Upload
lokuliyanan
View
239
Download
0
Embed Size (px)
Citation preview
Area Bounded by Curves
Note:- area bounded with y axis
A
x
Eg:-Find the area bounded by the x axis and the Curve
Area between two Curves
The area bounded by the curves
Eg:-Find the area bounded by and
Eg:-Find the area of the region of the xy plane defind by the inequalities
Ex:-(1)Find the area of the region of the xy plane bounded by the curve
(2)Find the area of the region of the x-y plane define by the following inequalities.
Volume of revolution
Curve is rotated one revolution aboutx-axis formed solids volume will be given.
Note:-
If the curve is rotated about y-axis.
Eg:-(1) is a curve given A portion bounded by y=1, y=2 x axis and curve is
rotate 3600 about x axis. Find the volume formed,
(2)The curve defined by the inequalities is rotated completely about the y axis. Find the volume generated.
(3)The area enclosed by the curve and the line y=3 is rotated about the line y=3. Find the volume of the solid generated?
Ex:-(1) the region defined by there inequalities is rotated completely
about x axis. Find the volume generated?
(2) the area bounded by these curves rotated completely about y axis.
Find the volume generated?
(3)Find the volume generated, when the area bounded between is
rorated about .
A Difinite Integral is,
If we cannot evaluate difinite integral with an antiderivative, we use numerical methods like the trapezoidal rule and Simpsons rule. These rules enable us to estimate an integrals value to as decimal places.
The trapezoidal rule approximates streches of curves with the line of segments.
We add this area of the trapezoids made by joining the ends of these segments to x-axis
gives, estimated area.
In this case, the estimate area in grater than the original. This is called over estimate.
Over estimate area = estimated area -
In this type of curves give the estimate area less than the original area. When we consider trapezoids, we lose small area in every trapezoids. This type is called Under estimate.
Under estimate area
formula for the trapezoid rule
n trapezoids are considered,
sub interval length
Eg:-Use the trapezian rule with five ordinates to evaluate ordinates y values
Eg:-Use the trapezian rule with five ordinates to evaluate ordinates y values
x00.160.320.480.64
y11.04081.17351.43331.8965
y0 y1 y2 y3 y4 (5 Ordinates)
Simpsons Rule
eg:-Use simpson role with five ordinates (4 ships) to find an approxomate value
x0
y00.840910.84090
y0 y1 y2 y3 y4 (5 Ordinates)
(2)Estimate to 4 decimal place using five ordinates and applying
(a)The trapezium rule
(b)Simpson rule
Using the subtitution or other wise evaluate and hence
determine the accuracy of your estimated volume.
(Take )x01
y10.94120.8 0.640.5
y0 y1 y2 y3 y4 (5 Ordinates)
using trapezium rule
Using Sinpson rule
accuracy method
Conclusion
The trapezium rule gave an estimate correct to 2 decimal place and
Simpson rule gave an estimate correct to 4 decimal place.
\
TRIGONOMETRY
Trigonometric Ratios
Using Pythagoras thmAB2+BC2=AC2
00300450600900
sin0
1
cos10
tan01
1st Quadrant angles
2nd Quadrant angles
sin=positive(+)
cos=negative(-)
tan=negative(-)3rd Quadrant angles
sin= negative (-)
cos=negative (-)
tan= positive (+)4th Quadrant angles
sin= negative (-)
cos= positive (+)
tan= negative (-)angles are measured in degree and radians.
1800 = radians ( c )
10 = radian
similarly
Write, Reciprocal trigonometric ratios
I
II
Identities (Questions)
A. Simplify
B. Proof the following
Answers
A.
B. Proove
Find the positive angle1.
2.
3.
4.
5.
6.
7.
8.
Bearings - Introduction
1. Draw a line, and show the North direction.
2. Use clockwise sense to measure the angles from the North.
3. Write the bearing in 3 digits.
Ex:
1. Point X is 0500 bearing from Y.
2. Point B is 1500 bearing of from A.
Ex
1. Car A is 0300 bearings from Car B Draw the diagram.
Find the bearing of A from B.
2. A Car in morning 15 km North direction and morning another bearing of 0900. Find the bearing of the Car from the initial point.Ans
1.
Bearing of B from A is 2100
2.
Bearing is 0300 from the starting point.
Angle of elevation
An observer in the ground and the object is in above him, then the angle between lines, horizontal and object is called angle of elevation
is called angle of elevation.
Angle of depression
is angle of depression
Question
1. A man observer a vertical tree, distance between the man and bottom or the tree is height of the tree is 50m. Find the angle of elevation to the top of the tree?
2. A man sit on the top of the building and observer in the ground object. Angle of the depression is 600 and the height of the building is 50m. Find the distance between building and ground.
3.
Observer in at D. Angle of depression of the bottom of the building is 450 angle of the elevation of the top the building is 600 If the height of AD=, Find the height of the building BC
Ans
Sine and Cosine RuleThe solution for an oblique triangle can be done with the application of the Law of Sine and Law of Cosine, simply called the Sine and Cosine Rules. An oblique triangle, as we all know, is a triangle with no right angle. It is a triangle whose angles are all acute or a triangle with one obtuse angle.
The two general forms of an oblique triangle are as shown:
Sine Rule (The Law of Sine)
The Sine Rule is used in the following cases:
CASE 1: Given two angles and one side (AAS or ASA)
CASE 2: Given two sides and a non-included angle (SSA)
The Sine Rule states that the sides of a triangle are proportional to the sines of the opposite angles. In symbols,
Case 2: SSA or The Ambiguous Case
In this case, there may be two triangles, one triangle, or no triangle with the given properties. For this reason, it is sometimes called the ambiguous case. Thus, we need to examine the possibility of no solution, one or two solutions.
Cosine Rule (The Law of Cosine)The Cosine Rule is used in the following cases:
1. Given two sides and an included angle (SAS)
2. Given three sides (SSS)
The Cosine Rule states that the square of the length of any side of a triangle equals the sum of the squares of the length of the other sides minus twice their product multiplied by the cosine of their included angle. In symbols:
Find the all the missing sides in this triangle, then work out its area
1)
Fill in all the missing angles in these triangles
2a)
b)
3a) Find the missing length x b) Find the missing angle x
4)
5)
Graphical Method of Solution of a Linear Programming Problem
So far we have learnt how to construct a mathematical model for a linear programming problem. If we can find the values of the decision variables x1, x2, x3, ..... xn, which can optimize (maximize or minimize) the objective function Z, then we say that these values of xi are the optimal solution of the Linear Program (LP).
a) The determination of the solution space that defines the feasible solution. Note that the set of values of the variable x1, x2, x3,....xn which satisfy all the constraints and also the non-negative conditions is called the feasible solution of the LP.
b) The determination of the optimal solution from the feasible region.
a) To determine the feasible solution of an LP, we have the following steps.
