 5.67) = 1 8. Find the value c such that P(-c z c) = .9500 where z has a st. n.d. a. Total unshaded area is 1 - .95 = .05 i. Each half is .05/2 = .025 b. P(-c < z < c) = .9500 i. P(z < -c) + P(-c z c)=.025 + .95 = P(z c)=.975 = P(z 1.96)=c=1.96 = P(-1.96 z 1.96) Standardizing a normal random variable (converting x value to a z value) a. In applications, a r.v. X may have a normal distribution with values of the and that are differ from 0 and 1, respectively. i. Converting allows us to compute the normal probability questions using table 4 b. Let the random variable X be normally distributed with mean and st. deviation, i. Z = x- / 1. Then, the r.v. Z is normally distributed with mean = 0 and st. deviation =1 c. If each value x of a normally distributed r.v. X is transformed into a standardized value z of Z, then it will become a standard normal i. Nonstandard normal distribution => Z = x- / => Standard normal distribution 1. The z value for the mean of a normal distribution is always zero 2. Do the rounding to 2 decimal places to use Table 4 d. Ex: i. Let x be a continuous random variable that is normally distributed with a mean = 50 and a st. deviation = 10. 1. Find the area to the left of x = 55 a. Z = x- / => z = 55-50 / 10 = .50 b. P(x < 55) = P(z < .50) = .6915 ii. Let x be a continuous random variable that is normally distributed with a mean = 25 and a st. deviation = 4. 1. Find the area between x = 25 and x = 32 a. Z = x- / => z = 25 - 25 / 4 = 0.00 b. Z = x- / => z = 32 - 25 / 4 = 1.75 c. P(25 < x < 32) = P(o < z < 1.75) = P(z < 1.75) P(z 0) = . 9599 - .5000 = .4599

3.

iii. Let x be a continuous random variable that is normally distributed with a mean = 25 and a st. deviation = 4. 1. Find the area between x = 18 and x = 34 a. Z = x- / => z = 18 - 25 / 4 = -1.75 b. Z = x- / => z = 34 - 25 / 4 = 2.25 c. P(18 < x < 34) = P(-1.75 < z < 2.25) = P(z < 2.25) P(z -1.75) = .9878 - .0401 = .9477 iv. Let x be a continuous random variable that has a normally distribution with a mean = 80 and a st. deviation = 12. 1. Find the area under the curve to the left of 27 a. Z = x- / => z = 27-80 / 12 = -4.42 b. P(x < 27) = P(z < -4.42) = 0 i. P(z < -4.42) = P(z > 4.42) due to symmetry ii. 1 - P(z 4.42) = 1 1 = 0 v. Supposes the prices of 3 year old 911s have a n.d. with a mean of \$48, 125 and a st. deviation of \$1600. 1. Find the probability that a randomly selected 911 will select for a price between \$46,000 and \$49,000 a. Z = x- / => z = 46000 48125 / 1600 = - 1.33 b. Z = x- / => z = 49000 48125 / 1600 = 0.55 c. P(46000 < x < 49000) = P(-1.33 < z < 0.55) = P(z < 0.55) P(z -1.33) = .7088 - .0918 = .6170 i. 61.70% vi. The life span of a TI calculator has a normal distribution with a mean of 54 months and a standard deviation of 8 months. The company guarantees that any calculator that starts malfunctioning within 36 months will be replaced with a new one. 1. What % of TI calculators are expected to be replaced? a. Z = x- / => z = 36-54 / 8 = -2.25 b. P(x < 36) = P(z < -2.25) = .0122 i. 1.22% F. Determining the z and x values when an area is given a. Ex: i. Find the value of z such that the area under the st. n.c. to the left of z is .9251 and the value of z is positive 1. P(Z < z) = .9251 2. P(Z 1.44) = .9251 ii. Find the value of z such that P(Z < c) = .0050 1. P(Z < c) = .0050 => P(Z c) = 1 - .0050 = .9950 2. P(Z 2.57) = .9949 and P(Z 2.58) = .9951 a. P(Z 2.58) = .9951 b. When value not in table and falls exactly in the middle of two numbers, pick the bigger absolute magnitude of two numbers c. C = 2.58 iii. Find the value of z such that P(Z k) = .0050 1. P(Z k) = .0050 = P(Z -1.65) G. Finding an x value for a normal distribution a. Assume that x has a normal curve with known values of mean and st. deviation. For a given area under the curve between the mean and the unknown x, the x value is obtained by i. X = + z* b. Procedure for finding an x value i. Draw a normal curve with the area corresponding to the given probability ii. Use table 4 to find the z value that corresponds to the shaded area iii. Obtain the x value using the equation above

c.

Ex:

## i. The life span of a TI calculator has a normal distribution with a mean of 54

months and a standard deviation of 8 months. What should the warranty period be to replace a malfunctioning calculator if the company does not want to replace more than 1% of all the calculators sold? 1. Let x be the warranty period a. P(x x) = .0100 i. P(z -2.32) = .0102 or P(z -2.33) = .0099 1. Choose closest value of two ii. P(z -2.33) = .0099 .0100 1. X = + z => x = 54 + (-2.33)(8) = 35.36 months ii. Kim plans to take SATs soon. All students who take this with Kim will have a normal distribution with mean = 1656 and st. deviation = 300. What should her score be so that only 10% of all examinees score higher than she does? 1. Find the 90th percentile of the SAT score a. P(X > x) = .10 i. P(X x) = 1 - .10 = .9000 1. P(Z 1.28) 2. X = + z => x = 1656 + 1.28 * 300 = 2040 < z < 3.1416 e 2.7183

HW 6.15, 6.17, 6.25, 6.29, 6.35, 6.37, 6.43, 6.49, 6.53, 6.57, 6.61, 6.62