Похожие презентации:

# Descriptive statistics. Frequency distributions and their graphs. (Section 2.1)

## 1. Descriptive Statistics

2Descriptive Statistics

Elementary Statistics

Larson

Larson/Farber Ch 2

Farber

## 2. Section 2.1

FrequencyDistributions and

Their Graphs

## 3. Frequency Distributions

Minutes Spent on the Phone102

71

103

105

109

124

104

116

97

99

108

112

85

107

105

86

118

122

67

99

103

87

87

78

101

82

95

100

125

92

Make a frequency distribution table with five classes.

Larson/Farber Ch 2

## 4. Frequency Distributions

Classes - the intervals used in the distributionClass width - the range divided by the number of classes,

round up to next number

greatest # - smallest #

# of classes

ALWAYS ROUND UP

Lower class limit - the smallest # that can be in the class

Upper class limit - the greatest # that can be in the class

Frequency - the number of items in the class

Larson/Farber Ch 2

## 5. Frequency Distributions

Midpoint - the sum of the limits divided by 2lower class limit + upper class limit

2

Relative frequency - the portion (%) of data in that class

class frequency (f)

sample size (n)

Cumulative frequency – the sum of the frequencies for that

class and all previous classes

Larson/Farber Ch 2

## 6. Construct a Frequency Distribution

Minimum = 67, Maximum = 125Number of classes = 5

Class width = 12

Class

67

Limits

78

79

90

5

91

102

8

103

114

9

126

115

Do all lower class limits first.

Larson/Farber Ch 2

Tally

3

5

## 7. Other Information

MidpointClass

Relative

Frequency

Cumulative

Frequency

67 - 78

3

72.5

0.10

3

79 - 90

5

84.5

0.17

8

91 - 102

8

96.5

0.27

16

103 - 114 9

108.5

0.30

25

115 - 126 5

120.5

0.17

30

Larson/Farber Ch 2

## 8. Frequency Histogram

A bar graph that represents thefrequency distribution of the data set

1. horizontal scale uses class boundaries

or midpoints

2. vertical scale measures frequencies

3. consecutive bars must touch

Class boundaries - numbers that separate classes

without forming gaps between them

Larson/Farber Ch 2

## 9. Frequency Histogram

ClassBoundaries

67 - 78

3

66.5 - 78.5

79 - 90

5

78.5 - 90.5

91 - 102

8

90.5 - 102.5

Time on Phone

9

9

103 -114

9

102.5 -114.5

8

8

7

115 -126

5

114.5 -126.5

6

5

5

5

4

3

3

2

1

0

66.5

78.5

90.5

102.5

minutes

Larson/Farber Ch 2

114.5

126.5

## 10. Relative Frequency Histogram

A bar graph that represents the relativefrequency distribution of the data set

Same shape as frequency histogram

1. horizontal scale uses class boundaries

or midpoints

2. vertical scale measures relative

frequencies

Larson/Farber Ch 2

## 11. Relative Frequency Histogram

Relative frequencyTime on Phone

minutes

Relative frequency on vertical scale

Larson/Farber Ch 2

## 12. Frequency Polygon

A line graph that emphasizes thecontinuous change in frequencies

1. horizontal scale uses class midpoints

2. vertical scale measures frequencies

Larson/Farber Ch 2

## 13. Frequency Polygon

Class67 - 78

Time on Phone

3

9

9

79 - 90

91 - 102

5

8

8

8

7

6

103 -114

9

5

115 -126

5

3

5

5

4

3

2

1

0

72.5

84.5

96.5

108.5

120.5

minutes

Mark the midpoint at the top of each bar. Connect consecutive

midpoints. Extend the frequency polygon to the axis.

Larson/Farber Ch 2

## 14. Ogive

Also called a cumulative frequency graphA line graph that displays the cumulative

frequency of each class

1. horizontal scale uses upper boundaries

2. vertical scale measures cumulative

frequencies

Larson/Farber Ch 2

## 15. Ogive

Cumulative FrequencyAn ogive reports the number of values in the data set that

are less than or equal to the given value, x.