Step 1: Since the two decision variable x and y are non-negative, consider only the first quadrant of xy-coordinate plane
Draw the line ax + by = c (1)
For each constraint,
the line (1) divides the first quadrant in to two regions say R1 and R2, suppose (x1, 0) is a point in R1. If this point satisfies the in equation ax + by c or ( c), then shade the region R1. If (x1, 0) does not satisfy the inequality, shade the region R2.
Step 3: Corresponding to each constant, we obtain a shaded region. The intersection of all these shaded regions is the feasible region or feasible solution of the LP.
Let us find the feasible solution for the problem of a decorative item dealer whose LPP is to maximize profit function.
Z = 50x + 18y (1)
Subject to the constraints
Step 1: Since x0, y0, we consider only the first quadrant of the xy - plane
Step 2: We draw straight lines for the equation
2x+ y = 100 (2)
x + y = 80
To determine two points on the straight line 2x + y = 100
Put y = 0, 2x = 100
x = 50
(50, 0) is a point on the line (2)
put x = 0 in (2), y =100
(0, 100) is the other point on the line (2)
Plotting these two points on the graph paper draw the line which represent the line 2x + y =100.
This line divides the 1st quadrant into two regions, say R1 and R2. Choose a point say (1, 0) in R1. (1, 0) satisfy the inequality 2x + y 100. Therefore R1 is the required region for the constraint 2x + y 100.
Similarly draw the straight line x + y = 80 by joining the point (0, 80) and (80, 0). Find the required region say R1', for the constraint x + y 80.
The intersection of both the region R1 and R1' is the feasible solution of the LPP. Therefore every point in the shaded region OABC is a feasible solution of the LPP, since this point satisfies all the constraints including the non-negative constraints.
b) There are two techniques to find the optimal solution of an LPP.
Corner Point Method
The optimal solution to a LPP, if it exists, occurs at the corners of the feasible region.
The method includes the following steps
Step 1: Find the feasible region of the LLP.
Step 2: Find the co-ordinates of each vertex of the feasible region.
These co-ordinates can be obtained from the graph or by solving the equation of the lines.
Step 3: At each vertex (corner point) compute the value of the objective function.
Step 4: Identify the corner point at which the value of the objective function is maximum (or minimum depending on the LP)
The co-ordinates of this vertex is the optimal solution and the value of Z is the optimal value
Example: Find the optimal solution in the above problem of decorative item dealer whose objective function is Z = 50x + 18y.
In the graph, the corners of the feasible region are
O (0, 0), A (0, 80), B(20, 60), C(50, 0)
At (0, 0) Z = 0
At (0, 80) Z = 50 (0) + 18(80)
= 1440
At (20, 60), Z = 50 (20) +18 (60)
= 1000 + 1080 = Rs.2080
At (50, 0) Z = 50 (50 )+ 18 (0)
= 2500.
Since our object is to maximize Z and Z has maximum at (50, 0) the optimal solution is x = 50 and y = 0.
The optimal value is 2500.
If an LPP has many constraints, then it may be long and tedious to find all the corners of the feasible region. There is another alternate and more general method to find the optimal solution of an LP, known as 'ISO profit or ISO cost method'
ISO- PROFIT (OR ISO-COST)
Method of Solving Linear Programming Problems
Suppose the LPP is to
Optimize Z = ax + by subject to the constraints
This method of optimization involves the following method.
Step 1: Draw the half planes of all the constraints
Step 2: Shade the intersection of all the half planes which is the feasible region.
Step 3: Since the objective function is Z = ax + by, draw a dotted line for the equation ax + by = k, where k is any constant. Sometimes it is convenient to take k as the LCM of a and b.
Step 4: To maximise Z draw a line parallel to ax + by = k and farthest from the origin. This line should contain at least one point of the feasible region. Find the coordinates of this point by solving the equations of the lines on which it lies.
To minimise Z draw a line parallel to ax + by = k and nearest to the origin. This line should contain at least one point of the feasible region. Find the co-ordinates of this point by solving the equation of the line on which it lies.
Step 5: If (x1, y1) is the point found in step 4, then
x = x1, y = y1, is the optimal solution of the LPP and
Z = ax1 + by1 is the optimal value.
The above method of solving an LPP is more clear with the following example.
Example: Solve the following LPP graphically using ISO- profit method.
maximize Z =100 + 100y.
Subject to the constraints
Suggested answer:
since x0, y0, consider only the first quadrant of the plane graph the following straight lines on a graph paper
10x + 5y = 80 or 2x+y =16
6x + 6y = 66 or x +y =11
4x+ 8y = 24 or x+ 2y = 6
5x + 6y = 90
Identify all the half planes of the constraints. The intersection of all these half planes is the feasible region as shown in the figure.
Give a constant value 600 to Z in the objective function, then we have an equation of the line
120x + 100y = 600 (1)
or 6x + 5y = 30 (Dividing both sides by 20)
P1Q1 is the line corresponding to the equation 6x + 5y = 30. We give a constant 1200 to Z then the P2Q2 represents the line.
120x + 100y = 1200
6x + 5y = 60
P2Q2 is a line parallel to P1Q1 and has one point 'M' which belongs to feasible region and farthest from the origin. If we take any line P3Q3 parallel to P2Q2 away from the origin, it does not touch any point of the feasible region.
The co-ordinates of the point M can be obtained by solving the equation 2x + y = 16
x + y =11 which give
x = 5 and y = 6
The optimal solution for the objective function is x = 5 and y = 6
The optimal value of Z
120 (5) + 100 (6) = 600 + 600
= 1200
Statistics and probability
Definitions:
Event Any collection of results or outcomes of a procedure
Simple Event An outcome or event that cannot be broken down into simpler components
Sample Space The collection of all simple events that could result from a procedure.
Complement The complement of an event A consists of all outcomes where A does not occur.
