68
Statistics 2

Statistics 2

  • Upload
    eyad

  • View
    17

  • Download
    0

Embed Size (px)

DESCRIPTION

Statistics 2. Quantitative (Numerical) (measurements and counts). Qualitative (categorical) (define groups). Continuous. Discrete. Categorical (no idea of order). Ordinal (fall in natural order). We are only going to consider quantitative variables in this AS. Variables. - PowerPoint PPT Presentation

Citation preview

Page 1: Statistics 2

Statistics 2

Page 2: Statistics 2

Variables

DiscreteContinuous 

Quantitative(Numerical)

(measurements and counts)

Qualitative(categorical)

(define groups)

Ordinal(fall in natural order)

Categorical(no idea of order)

We are only going to consider quantitative variables in this AS

Page 3: Statistics 2

Quantitative

Discrete• Many repeated

values• Age groups• Marks

Continuous• Few repeated

values• Height• Length• Weight

Page 4: Statistics 2

Qualitative

Categorical• Gender• Religious

denomination• Blood types• Sport’s numbers

(e.g. He wears the number ‘8’ jersey)

Ordinal• Grades• Places in a race

(e.g. 1st, 2nd, 3rd)

Page 5: Statistics 2

Collecting data

• Tally charts • Stem and leaf plots

How we collect the data usually depends on what question we wish to

answer.

Page 6: Statistics 2

Tally chart

• If we were asking people what they had for breakfast we might set up a table like this…

Page 7: Statistics 2

Tally chart

Breakfast Tally Frequency

Toast

Cereal

Eggs

Porridge

Rice

No breakfast

Page 8: Statistics 2

Tally Chart

• We use a tally chart when data fits easily into categories.

Page 9: Statistics 2

Stem and leaf plot

• A stem and leaf plot sorts data that has few values the same.

Page 10: Statistics 2

Example

• The number of punnets of strawberries picked by Carol over a 17-day period. (This example is in your text book)

• 65 73 86 90 99 106 45 92 94 102 107 107 99 83 101 91

Page 11: Statistics 2

Example

• Set up a ‘stem’ based on the fact that the numbers picked are between 40 and 110

Page 12: Statistics 2

Example

Stem

4

5

6

10

Page 13: Statistics 2

Example

• The first number is 65 and the next is 73.

• They are recorded like this

Page 14: Statistics 2

Example

Stem Leaf

4

5

6 5

7 3

Page 15: Statistics 2

Example

Stem Leaf

4 5

5

6 5

7 3

8 6 3

9 0 9 2 4 7 9 1

10 6 2 7 7 1

Page 16: Statistics 2

Sort the data in order

Stem Leaf

4 5

5

6 5

7 3

8 3 6

9 0 1 2 4 7 9 9

10 1 2 6 7 7

Page 17: Statistics 2

Lowest and highest values

Stem Leaf

4 5 = 45

5

6 5

7 3

8 3 6

9 0 1 2 4 7 9 9

10 1 2 6 7 7 = 107

Page 18: Statistics 2

Median and quartiles

Stem Leaf

4 5 = 45

5

6 5

7 3

8 3 6 = 84.5

9 0 1 2 4 7 9 9

10 1 2 6 7 7 = 107

Page 19: Statistics 2

Median and quartiles

Stem Leaf

4 5

5

6 5

7 3

8 3 6

9 0 1 2 4 7 9 9

10 1 2 6 7 7

Page 20: Statistics 2

• 5- number summary• Lowest = 45• LQ = 84.5• Median = 94• UQ = 101.5• Highest = 107

Stem Leaf

4 5

5

6 5

7 3

8 3 6

9 0 1 2 4 7 9 9

10 1 2 6 7 7

Median and quartiles

Page 21: Statistics 2

Pictures that tell a story

• Drawing a picture of our data.

• Our data is discrete and hence a bar graph is an appropriate way of showing our ‘picture’.

Page 22: Statistics 2

A bar graph

Page 23: Statistics 2

A bar graph

• We use a bar graph (spaces between bars) because we are dealing with discrete data (counted data, many repeated values)

Page 24: Statistics 2

Bar graph

• A bar graph gives us a picture of the data and we can easily see many features of our data.

Page 25: Statistics 2

Bar graph

• Lowest = 3 letters• Highest = 8 letters• Mode = 5 letters• The graph is

approximately symmetrical and uni-modal (has only one mode)

Page 26: Statistics 2

Bar graph

• To find out how many were surveyed, you add the frequencies together.

Page 27: Statistics 2

Pie graph

• Each category makes up a certain percentage of the ‘pie’.

• A pie graph does not tell us how many were in the data set.

• You must be careful when comparing data from 2 pie graphs.