Minutes on Phone

30

30

25

20

16

10

8

3

0

Larson/Farber Ch 2

0

66.5

78.5

90.5

102.5

minutes

114.5

126.5

## 16. Section 2.2

More Graphs andDisplays

## 17. Stem-and-Leaf Plot

-contains all original data-easy way to sort data & identify outliers

Minutes Spent on the Phone

102 124 108

86 103

82

71 104 112 118

87

95

103 116

85 122

87 100

105

97 107

67

78 125

109

99 105

99 101

92

Key values:

Larson/Farber Ch 2

Minimum value = 67

Maximum value = 125

## 18. Stem-and-Leaf Plot

Lowest value is 67 and highest value is 125, so liststems from 6 to 12.

Never skip stems. You can have a stem with NO leaves.

Stem

6|

7|

8|

9|

10 |

11 |

12 |

Larson/Farber Ch 2

Leaf

Stem

12 |

11 |

10 |

9|

8|

7|

6|

Leaf

## 19. Stem-and-Leaf Plot

6 |77 |18

8 |25677

9 |25799

10 | 0 1 2 3 3 4 5 5 7 8 9

11 | 2 6 8

12 | 2 4 5

Key: 6 | 7 means 67

Larson/Farber Ch 2

## 20. Stem-and-Leaf with two lines per stem

Key: 6 | 7 means 671st line digits 0 1 2 3 4

2nd line digits 5 6 7 8 9

1st line digits 0 1 2 3 4

2nd line digits 5 6 7 8 9

Larson/Farber Ch 2

6|7

7|1

7|8

8|2

8|5677

9|2

9|5799

10 | 0 1 2 3 3 4

10 | 5 5 7 8 9

11 | 2

11 | 6 8

12 | 2 4

12 | 5

## 21. Dot Plot

-contains all original data-easy way to sort data & identify outliers

Minutes Spent on the Phone

66

76

86

96

minutes

Larson/Farber Ch 2

106

116

126

## 22. Pie Chart / Circle Graph

• Used to describe parts of a whole• Central Angle for each segment

NASA budget (billions of $) divided

among 3 categories.

Billions of $

Human Space Flight

5.7

Technology

5.9

Mission Support

2.7

Larson/Farber Ch 2

Construct a pie chart for the data.

## 23. Pie Chart

Billions of $Human Space Flight

Technology

Mission Support

Total

5.7

5.9

2.7

14.3

Degrees

143

149

68

360

Mission

Support

19%

Human

Space Flight

40%

Technology

41%

Larson/Farber Ch 2

NASA Budget

(Billions of $)

## 24. Pareto Chart

-A vertical bar graph in which theheight of the bar represents

frequency or relative frequency

-The bars are in order of

decreasing height

-See example on page 53

Larson/Farber Ch 2

## 25. Scatter Plot

- Used to show the relationshipbetween two quantitative sets of data

Final

grade

(y)

95

90

85

80

75

70

65

60

55

50

45

40

0

2

4

6

8

10

12

Absences (x)

Larson/Farber Ch 2

Absences

x

8

2

5

12

15

9

6

14

16

Grade

y

78

92

90

58

43

74

81

## 26. Time Series Chart / Line Graph

- Quantitative entries taken at regularintervals over a period of time

- See example on page 55

Larson/Farber Ch 2

## 27. Section 2.3

Measures of CentralTendency

## 28. Measures of Central Tendency

Mean: The sum of all data values divided by the numberof values

For a population:

For a sample:

Median: The point at which an equal number of values

fall above and fall below

Mode: The value with the highest frequency

Larson/Farber Ch 2

## 29.

An instructor recorded the average number ofabsences for his students in one semester. For a

random sample the data are:

2 4 2 0 40 2 4 3 6

Calculate the mean, the median, and the mode

Larson/Farber Ch 2

## 30.

An instructor recorded the average number ofabsences for his students in one semester. For a

random sample the data are:

2 4 2 0 40 2 4 3 6

Calculate the mean, the median, and the mode

Mean:

Median:

Sort data in order

0 2 2 2 3 4

4

6

40

The middle value is 3, so the median is 3.