Notations:
P this means probability
A, B, C, these stand for events
Ac, this means the complement of A
P(A) this means the probability that A occurs
S this is used to denote the sample space
Example:
Q: Raj rolls a 6-sided die. Then the sample space of this is as followsA: S = {1, 2, 3, 4, 5, 6}Q: Sue measures how many coin flips it takes to get 3 heads. What is the sample space of this procedure?
A: S = {3, 4, 5,} = {all integers > 2}Q: Fred sees what proportion of cars on his block are SUVs. What is the sample space of this procedure?
A: S = {any real number between 0 and 1} = [0,1]
Since events come in a lot of different ways, there are 3 general approaches to finding the probabilities for events. The method that is most useful depends on the situation.
Approach 1: Relative Frequency Approximation
For procedures that can be repeated over and over again, we can estimate the probability of an event A by using the following:
From theoretical arguments (see Law of Large Numbers, p.141), it turns out that this value p will get closer to P(A) as the number of trials gets larger.Approach 2: Classical Approach
For procedures with equally likely outcomes (e.g. rolling a die, flipping a coin, etc.), we can find P(A) directly, by computing:
Approach 3: Subjective Probability
For procedures that cannot be repeated, and do not have equally likely outcomes, the true probability of an event is usually not able to be determined. In situations like this, we can estimate the probability using our knowledge and experience of the subject. For instance, we could ask What is the probability that the Columbus Blue Jackets will win the Stanley Cup this year? No one knows the true probability, but people who know a lot about hockey could give a ballpark figure.Examples:
A situation where Approach 1 is used is in baseball. If we want to know the probability that a player will get a hit when they go up to bat, we cannot use Approach #2 because the outcomes are not equally likely. We could use Approach #3, but that would be subjective. However, by dividing the number of hits by the number of at-bats gives the batting average, which is an estimate of the true probability of getting a hit.
A situation where Approach 2 is used is something like rolling a die. Each face is equally likely to turn up, so we can find probabilities using this approach. Lets say A is the event of rolling an even number. What is P(A)?
Another Example
Q: Joe flips one coin 3 times and records the 3 outcomes. What is the sample space?
A: S = {HHH, HHT, HTH, HTT, THH, THT, TTH, TTT}
Q: What is the probability of getting 1 or 2 heads?
A: Since all outcomes are equally likely (we assume the coin is fair), we can use Approach #2.
Q: What is the probability of the complement of the previous event? (i.e. P(not 1 or 2 heads))
A: There are 2 ways this can happen (HHH or TTT), so it will be
Section 4-3: Addition RuleCompound Event An event that is comprised of two or more simple events.
Generally, compound events are written in terms of their simple events.
For example, the event It will rain or snow today could be written as A or B, where A is the event that it rains today and B is the event that it snows today. So this event would happen if it rained today, snowed today, or both.
Another type of event is of the form A and B, in which the event only occurs if both A and B occur.
For example, the event It is at least 70 degrees and sunny outside could be written as A and B, where A is the event that it is at least 70 degrees outside, and B is the event that it is sunny.The Formal Addition RuleTo see how this rule is derived, lets examine a Venn Diagram. The area within each circle corresponds to the probability of that event occurring. Where the two circles overlap (dark grey), both A and B occur. However the area, say, in circle A that does not overlap B (grey) would be when A occurs but B does not. The area outside of both circles (light grey) corresponds to neither A nor B occurring.
How would we find P(A or B) then? We want the area within the two circles (the grey and dark grey areas) because thats where A happens, B happens, or they both happen. What we could do is add together the area in circle A, and the area of circle B. The problem is that we could the overlapping area (dark grey) twice. That means we need to subtract it. Using the fact that the area in circle A is P(A), the area in circle B is P(B), and the overlap is P(A and B), we get the formal addition rule:
P(A or B) = P(A) + P(B) P(A and B)
This rule works for any events A and B. Anytime you know three of the four quantities in the equation, you can solve for the fourth.
Disjoint Events
Disjoint Events are events that cannot both happen at the same time. For example, let A be the event that a traffic light is green, and B be the event that the traffic light is red. The event A and B cannot happen, because traffic lights are never green and red at the same time. If two events are disjoint, then P(A and B) = 0. Disjoint events are also often called mutually exclusive events.Addition Rule for Disjoint Events
Using the fact that P(A and B) = 0 for disjoint events, we can rewrite the formal addition rule as:P(A or B) = P(A) + P(B)
Complementary EventsRecall from the previous section that for an event A, its complement Ac is the event that A does not occur. Since Ac only happens when A does not, and vice versa, P(A and Ac) = 0. In other words, A and Ac are disjoint. Therefore, P(A or Ac) = P(A) + P(Ac), by the addition rule for disjoint events. But what is P(A or Ac)? This means the probability that either A happens, or A does not happen. This probability is 1, since something has to happen, whether it is A or not. Therefore, we have a trio of equivalent formulas:
P(A) + P(Ac) = 1
P(Ac) = 1 P(A)
P(A) = 1 P(Ac)
Examples: For the following questions, imagine we are drawing one card from a deck of 52 cards.
Q: What is the probability of drawing a queen?
A: Using Approach 2 from the previous section, and letting A be the event in question,
Q: What is the probability of drawing a diamond?
A: Using Approach 2 from the previous section, and letting B be the event in question,
Q: What is the probability of drawing a queen of diamonds?
A: This is the event A and B, and we can use Approach 2 again:
Q: What is the probability of drawing a queen or a diamond?
A: We could could up the total number of cards that fit this bill (13 diamonds one of which is a queen and the other 3 queens = 16
possible cards out of 52), or we can just use the formal addition rule:
Q: What is the probability of drawing a number card? (Aces included)
A: Lets call this event C. There are 4 of each number 1 to 10, for a total of 40 out of 52 cards.
Q: What is the probability of drawing a number card or a queen?
A: Now we can use the addition rule for disjoint events, since A and C cant happen at the same time.
Section 4-4: Multiplication Rule: The BasicsNow that we can find A or B probabilities, we focus on how to find A and B probabilities. Intuitively, for A and B to happen, we need two things to take place:
i. A needs to happen
ii. Given that A happened, B needs to happen
This leads us to
The Formal Multiplication RuleP(A and B) = P(A)P(B|A)
Here, P(B|A) is what is called a conditional probability. It stands for the probability that B happens given A already happened. (The vertical bar means given) Since A and B is the same as B and A, we can also write the formula as:P(A and B) = P(B)P(A|B)
Which form you use depends on what information is available.