Page 28: Statistics 2

Pie graph

Letters Frequency Angle of pie

3 2 360÷35x2=21

4 5 360÷35 x 5=51

5 14 144

6 7 72

7 5 51

8 2 21

Page 29: Statistics 2

Pie graph

Page 30: Statistics 2

Pie Graph

• This also is an appropriate graph as it shows the relative numbers in each category.

• It does not give us a lot of specific information like how many were surveyed or how many had 8 letters in their name.

Page 31: Statistics 2

Box and Whisker plot

• The box and whisker plot is a picture of the 5-number summary and it shows us where the cut-off is for every quarter of the data.

• Again, the box and whisker plot does not tell us how many were in the sample just how the quarters were distributed.

Page 32: Statistics 2

Box and Whisker plot

Page 33: Statistics 2

Box and Whisker plot

• This gives us a lot of information.

• The lowest and highest values.

• The median, upper and lower quartiles.

• We also get a sense of how the data is distributed.

Page 34: Statistics 2

Box and Whisker Plot

• Box and whisker plots can also be used to compare two sets of data.

Page 35: Statistics 2

Back to strawberry picking!

• Who would you employ?

Page 36: Statistics 2

Strawberry picking

Page 37: Statistics 2

Comparing

Carol Dilip

Mean 90.4 90.1

Median 94 99

Mode 99 95

Page 38: Statistics 2

Comparing

Carol Dilip

Mean 90.4 90.1

Median 94 99

Mode 99 95

• Carol has the higher mean.

• Dilip has the higher median.

• Carol has the higher mode.

Page 39: Statistics 2

Central tendency

• Which central tendency is more useful in measuring the punnets picked overall?

Page 40: Statistics 2

Comparing

Carol Dilip

Range 62 108

Interquartile range

17 7.5

Lowest 45 0

Highest 107 108

Page 41: Statistics 2

Comparing

Carol Dilip

Range 62 108

Interquartile range

17 7.5

Lowest 45 0

Highest 107 108

• Carol has the lower range.

• Dilip has the lower interquartile range.

• Carol’s lowest value is higher than Dilip’s.

• Dilip’s highest value is higher than Carol’s.

Page 42: Statistics 2

Spread

• Which picker is more reliable?

Page 43: Statistics 2

Back to the data

Page 44: Statistics 2

Comparing using a picture

Page 45: Statistics 2

Box and whisker

Page 46: Statistics 2

Box and whisker

• Overall they both picked roughly the same number of punnets.

• Carol 1537• Dilip 1532

Page 47: Statistics 2

Box and whisker

• The long tails on the box and whisker plots suggest outliers (extreme values).

• 45 is a likely outlier for Carol and suggests she worked a half day.

• 0 suggests that Dilip did not work on one of the days which would have pulled his mean value down.

• 49 is also an outlier for Dilip suggesting he also worked half a day.

Page 48: Statistics 2

Box and whisker

• Dilip is more reliable as his spread as shown by the interquartile range is smaller.

• (This is presuming he doesn’t just take days off when he wants to.)

Page 49: Statistics 2

What not to do!!!

Page 50: Statistics 2

No! No! No!- this is not a good idea!

Page 51: Statistics 2

No! No! No!- this is not a good idea!

• Axes need to be labelled.

• Colour distorts the graph.

• Lines also distort the graph- take a look at these.

Page 52: Statistics 2

Are the lines parallel?

Page 53: Statistics 2

Are these lines parallel?

Page 54: Statistics 2

Are these lines parallel?

Page 55: Statistics 2

Are the lines parallel?

Page 56: Statistics 2
Page 57: Statistics 2

• This kind of graph gives us very little information.

Page 58: Statistics 2

Negatively skewed (unimodal)

Page 59: Statistics 2

Positively skewed

Page 60: Statistics 2

Symmetric

Page 61: Statistics 2

Uniform

Page 62: Statistics 2

Groupings (bimodal)

Page 63: Statistics 2

Outlier

Page 64: Statistics 2

Bi-variate data

• Looking for relationships between two variables.

Page 65: Statistics 2

Example

• Is there a relationship between the amount of study a person does and their test result?

Page 66: Statistics 2

Consider data on ‘hours of study’ vs ‘ test score’

Hours Score Hours Score Hours Score

18 59 14 54 17 59

16 67 17 72 16 76

22 74 14 63 14 59

27 90 19 72 29 89

15 62 20 58 30 93

28 89 10 47 30 96

18 71 28 85 23 82

19 60 25 75 26 35

22 84 18 63 22 78

30 98 19 61

Page 67: Statistics 2
Page 68: Statistics 2

Relationship

• There is a positive linear relationship between the amount of study and the test score. This means that as the hours of study increases, we expect an increase in test score.