Mode:

The mode is 2 since it occurs the most times.

Larson/Farber Ch 2

## 31.

Suppose the student with 40 absences is dropped from thecourse. Calculate the mean, median and mode of the remaining

values. Compare the effect of the change to each type of average.

2 4 2 0 2 4 3 6

Calculate the mean, the median, and the mode.

Mode:

The mode is 2 since it occurs the most times.

Larson/Farber Ch 2

## 32.

Suppose the student with 40 absences is dropped from thecourse. Calculate the mean, median and mode of the remaining

values. Compare the effect of the change to each type of average.

2 4 2 0 2 4 3 6

Calculate the mean, the median, and the mode.

Mean:

Median:

Sort data in order.

0 2 2 2 3 4 4

6

The middle values are 2 and 3, so the median is 2.5.

Mode:

The mode is 2 since it occurs the most times.

Larson/Farber Ch 2

## 33. Shapes of Distributions

SymmetricUniform

Mean = Median

Skewed right

positive

Mean > Median

Larson/Farber Ch 2

Skewed left

negative

Mean < Median

## 34.

Weighted MeanA weighted mean is the mean of a data set

whose entries have varying weights

(x× w)

X =

åw

å

where w is the weight of each entry

Larson/Farber Ch 2

## 35.

Weighted MeanA student receives the following grades, A worth 4

points, B worth 3 points, C worth 2 points and D

worth 1 point.

If the student has a B in 2 three-credit classes, A in

1 four-credit class, D in 1 two-credit class and C in

1 three-credit class, what is the student’s mean

grade point average?

Larson/Farber Ch 2

## 36.

Mean of Grouped DataThe mean of a frequency distribution for a sample

is approximated by

å

X =

(x× f )

n

where x are the midpoints, f are the frequencies and

n is å f

Larson/Farber Ch 2

## 37.

Mean of Grouped DataThe heights of 16 students in a physical ed. class:

Height

60-62

63-65

66-68

69-71

Frequency

3

4

7

2

Approximate the mean of the grouped data

Larson/Farber Ch 2

## 38. Section 2.4

Measures of Variation## 39. Two Data Sets

Closing prices for two stocks were recorded on tensuccessive Fridays. Calculate the mean, median and mode

for each.

Stock A

Larson/Farber Ch 2

56

56

57

58

61

63

63

67

67

67

33

42

48

52

57

67

67

77

82

90

Stock B

## 40. Two Data Sets

Closing prices for two stocks were recorded on tensuccessive Fridays. Calculate the mean, median and mode

for each.

Stock A

Mean = 61.5

Median = 62

Mode = 67

Larson/Farber Ch 2

56

56

57

58

61

63

63

67

67

67

33

42

48

52

57

67

67

77

82

90

Stock B

Mean = 61.5

Median = 62

Mode = 67

## 41. Measures of Variation

Range = Maximum value – Minimum valueRange for A = 67 – 56 = $11

Range for B = 90 – 33 = $57

The range is easy to compute but only uses two

numbers from a data set.

Larson/Farber Ch 2

## 42. Measures of Variation

To calculate measures of variation that use every value inthe data set, you need to know about deviations.

The deviation for each value x is the difference between

the value of x and the mean of the data set.

In a population, the deviation for each value x is:

In a sample, the deviation for each value x is:

Larson/Farber Ch 2

## 43.

DeviationsStock A Deviation

56

– 5.5

56 – 61.5

56

– 5.5

56 – 61.5

57

– 4.5

57 – 61.5

58

– 3.5

58 – 61.5

61

– 0.5

63

1.5

63

1.5

67

5.5

67

5.5

67

5.5

Larson/Farber Ch 2

The sum of the deviations is always zero.