Example: Students can take a standardized test at three test centers A, B, and C. Suppose that after the most recent test, 500 students went to A, 200 went to B, and 300 went to C. Furthermore, the proportion of students who passed the exam were 50%, 80%, and 75%, respectively.
Q: What is the probability that a randomly selected student took the test at center B?
A: There are a total of 1000 students, and 200 went to B. Thus P(B) = 200/1000 = 0.20.
Q: What is the probability that a student who took the test at B passed the exam?
A: Now, we want to find the probability of passing given that the student took the test at B. We are told in the problem that 80% of
the students at center B passed. Thus we have: P(Pass | B) = 0.80.
Q: What is the probability that a student both took the test at B and passed?
A: Using the Multiplication Rule, P(Pass and B) = P(B)P(Pass | B) = (0.20)(0.80) = 0.16.
Independent Events
Two events are called independent if the occurrence of one does not affect the chances of the other one occurring. Statistically, what this means is that A and B independent ( P(A | B) = P(A). In other words, the probability of A happening given that B happened is just the same as if we didnt know whether B happened (because the occurrence of B has no effect on the occurrence of A).
Note: if A and B are disjoint, then we know that only one can occur. Thus, knowing that B happened tells you that A definitely did not happen, and we have P(A | B) P(A). Thus disjoint events are never independent events.Multiplication Rule for Independent Events
Using the fact that P(A | B) = P(A) for independent events, we see that the formal multiplication rule turns into:P(A and B) = P(A)P(B)
The Law of Total Probability
This rule is very intuitive, and is useful for finding probabilities of events. To explain it, we refer to the test center example above.Q: What is the probability of a randomly selected student passing the exam?
A: From the information above, we can find out (similar to the previous example) that:
P(A) = 0.50
P(B) = 0.20
P(C) = 0.30
P(Pass | A) = 0.50 P(Pass | B) = 0.80 P(Pass | C) = 0.75
We want to find P(Pass). What are the possible scenarios where a student passes the exam? They could take the test at A and
pass, they could take it at B and pass, or they could take it at C and pass.
So P(Pass) = P(A and Pass OR B and Pass OR C and Pass). But each of those 3 scenarios are disjoint, because a student cant take
the test at more than one center. Therefore, by the addition rule we can add these probabilities as follows:
P(Pass) = P(A and Pass) + P(B and Pass) + P(C and Pass)
Then, by the multiplication rule, we can find all of these probabilities:
P(A and Pass) = P(A)P(Pass | A) = (0.50)(0.50) = 0.25
P(B and Pass) = 0.16
P(C and Pass) = P(C)P(Pass | C) = (0.30)(0.75) = 0.225
Thus P(Pass) = 0.25 + 0.16 + 0.225 = 0.635
In general, if you have disjoint events B1, B2, , Bn that represent every possible outcome of a procedure, then you can write:P(A) = P(A and B1) + P(A and B2) + + P(A and Bn) =
The most common way to use this rule is if you have two events A and B, then:P(A) = P(A and B) + P(A and Bc)
Examples:
A telemarketing company makes phone calls to potential customers all across the U.S. For each call, the probability of the customer answering the phone is 0.20. For the next couple of questions, assume calls are independent of each other.Q: Lets say the company makes 10 phone calls. What is the probability that all of them are answered?
A: P(10 calls answered) = P(1st call answered AND 2nd call answered AND AND 10th call answered)
= P(1st call answered)P(2nd call answered) P(10th call answered) ( (Mult. Rule for Independent Events)
= (0.20)(0.20) (0.20) = 0.2010 = 0.0000001024
Not very likely, is it?Q: Lets say the company makes 2 phone calls. What is the probability that exactly one of them is answered?
A: First, note that from the Complement Rule, the probability that a call is not answered is 1 0.20 = 0.80. Thus:
P(1 call answered) = P(1st call answered and 2nd call not answered OR 1st call not answered and 2nd call answered)
= P(1st call answered and 2nd call not answered) + P(1st call not answered and 2nd call answered) ( (Add. Rule)
= P(1st call answered)P(2nd call not answered) + P(1st call not answered)P(2nd call answered) ( (Mult. Rule)
= (0.20)(0.80) + (0.80)(0.20) = 0.16 + 0.16 = 0.32
Q: Now suppose that if a customer answers the phone, their chance of buying the product is 0.10. (Note that if they do not answer the
phone, their chance of buying it is 0). What is the overall chance of a telemarketer selling the product when they call a home?
A: In the question, we are told P(Buying | Call Answered) = 0.10 and P(Buying | Not Answered) = 0. We want to find P(Buying).
From the Law of Total Probability,
P(Buying) = P(Buying and Call Answered) + P(Buying and Not Answered)
= P(Call Answered)P(Buying | Call Answered) + P(Not Answered)P(Buying | Not Answered) ( (Mult. Rule)
= (0.20)(0.10) + (0.80)(0) = 0.02.
Note: If this seemed complicated, try just replaced Buying with A, Call Answered with B, and Not Answered with Bc. Then
the calculations above follow directly from the Law of Total Probability written before.I. DESCRIPTIVE STATISTICS
There are certain statistics that can help us condense large amounts of data into a few numbers that are easier to comprehend. These statistics are called descriptive statistics and they are used to convey summary information about any set of numbers or data. By using descriptive statistics we can get a quick estimate of what our data (e.g., students' Mathematics scores; people's lifes expectation)II. MEASURES OF CENTRAL TENDENCYMeasures of central tendency are statistics that identify the center of a distribution of scores. The most common measures of central tendency are the mode, the median, and the mean. To make calculations easier, instead of discussing full data sets .A. The modeThe mode is a statistic that identifies the most frequently occurring score in a distribution. For example, in the following distribution, the mode is 6:
4 6 7 8 6 3 5 9 6
Mode = 6 (it occurs 3 times)
B. The medianThe median is a statistic that identifies the middle score in a distribution. For example, in the distribution above, the median is also 6. To determine this, you must first rearrange the numbers and order them from lowest to highest:
3 4 5 6 6 6 7 8 9
Median = 6
In a distribution with an odd number of scores, such as the one above, the median is simply the middle score. In this case it is 6 (a number which has 4 scores to the left of it and 4 scores to the right). In a distribution with an even number of scores, the median is found by taking the average of the two middle scores. For example, in the following distribution, the median is 5.5:
2 3 4 5 6 7 8 9
Median = 6 + 5 = 5.5
2
C. The meanThe mean, more commonly known as the average, is the most common measure of central tendency in statistics. It is determined by dividing the sum of the scores (N) in a distribution by the total number of scores (N) in that distribution. For example, in the distribution below, the mean is 6:
4 6 7 8 6 3 5 9 6
Mean = N = 4+6+7+8+6+3+5+9+6 = 6
N 9
In the above distribution, the mode, median, and mean were all the same value (6). The number six thus represents the center of that distribution no matter how we measure it. However, the mode, median, and mean are rarely the same for a given distribution. Here are some examples for you to work out on your own. You can look up the answers on the last page of this handout.
