This preview shows pages 1–3. Sign up to view the full content.
Chapter 2 (cont)
Chapter 3:
Association:
Contingency, Correlation, and
Regression
Read Chapter 3
Quick Review of Last Lecture
±
Graphical Display
²
Qualitative variables: bar plots and pie charts
²
Quantitative variables: histograms, stem and leaf plots, boxplots
±
Numerical summary:
²
Measures of center: mean, median
²
Measures of spread: range, IQR = 75
th
25
th
percentile
²
Other measures of spread: variance, standard deviation
±
Graphical and Numerical: Boxplot
Numerical Measures of Center
±
Mean
²
Arithmetic mean, Sample mean
²
Center of gravity
±
Median
²
the midpoint of the data, when data are ordered from
lowest to highest
²
50th percentile,
with half of the data above and half of the
data below.
±
Mode
²
The local maximum of distribution
²
The measurement that occurs most often
²
Commonly used as a measure of popularity
Measures of Dispersion, Spread, or
Variability
Range(data)
= max(data)  min(data)
Standard Deviation (formulas given soon)
Variance (formulas given soon)
Percentiles
²
Arrange the data in order from smallest to largest
²
The
ith
percentile is the value that has at most
i%
of
the measurements below it and at most
(100 – i)%
above
²
Quartiles
:
1
st
, 2
nd
or 3
rd
are respectively the 25
th
, 50
th
, and 75
th
percentiles.
IQR (interquartile range)=
75
th
percentile – 25
th
percentile
The FiveNumber Summary
±
The fivenumber summary of a dataset
consists of the
²
Minimum value
²
First Quartile
²
Median
²
Third Quartile
²
Maximum value
Criteria for identifying an outlier
±
An observation is a potential outlier
if it falls more than
1.5 x IQR
below
the first quartile or more than
1.5 x
IQR
above the third quartile
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentBoxplot
±
A box goes from the Q1 to Q3
±
A line is drawn inside the box at the median
±
A line goes from the lower end of the box to the smallest
observation that is not a potential outlier and from the
upper end of the box to the largest observation that is
not a potential outlier. The potential outliers are shown
separately
Recall Logarithms
x = log
b
y
<>
b
x
= y
.
We say that
This is the end of the preview. Sign up
to
access the rest of the document.
 '07
 VELLEMANP

Click to edit the document details