## 44. Population Variance

Population Variance: The sum of the squares of thedeviations, divided by N.

x

56

56

57

58

61

63

63

67

67

67

)2

(

– 5.5

– 5.5

– 4.5

– 3.5

– 0.5

1.5

1.5

5.5

5.5

5.5

30.25

30.25

20.25

12.25

0.25

2.25

2.25

30.25

30.25

30.25

188.50

Larson/Farber Ch 2

Sum of squares

## 45. Population Standard Deviation

Population Standard Deviation: The square root ofthe population variance.

The population standard deviation is $4.34.

Larson/Farber Ch 2

## 46. Sample Variance and Standard Deviation

To calculate a sample variance divide the sum ofsquares by n – 1.

The sample standard deviation, s, is found by

taking the square root of the sample variance.

Larson/Farber Ch 2

## 47. Interpreting Standard Deviation

Standard deviation is a measure of the typicalamount an entry deviates (is away) from the mean.

The more the entries are spread out, the greater

the standard deviation.

The closer the entries are together, the smaller the

standard deviation.

When all data values are equal, the standard

deviation is 0.

Larson/Farber Ch 2

## 48. Summary

Range = Maximum value – Minimum valuePopulation Variance

Population Standard Deviation

Sample Variance

Sample Standard Deviation

Larson/Farber Ch 2

## 49. Empirical Rule (68-95-99.7%)

Data with symmetric bell-shaped distribution have thefollowing characteristics.

13.5%

13.5%

2.35%

–4

–3

2.35%

–2

–1

0

1

2

3

4

About 68% of the data lies within 1 standard deviation of the mean

About 95% of the data lies within 2 standard deviations of the mean

About 99.7% of the data lies within 3 standard deviations of the mean

Larson/Farber Ch 2

## 50. Using the Empirical Rule

The mean value of homes on a certain street is$125,000 with a standard deviation of $5,000.

The data set has a bell shaped distribution.

Estimate the percent of homes between $120,000

and $135,000.

Larson/Farber Ch 2

## 51. Using the Empirical Rule

The mean value of homes on a certain street is $125,000 with astandard deviation of $5,000. The data set has a bell shaped

distribution. Estimate the percent of homes between $120,000 and

$135,000.

105

110

115

120

125

$120,000 is 1 standard deviation below

the mean and $135,000 is 2 standard

deviations above the mean.

130

135

140

145

68% + 13.5% = 81.5%

So, 81.5% have a value between $120 and $135 thousand.

Larson/Farber Ch 2

## 52. Chebychev’s Theorem

For any distribution regardless of shape theportion of data lying within k standard

deviations (k > 1) of the mean is at least 1 – 1/k2.

For k = 2, at least 1 – 1/4 = 3/4 or 75% of the data lie

within 2 standard deviation of the mean. At least 75%

of the data is between -1.68 and 13.68.

For k = 3, at least 1 – 1/9 = 8/9 = 88.9% of the data lie

within 3 standard deviation of the mean. At least 89%

of the data is between -5.52 and 17.52.

Larson/Farber Ch 2

## 53. Chebychev’s Theorem

The mean time in a women’s 400-meter dash is52.4 seconds with a standard deviation of 2.2 sec.

Apply Chebychev’s theorem for k = 2.

Larson/Farber Ch 2

## 54. Chebychev’s Theorem

The mean time in a women’s 400-meter dash is52.4 seconds with a standard deviation of 2.2 sec.

Apply Chebychev’s theorem for k = 2.

Mark a number line in

standard deviation units.

2 standard deviations

A

45.8

48

50.2

52.4

54.6

56.8

59

At least 75% of the women’s 400-meter dash

times will fall between 48 and 56.8 seconds.