ModeMedianMeanData Set 1:4 6 7 2 7 9 3 7__________________
Data Set 2:3 8 5 7 4 4 7 4 __________________
Data Set 3:8 9 7 8 1 5 6 8__________________
III. MEASURES OF DISPERSION
A. VarianceMeasures of central tendency provide useful information, but they do not always accurately represent the entire distribution. In addition to a measure of central tendency, it is usually helpful to know something about the extent to which the scores in a given distribution differ (or deviate) from the mean. Another way to state this issue is to ask the question, "How much variation is there in a given set of scores?" Obviously, if all the scores in a set of data are the same (e.g., if every professor goes off on 6 boring tangents/irrelevant anecdotes during lecture) then there is no variation. This rarely happens in research (or in real life), however; people vary in their characteristics, behaviors, attitudes, and emotions. If everyone was the same, then the science of Psychology could proceed by merely studying one person. How dull. Variety, as they say, is the spice of life.
The concept of "variation" in a set of data is illustrated easily by the following example. Given your tremendous popularity you receive invitations to 3 parties that all fall on the same night. All you are told is that the mean age of the 8 guests at each party will be 22 years old. Given this information, which party do you wish to attend? What other information might be helpful in making your decision?
The ages of those attending the 3 different parties are as listed in the following table:
PersonParty 1Party 2Party 3
#12034 2
#22393
#322102
#424413
#522384
#62473
#7203178
#821681
Mean:222222
Party 1 is going to be a night of who knows what with some young adults. Party 2 is going to be a dinner party with parents and their children. Party 3 is going to be Little Billy's third birthday party (hosted by his Grandma and Grandpa Jones). Therefore, although the mean age for each party is the same, these three data sets are very different from one another. Determining the mode and median for each party would give us a more complete picture, but it would be very helpful to have some statistic that tells us how much the ages of the guests at each party deviated or "varied" from the mean. Other than merely forming a subjective impression of our data, how do we determine this "variability" in scores?
The thought that immediately comes to mind is: " Let's simply add up how much each score differs from the mean." To do this, we could take the mean, which is 22, and then subtract the mean from each individual score. So, for example, for Person 1 at Party 1 we would have 20 - 22 = -2. For Person 2 and Party 1 we would have 23 - 22 = 1.
At this point, it will facilitate your understanding of this concept if you do the following. For Party 1, continue with these calculations and subtract the mean from each of the 8 scores. Then total up these "deviation scores," being sure to pay attention to the plus and minus signs. After you get your total, then perform the same calculations for Party 2 and Party 3. Move on to the paragraph below after you have finished these calculations.
Now you see the problem. For any set of data, if we simply subtract the mean from each individual score and add these deviation scores up, we will get a total of zero. Therefore, the average deviation will also come out to be zero (i.e., the sum of deviation scores divided by the number of scores, or 0/8 = 0 in our example.) Thus, we cannot determine the "average deviation" in this way. Astoundingly, to the great benefit of humankind, there are two statistics that provide very meaningful information about variability: the variance and the standard deviation. These are called measures of dispersion because they quantify the degree to which a set of scores, overall, differs from the mean.
The word "variance" -- because it sounds foreign, mystical, or technical -- sometimes produces a fear/anxiety response in students; some students sweat profusely, while others experience increased heart rate, nausea, or light-headedness. In extreme cases some students have heard voices telling them "Drop this course! Become an English major!" In case you are having any of the above reactions to the sight or sound of the word "variance," then do the following two things: 1) remember that Statistics are our friends, and 2) think of the word "variance" as a synonym for the word "variation."
Variance is defined as the average of the squared deviations about the mean. This is represented mathematically by the following equation, where X represents a single score within a distribution and N represents the total number of scores:
Variance = (X-Mean)2
N
The variance is arrived at by performing the following computations in the listed order:
Step 1. find the mean (sum of the scores divided by the number of scores)
Step 2.compute the deviation scores (the difference between an individual score and the mean)
Step 3.square each of the deviation scores
Step 4.divide the sum of the deviation scores by the number of scores
For example, the variance for Party 1 would be computed as follows:
PersonAgeMeanDeviation Score
(Age-Mean)Deviation Squared
#12022-24
#2232211
#3222200
#4242224
#5222200
#6242224
#72022-24
#82122-11
Average:2222018/8 = 2.25
The answer to step 4 above, then, is 18 divided by 8, or 2.25. This is the variance of ages at Party 1.
B. Standard DeviationThe standard deviation is the most commonly reported measure of dispersion. It is simply the square root of the variance. In the case of Party 1, the standard deviation is the square root of 2.25, or 1.5. Why take the square root of the variance? Well, remember that when we computed the variance we had to square each deviation score before adding these scores up. (As we saw earlier, if you add the deviation scores without squaring them, then you will always get a total of zero.) Therefore, because we squared the deviation scores to get the variance, we now take the square root of the variance in order to convert our numbers back to their original units of measurement. Thus, for Party 1 the mean is 22 years, the variance is 2.25, and the standard deviation is 1.5 years. At this point I strongly encouraged you to calculate the variance and standard deviation for Party 2 and Party 3 to check your understanding of these statistics. The correct answers are on the last page of the handout.)C. The RangeThe range is a relatively crude measure of dispersion. It represents the highest score in a distribution minus the lowest score. It is a crude measure of dispersion because the composition of other scores in the distribution (other than the high and low scores) have no effect on the range. For example, each of the 3 distributions below has a range of 8, despite the fact that the distributions are quite different. Each distribution, however, would have a different value for the variance (and hence, for the standard deviation).
10 7 6 5 4 3 2 Range = 10 - 2 = 8.
10 10 10 9 9 9 2Range = 10 - 2 = 8
10 4 4 3 2 2 2
Range = 10 - 2 = 8.
