Is there a difference between male/female heartbeats?

1
(No Transcript)
2
Is there a difference between male/female
heartbeats?

• Put pulse rates for class (m/f) on board
• Are there any unusual pulse rates?
• Calculate/compare using SOCS

3
1.1 Displaying Distributions with Graphs

• Dotplot Age of your fathers
• Low scale 45
• High scale 75
• Doesnt have to start at zero, just cover the
  range of the data
• Label the axis

4
Stemplot Age of your father
5
Stemplot details

• Since each stem is a class in the histogram, it
  looks like a dotplot or histogram on its side.
• Benefit preserves the actual value of each
  observation.
• Variations Round the data so that the final
  digit is suitable as a leaf. (Ex 3.468 ? 3.5,
  2.567 ? 2.6)
• You can split stems to double the number of stems
  when all the leaves would otherwise fall on just
  a few stems. (Leaves 0-4 go on upper stem, leaves
  5-9 go on the lower stem)
• Ex Data Set 110 111 111 113 114 114 114
  116 119
• 11 0113444
• 11 69

6
Literacy in Islamic Countries
7
More stemplot

• You can also split stems into five (0-1, 2-3,
  4-5, 6-7, 8-9).
• Back to back stemplot
• Quiz 1 Quiz 2
• 33 1 58
• 997650 2 2367778888999
• 5211 3 234468
• 9999888775320 4 0112236
• 00000 5 00

8
Pie Chart/Bar Graph of Radio Stations by Format
9
Do you listen while you walk?

• What is the trend with the use of the MP3 player?
• You must always look carefully at data and for
  situations (outliers, clusters, gaps in the
  data!) that seem to differ from the general
  pattern.
• ALWAYS think about whether the data you have
  helped answer your question.

10
Histogram by hand

• 1. Divide into classes of equal width.
• Table 1.3 (p.49) 81-145
• Range 75-155
• Specify classes precisely so that each
  observation falls into exactly one class.
• 2. Count of observations in each class
  (frequencies)
• 3. Draw histogram
• Horizontal scale for the variable (IQ Score)
• Vertical scale of counts (bar height class
  count)
• Each bar represents a class.

Class Count
75-84 2
85-94 3
95-104 10
105-114 16
115-124 13
125-134 10
135-144 5
145-154 1
11
Histograms by TI83/84

• Stat, Edit, 1
• Enter data from p. 49, Table 1.3
• Stat, Edit, 2 (Sort A) L1 (2nd, 1) to arrange
  from lowest to highest
• 2nd Statplot
• On, Type Histogram
• Xlist L1, Freq 1
• Zoom, 9

12
No right choice

• There are several ways of constructing classes in
  a histogram.
• Too few/too many classes will not give a good
  idea of the shape of the distribution.
• Use your judgment! Make sure the classes have the
  same width.

13
Dealing with Outliers

• Dont just write off outliers. You should search
  for an explanation for an outlier if you find
  one.
• Can you get rid of the outlier as bad data or
  can you live with the statistical consequences of
  including it?

14
Examples of things that are symmetric?

• SYMMETRIC
• Peoples heights
• Peoples weights
• Crocodile lengths
• Any biological measurements

• RIGHT-SKEWED
• Salaries
• Savings
• Home prices

15
Ogives (relative cumulative frequency graph)

1. Decide on class intervals construct columns for
   relative frequency, cumulative frequency, and
   relative cumulative frequency
2. Label/scale axes and title graph
3. Plot a point corresponding to the relative
   cumulative frequency in each class interval at
   the left endpoint of the next class interval.

16
Uses
17
Time plots

• Plots each observation against the time at which
  it was measured.
• Connect points with lines.
• Vertical axis variable
• Horizontal axistime
• Remember to look for overall pattern or
  deviations from the pattern

• P. 22

18
Forbidden Words in AP Stats

• Outlier (use outlier rules to prove, dont just
  assume)
• Skewed (too loosy-goosy, be specific left or
  right)
• Normal (prefer symmetric or bell-shaped
  otherwise must prove via Empirical Rule)
• Lurking variables (must identify a l.v. if
  talking about it)
• Confounding (type of association particular but
  over-used in wrong situations)
• Range (other, better ways to describe
  variability)
• Bias (Name the type of bias, not just there is a
  bias)