Larson/Farber Ch 2

## 55. Standard Deviation of Grouped Data

å( x - x) fn -1

2

Sample standard deviation = s =

x

f

xf

x- x

(x - x)2

(x- x)2 f

å xf

f is the frequency, n is total frequency, x =

n

See example on pg 82

Larson/Farber Ch 2

## 56. Estimates with Classes

When a frequency distribution hasclasses, you can estimate the sample

mean and standard deviation by

using the midpoints of each class.

å xf

x=

n

å( x - x) f

n -1

2

s=

x is the midpoint, f is the frequency, n is total frequency

Larson/Farber Ch 2

See example on pg 83

## 57. Section 2.5

Measures of Position## 58. Quartiles

Fractiles – numbers that divide an ordereddata set into equal parts.

Quartiles (Q1, Q2 and Q3 ) - divide the data

set into 4 equal parts.

Q2 is the same as the median.

Q1 is the median of the data below Q2.

Q3 is the median of the data above Q2.

Larson/Farber Ch 2

## 59. Quartiles

You are managing a store. The average salefor each of 27 randomly selected days in the

last year is given. Find Q1, Q2, and Q3.

28 43 48 51 43 30 55 44 48 33 45 37

37 42 27 47 42 23 46 39 20 45 38 19

17 35 45

Larson/Farber Ch 2

## 60. Finding Quartiles

The data in ranked order (n = 27) are:17 19 20 23 27 28 30 33 35 37 37 38 39 42

42 43 43 44 45 45 45 46 47 48 48 51 55.

The median = Q2 = 42.

There are 13 values above/below the median.

Q1 is 30.

Q3 is 45.

Larson/Farber Ch 2

## 61. Interquartile Range (IQR)

Interquartile Range – the difference between thethird and first quartiles

IQR = Q3 – Q1

The Interquartile Range is Q3 – Q1 = 45 – 30 = 15

Any data value that is more than 1.5 IQRs to the

left of Q1 or to the right of Q3 is an outlier

Larson/Farber Ch 2

## 62. Box and Whisker Plot

A box and whisker plot uses 5 key values to describe a setof data. Q1, Q2 and Q3, the minimum value and the

maximum value.

Q

30

1

Q2 = the median

Q3

Minimum value

Maximum value

42

30

45

17

15

55

25

35

45

55

Interquartile Range = 45 – 30 = 15

Larson/Farber Ch 2

42

45

17

55

## 63. Percentiles

Percentiles divide the data into 100 parts. There are99 percentiles: P1, P2, P3…P99.

P50 = Q2 = the median

P25 = Q1

P75 = Q3

A 63rd percentile score indicates that score is greater

than or equal to 63% of the scores and less than or

equal to 37% of the scores.

Larson/Farber Ch 2

## 64. Percentiles

Cumulative distributions can be used to find percentiles.114.5 falls on or above 25 of the 30 values.

25/30 = 83.33.

So you can approximate 114 = P83.

Larson/Farber Ch 2

## 65. Standard Scores

Standard score or z-score - represents thenumber of standard deviations that a data

value, x, falls from the mean.

Larson/Farber Ch 2

## 66. Standard Scores

The test scores for a civil service exam have a mean of152 and standard deviation of 7. Find the standard zscore for a person with a score of:

(a) 161

(b) 148

(c) 152

Larson/Farber Ch 2

## 67. Calculations of z-Scores

(a)A value of x = 161 is 1.29

standard deviations above the

mean.

(b)

A value of x = 148 is 0.57

standard deviations below the

mean.

(c)

A value of x = 152 is equal to

the mean.

Larson/Farber Ch 2

## 68. Standard Scores

When a distribution is approximately bellshaped, about 95% of the data lie within 2

standard deviations of the mean. When this

is transformed to z-scores, about 95% of the

z-scores should fall between -2 and 2.

A z-score outside of this range is considered

unusual and a z-score less than -3 or greater

than 3 would be very unusual.

Larson/Farber Ch 2