Variance and the standard deviation are more sensitive measures of dispersion, because they are influenced by each particular score in the distribution. Change even one score, and you'll change the values of the variance and standard deviation.
D. Additional Comments: This Handout Versus The TextYou should be aware of the following differences between the formula used in this handout versus the one used in your textbook. On page 423 of your textbook, a formula is given for calculating the standard deviation. This formula calculates the standard deviation by dividing by n-1. The examples in this handout divide by n. Remember that n corresponds to the number of people attending each party (8). Why the difference and which divisor should you use? The answer depends on what you want to use the standard deviation for. Consider the following two examples.
Example 1. Assume that I wish to know how much variability in age there is for students in this class. To gather this information, I have the 25 students in this class complete an anonymous questionnaire on which they indicate their age. If I am only concerned with the variability of age for this specific group of people (and I am not interested in trying to generalize my findings to other students), then I would divide by n. In this instance, the standard deviation I am calculating would be considered a descriptive statistic, since I only want to describe the variability of this particular set of numbers. (Aside: Computer programs and calculators can both calculate this number for us very quickly so why do I bother to make you calculate it by hand? No, I dont enjoy inflicting pain and anguish on my students (Ok maybe I do just a little!). The real reason for asking you to become familiar with this way of calculating the standard deviation is that it is useful in helping you gain a better conceptual understanding of measures of dispersion.)
Example 2. Alternatively, assume that I wish to know the variability in age for all students at Shoreline. In general, what kind of spread is there in age for students attending Shoreline? It would be possible for me to contact every single student at Shoreline, ask how old he or she is, and calculate the standard deviation of this rather large set of numbers. But this would be very time consuming (and besides, Im also very lazy!). What I could do instead is to determine the variability in age of a small sample of Shoreline students and then use this number to make an educated guess about the variability in age of the entire population of Shoreline students. So assume that I randomly sample 25 Shoreline students about their ages. Since I am using my sample to try to infer the variability in age for the whole population, when I calculate the standard deviation in this example, I divide by n-1 instead of n. In this second case, the standard deviation I am calculating would be considered an inferential statistic, since I am using the standard deviation of my sample to make an inference about the overall standard deviation of the entire population of students. For the purposes of this class, when you are asked to calculate the standard deviation, please divide by n.IV. Z-SCORES
Imagine that you and a friend are somewhat competitive and you want to compare how you each did on your last psychology exam. Unfortunately, you are taking different psychology classes (you are in Psychology 209 while your friend is in Psychology 204). What information would you need to find out who did better? You would probably start by comparing the points you each got correct on your respective exams. Lets say that you got 40 points correct and your friend got 20 points correct. Looks like you win, right? Not necessarily. You also need to know how many total points were on each exam. If your test had 50 possible points, and your friends test had 25, you are still tied (40/50 = 20/25 = 80%). The next thing you might want to know is what were the respective class means on each of the tests. If I tell you that the mean for your test was 30 (out of 50) while the mean for your friends test was 15 (out of 25), can you now tell who did better? It seems like you may have done better since you scored 10 points higher than the mean but your friend only scored 5 points higher than the mean. But remember your test had twice as many total points on it as your friends test (50 vs. 25), so the difference of each of your scores from the means still seems roughly equivalent.
As you can see, making a comparison in this situation is a bit difficult. But thanks to the standard deviation, there is still a way to make a comparison. If you also know the standard deviation of the scores in each of the classes, this can allow you and your friend settle your dispute. If I tell you that the standard deviation for both classes is 10 points, who did better on their test relative to the rest of their class? Fortunately for you, it looks like you are the winner. Your scores is a full standard deviation above the mean ((40-30)/10 = 1) but your friend was only a half of a standard deviation above the mean in his or her class ((20-15)/10 = 0.5). Thus, using standard deviations, we can see that you outscored a larger percentage of your class than your friend did of his/her class.
What we have just done in this example is to calculate something called a z-score. A z-score counts the difference between an individual score and the mean in terms of standard deviations. For instance, we could say that you scored 10 points above the mean on your test, or equivalently, that you scored 1.0 standard deviation above the mean. This 1.0 represents your z-score for this test. Similarly, the z-score for your friend was 0.5 standard deviation above the mean. He or she scored one half of a standard deviation better than the mean. It turns out that z-scores are a convenient way to compare scores from different groups that have used different numerical scales, as was the case in our example above (the scale used on your test was from 0-50 while the scale used in your friends class was from 0-25). By converting our numbers to z-scores, this allows us to make meaningful comparisons between the numbers in each of these groups, something we couldnt do initially. Z-scores also come in handy when trying to understand our next topic, the normal distribution.
V. THE NORMAL DISTRIBUTION
One of the most important concepts in statistics is a curve called the "normal distribution" or "normal curve." The normal distribution is an essential part of inferential statistics. While we will not be covering inferential statistics in this course, I would still like to introduce you to the normal curve and some of its unique properties. By learning a little about the normal curve now, you will be ahead of the game when you take your required statistics course.
The normal distribution is a bell shaped curved that is symmetric (that is, on either side of the mean it looks the same). A typical normal distribution is shown in Figure 1. The x-axis represents the all possible values or scores on some characteristic that we are interested in (e.g., SAT scores, reaction times, etc). The y-axis represents the frequency or percentage of each score on the x-axis occurs. Because it is symmetric, the mean, median, and mode for the normal distribution are all equal to one another. The main reason that the normal curve is useful is because there are many variables out in the real world which distribute themselves normally (i.e. they approximate a normal distribution). For instance, IQ is one variable that is normally distributed; if we were to look at the distribution of IQs for all adults, this distribution would look pretty much like the theoretical normal curve pictured below.
Figure 1.
Another useful feature of the normal distribution concerns the standard deviation. Specifically, in any normally distributed set of numbers, the standard deviation can be used to divide the distribution into segments which contain fixed percentages of scores. For instance, we know that in a normal distribution, 34% of the scores fall between the mean and one standard deviation above the mean (dont worry about how this percentage is calculated; it is simply a product of the mathematics of the normal distribution). Since the normal curve is symmetric, we also know that 34% of the scores will fall between the mean and one standard deviation below the mean. We can put these two pieces of information together to deduce that 68% of the scores in a normal distribution fall within one (plus or minus) standard deviation of the mean. Similar percentages also exist for segments further away from the mean and these are also shown in Figure 1.
To see why are these percentages useful, consider the following example. Assume that you took an IQ test and received a score of 130. Looking at this score, you assume that you did well but, being the competitive person you are, you want to know precisely how many people did as well or better than you. If we tell you that the average IQ score is 100 and that the standard deviation is 15 (both of which are true), you could determine, using the percentages listed in Figure 1, that only 2.5% of the people scored 130 or higher (Wow! Youre pretty smart!). Alternatively, you could say that you scored better than 98.5% of the people. In either case, the percentages generated by the normal distribution allow you to more accurately determine how well you did.
Another reason that the normal curve is useful concerns inferential statistics, a topic that we will discuss briefly later in this course. Inferential statistics will be covered in greater detail when you take statistics. I am briefly covering this information now in hopes that it will make it easier to assimilate when you come across it again in the future.Metric and Imperial unitsConversion Tables
The following tables show some of the more common measures, and the conversion between larger and smaller units. The left hand tables show the units for the metric system while the right hand tables show for the Imperial measurement systems.
Metric lengthImperial Length
10 millimeters=1 centimeter12 inches=1 foot
10 centimeters =1 decimeter3 feet=1 yard
10 decimeters=1 meter22 yards=1 chain
10 meters=1 decameter10 chains=1 furlong
10 decameters=1 hectometer8 furlongs=1 mile (5280 feet)
10 hectometers=1 kilometer (1000 meters)
Metric areaImperial area
100 square mm=1 square centimeter144 square inches=1 square foot
10000 square cm =1 square meter9 square feet=1 square yard
100 square m=1 are4840 square yards=1 acre
100 ares=1 hectare640 acres=1 square mile
100 hectares=1 square kilometer
=1000000 square meters
Metric massImperial weight
1000 grams=1 kilogram16 ounces=1 pound
1000 kilograms=1 ton14 pounds=1 stone (UK)
8 stones (UK)=1 hundredweight (UK)
=112 pounds (UK)
100 pounds=1 hundredweight (USA)
20 hundredweight (UK)=1 ton (UK)
=2240 pounds
20 hundredweight (USA)=1 ton (USA)
=2000 pounds
Metric capacityImperial liquid capacity
10 mililiters=1 centilitre2 teaspoons=1 dessertspoon
10 centiliters=1 decilitre3 teaspoons=1 tablespoon
10 deciliters=1 litre2 tablespoons=1 fluid ounce
1000 liters=1 cubic meter5 fluid ounces=1gill
2 gills=1 cup
2 cups=1 pint
=20 fluid ounces
2 pints=1 quart
4 quarts=1 gallon
USA liquid capacity
3 teaspoons=1 tablespoon
2 tablespoons=1 fluid ounce
4 fluid ounces=1 gill
2 gills=1 cup
2 cups=1 pint
16 fluid ounces
2 pints=1 quart
4 quarts=1 gallon
Representing Units
Length
The standard unit of length in the metric system is the meter. Other units of length and their equivalents in meters are as follows: 1 millimeter = 0.001 meter1 centimeter = 0.01 meter1 decimeter = 0.1 meter1 kilometer = 1000 meters
We symbolize these lengths as follows:1 millimeter = 1 mm1 centimeter = 1 cm1 meter = 1 m1 decimeter = 1 dm1 kilometer = 1 km
For reference, 1 meter is a little longer than 1 yard or 3 feet. It is about half the height of a very tall adult. A centimeter is nearly the diameter of a dime, a little less than half an inch. A millimeter is about the thickness of a dime.
Volume
The standard unit of volume in the metric system is the liter. One liter is equal to 1000 cubic centimeters in volume. Other units of volume and their equivalents in liters are as follows: 1 milliliter = 0.001 liter1 centiliter = 0.01 liter1 deciliter = 0.1 liter1 kiloliter = 1000 liters
From these units, we see that 1000 milliliters equal 1 liter; so 1 milliliter equals 1 cubic centimeter in volume. We symbolize these volumes as follows:1 milliliter = 1 ml1 centiliter = 1 cl1 deciliter = 1 dl1 liter = 1 l1 kiloliter = 1 kl
For reference, 1 liter is a little more than 1 quart. One teaspoon equals about 5 milliliters.
Mass
The standard unit of mass in the metric system is the gram. Other units of mass and their equivalents in grams are as follows:1 milligram = 0.001 gram1 centigram = 0.01 gram1 decigram = 0.1 gram1 kilogram = 1000 grams
We symbolize these masses as follows:1 milligram = 1 mg1 centigram = 1 cg1 decigram = 1 dg1 gram = 1 g1 kilogram = 1 kg
For reference, 1 gram is about the mass of a paper clip. One kilogram is about the mass of a liter of water.
Time
The following conversions are useful when working with time:1 minute = 60 seconds1 hour = 60 minutes = 3600 seconds1 day = 24 hours1 week = 7 days1 = 365 1/4 days (for the Earth to travel once around the sThis gives us a total of 52 complete 7 day weeks in each calendar year, with 1 day left over (or 2 in a leCoordinate Geometry
I. Distance between two points.
Look at horizontal and vertical distances.
Ex: Distance from ((3, (2) to (5, 4)
= 8 = 6
(AC)2 = 82 + 62
(AC)2 = 100
AC = 10
Distance from (x1, y1) to (x2, y2)
d2 = (x2 ( x1)2 + (y2 ( y1)2
d =
I. Midpoint.
( middle of a segment.
( find the midpoint for the vertical and
the horizontal segment.
( to find the middle use and
. The point (1, 2) is the
midpoint.
Median ( a segment from a vertex of a triangle to the midpoint of the opposite side.
Mid(A, C) = = (3, 1)
=
I. Slope of a line or segment.
Slope (m) = how steep a line is.
=
= for points (x1, y1) and (x2, y2).
Examples:
1. Find slopes for each of the following.
a.
b.
c.
m =
m =
m =
***The slope of a horizontal line (parallel to the xaxis) is 0.***The slope of a vertical line (parallel to the yaxis) is undefined.
***Lines rising to the right have a positive slope.***Lines falling to the right have a negative slope.I. Slope yintercept form of a line.
yintercept
( point where a relation intersects the yaxis. x = 0
xintercept
( point where the relation intersects the xaxis. y = 0
1. Find the yintercept and slope for the following.
a. 3x + 2y ( 12 = 0
b. y = (5x + 4
two points are (0, 6) and (2, 3) two points are (0, 4) and (3, (11)
m =
m =
m = and yintercept is (0, 6) m = (5 and yintercept is (0, 4)
From above y = mx + b; m = slope b = yintercept
2. Determine equations of the following lines given slope and point.
a. m = (2; (0, (3)
b. m = 3; yintercept is 4c. m = ; (0, (6
y = (2x ( 3
y = 3x + 4
y = (
d. m = (5 and same yintercept as 3x ( 4y + 32 = 0
yint is 8y = (5x + 8
3. Determine equations of the following.
a.
m =
b. m = , b =
y =
y =
4. The equation of a line is y = 2x + b. Find b if the line passes through the point:
a. (2, (6)
b. ((1, (3)
(6 = 2(2) + b
(3 = 2((1) + b
(10 = b
(1 = bI. Parallel and perpendicular lines.
Parallel lines have
Perpendicular lines have
the same slope.
slopes that are negative
reciprocals of each other.
Examples.
1. Find slopes of parallel and perpendicular lines to:
Parallel
Perpendicular
a. m =
b. y =
c. 4x + 5y ( 11 = 0
2. a. Given A (0, 2), B ((3, (4), C (2, (4)b. Given A (2, 3), B (6, 5), C ((1, 4)
and D ((8, 1), show that . and D (3, 6), is?
Ye
3. Which of the following lines are: i. parallel? ii. perpendicular?
a. 3x + 4y (24 = 0b. 4x + 3y ( 16 = 0c. 3x ( 4y + 10 = 0d. 6x + 8y + 15 = 0
m =
m =
m =
m =
i. a & d are parallel
ii. b & c are perpendicular
4. Find y in A (3, 8), B ((1, (2), C (4, 1) D (2, y) such that:
a.
b.
20 = (4y + 4
5y ( 5 = 4
16 = (4y
5y = 9
(4 = y
y =
5. Given , find k.
a.
b.
5k = 60
(2k = 15
k = 12
k = (7.5
6. For what value of k are the lines 3x ( 4y + 4 = 0 and kx + 3y + 10 = 0 perpendicular?
m = m =
(3k = (12
k = 4
7. Find the equation of the line through A ((1, 5) which is perpendicular to 3x ( 2y ( 12 = 0.
(2y = (3x + 12
m =
y =
3y ( 15 = (2x ( 2
m =
2x + 3y ( 13 = 0
8. Find the equation of a line which is parallel to 3x + 2y + 8 = 0 and has a yint of (2.
2y = (3x ( 8
y = mx + b
y =
y =
x0
A
B
C
Hypotenuse
Adjacent
Opposite
EMBED Equation.3
EMBED Equation.3
a
x
450
a
600
a
a
600
a
2a
2a
300 300
1st
4th
3rd
2nd
1st
4th
3rd
2nd
1st
4th
3rd
2nd
1st
4th
3rd
2nd
10 = QUOTE
EMBED Equation.3
EMBED Equation.3
EMBED Equation.3
EMBED Equation.3
450
450
300
300
EMBED Equation.DSMT4
300
300
600
600
EMBED Equation.DSMT4
300
300
600
600
EMBED Equation.DSMT4
450
450
600
600
EMBED Equation.DSMT4
500
N
Y
X
500
1500
N
B
A
N
300
300
N
B
A
1800
15km
EMBED Equation.DSMT4
900
Y
N
X
Z
ground
observer
h
object
h
horizontal
observer
object
d
EMBED Equation.DSMT4
man
50m
tree
50
=600
observer
object
x
=600
B
A
observer
D
building
y
x
C
Negative reciprocals
_1357554004.unknown
_1357554045.unknown
_1357554065.unknown
_1357554075.unknown
_1357554085.unknown
_1357554090.unknown
_1357554095.unknown
_1357554097.unknown
_1357554098.unknown
_1357554100.unknown
_1357554096.unknown
_1357554092.unknown
_1357554093.unknown
_1357554091.unknown
_1357554087.unknown
_1357554088.unknown
_1357554086.unknown
_1357554080.unknown
_1357554082.unknown
_1357554084.unknown
_1357554081.unknown
_1357554077.unknown
_1357554079.unknown
_1357554076.unknown
_1357554070.unknown
_1357554072.unknown
_1357554074.unknown
_1357554071.unknown
_1357554067.unknown
_1357554069.unknown
_1357554066.unknown
_1357554055.unknown
_1357554060.unknown
_1357554062.unknown
_1357554064.unknown
_1357554061.unknown
_1357554057.unknown
_1357554059.unknown
_1357554056.unknown
_1357554050.unknown
_1357554052.unknown
_1357554054.unknown
_1357554051.unknown
_1357554047.unknown
_1357554049.unknown
_1357554046.unknown
_1357554025.unknown
_1357554035.unknown
_1357554040.unknown
_1357554042.unknown
_1357554044.unknown
_1357554041.unknown
_1357554037.unknown
_1357554039.unknown
_1357554036.unknown
_1357554030.unknown
_1357554032.unknown
_1357554034.unknown
_1357554031.unknown
_1357554027.unknown
_1357554029.unknown
_1357554026.unknown
_1357554015.unknown
_1357554020.unknown
_1357554022.doc
_1357554024.unknown
_1357554021.unknown
_1357554017.unknown
_1357554018.unknown
_1357554016.unknown
_1357554010.unknown
_1357554012.unknown
_1357554013.unknown
_1357554011.unknown
_1357554007.unknown
_1357554008.unknown
_1357554006.unknown
_1357553978.unknown
_1357553992.unknown
_1357553999.unknown
_1357554002.unknown
_1357554003.unknown
_1357554001.unknown
_1357553996.unknown
_1357553997.unknown
_1357553998.unknown
_1357553993.unknown
_1357553994.unknown
_1357553984.unknown
_1357553988.unknown
_1357553989.unknown
_1357553991.unknown
_1357553987.unknown
_1357553986.unknown
_1357553982.unknown
_1357553983.unknown
_1357553979.unknown
_1357553981.unknown
_1357553964.unknown
_1357553972.unknown
_1357553974.unknown
_1357553975.unknown
_1357553977.unknown
_1357553973.unknown
_1357553967.unknown
_1357553969.unknown
_1357553970.unknown
_1357553968.unknown
_1357553965.unknown
_1357553956.unknown
_1357553962.unknown
_1357553963.unknown
_1357553959.unknown
_1357553960.unknown
_1357553958.unknown
_1357553954.unknown
_1357553955.unknown
_1357553951.unknown
_1357553953.unknown
_1357553950.unknown