Statistics 120
More R
First Prev Next Last Go Back Full Screen Close Quit
Subsetting
One of the strong features of R, is the ability to extract
data subsets in a exible way.
The subsetting in R applies to vectors and also to more
general objects.
The s
Statistics 120
Time Series Applications
First Prev Next Last Go Back Full Screen Close Quit
Atmospheric Carbon Dioxide Levels
The island of Hawaii is a volcanic cone which rises
roughly 17km from the ocean oor to the top of its
tallest peak.
The two tal
Statistics 120
Displaying Time Series Data
First Prev Next Last Go Back Full Screen Close Quit
Time Series
A time series is a set of observations made at equally
spaced points in time.
Time series observations are usually numerical
measurements, but occ
Statistics 120
Multipanel Conditioning II
First Prev Next Last Go Back Full Screen Close Quit
Trellis Graphics
The Trellis graphics system in R is written by Deepayan
Sarkar of the University of Wisconsin, using the Grid
graphics system written by Paul M
Statistics 120
Plots Based on Quantiles II
First Prev Next Last Go Back Full Screen Close Quit
An Example Rats and Ozone
A group of young rats was randomly split into two groups.
One group was used as a control and the other raised in an
ozone enriched en
Statistics 120
Fitting a Straight Line
First Prev Next Last Go Back Full Screen Close Quit
The Problem
Given a set of points
(x1 , y1 ), . . . , (xn , yn ),
how do we nd a straight line
y = a + bx
which provides a good description of the general trend
und
Statistics 120
Pie Charts, Bar Charts & Dot Charts
First Prev Next Last Go Back Full Screen Close Quit
A Single Categorical Variable
We often need to display a set of values each of which
is associated with a single category of a factor or
ordered factor
Statistics 120
Data Handling
First Prev Next Last Go Back Full Screen Close Quit
Data Formats
Usually raw data sets are entered using spreadsheet or
produced in a form suitable for reading into a
spreadsheet (see STAT 220 for more details).
The most com
Statistics 120 Using Colour
First Prev Next Last Go Back Full Screen Close Quit
Light and Dark Contrast
The basic structure of any image is conveyed by the light and dark contrast in the image. This information is conveyed by the basic R + G + B channel
Statistics 120
Density Traces
First Prev Next Last Go Back Full Screen Close Quit
Histograms
Traditional histograms work with a xed set of
histogram cells.
The height of each histogram bar provides a measure of
the density of data values within the bar.
Statistics 120
Mosaic Plots
First Prev Next Last Go Back Full Screen Close Quit
Who Listens To Classical Music?
The following table of values shows a sample of 2300 music
listeners classied by age, education and whether they listen
to classical music.
Edu
Statistics 120
Plots Based on Quantiles
First Prev Next Last Go Back Full Screen Close Quit
Percentiles and Quantiles
The k-th percentile of a set of values divides them so that k %
of the values lie below and (100 k)% of the values lie above.
The 25th p
Statistics 120
Histograms and Variations
First Prev Next Last Go Back Full Screen Close Quit
Graphics for a Single Set of Numbers
The techniques of this lecture apply in the following
situation:
We will assume that we have a single collection of
numeric
Statistics 120
Light and Color
First Prev Next Last Go Back Full Screen Close Quit
Light
Light is a form of electromagnetic radiation.
Electromagnetic radiation can be regarded as a
wave-like phenomenon.
There are different kinds of em-radiation, each
Statistics 120
Examining Three-Dimensional Data
First Prev Next Last Go Back Full Screen Close Quit
Examining Two Variables
The most important tool is the scatter plot.
Scatter plots do two things well
They display relationships between variables.
(Smo
Statistics 120
Multipanel Conditioning Plots
First Prev Next Last Go Back Full Screen Close Quit
Trellis Graphics
Trellis Graphics is a family of techniques for viewing
complex, multi-variable data sets.
The ideas have been around for a while, but were
Statistics 120
Scatter Plots and Smoothing
First Prev Next Last Go Back Full Screen Close Quit
An Example Car Stopping Distances
An experiment was conducted to measure how the
stopping distance of a car depends on its speed.
The experiment used a random
Statistics 120
Graphics II
First Prev Next Last Go Back Full Screen Close Quit
Building Up Plots
Graphs are produced in R by calling functions which
build up graphs in a step-by-step fashion.
Each function call carried out one small step of
producing th
Statistics 120
Perception I
First Prev Next Last Go Back Full Screen Close Quit
Visual Processing And The Brain
When an image is passed to the brain it is processed
through increasingly complex steps until it reaches the
higher areas of the brain.
Very
Statistics 120 Vision II
First Prev Next Last Go Back Full Screen Close Quit
High Resolution Vision
For a full visual examination of objects, we must move our eyes so that all parts of the object's image fall for a time on the fovea. We do this by moving
Statistics 120
Vision I
First Prev Next Last Go Back Full Screen Close Quit
The Visual System
The visual system consists of two parts.
The eyes act as image receptors.
The brain acts as an image processing and
interpretation unit.
Understanding how we
Statistics 120
Good and Bad Graphs
First Prev Next Last Go Back Full Screen Close Quit
The Plan
In this lecture we will try to set down some basic rules
for drawing good graphs.
We will do this by showing that violating the rules
produces bad graphs.
L
Statistics 120
A Graphical Tour
First Prev Next Last Go Back Full Screen Close Quit
Early Uses of Graphical Representation
The oldest known uses of graphical representation are
probably cave paintings found in a variety of caves in
Southern Europe (E.g.
Topics covered in SS 2864b, Winter 2014.
The numbered notes e.g. (3.1), give sections from the textbook. For some
of the material, the class notes are the best reference. (This summary is not
in exactly the same order as presented in class.)
1. Introducti
Statistics 120
Perception II
First Prev Next Last Go Back Full Screen Close Quit
Graphical Perception
Some visual processing takes place without any
concious effort on our part.
Psychologists call this preattentive vision.
In the context of extracting
Statistics 120
Information Visualisation
First Prev Next Last Go Back Full Screen Close Quit
Contact Details
Ross Ihaka
Room 275, Department of Statistics
Extension 5054
Ofce Hours:
Friday, Noon 2pm
By arrangement
First Prev Next Last Go Back Full S
Statistics 120
Statistical Computing With R
First Prev Next Last Go Back Full Screen Close Quit
The R System
This course uses the R computing environment for
practical examples.
R serves both as a statistical package and as a general
programming environ
Statistics 120
Graphics
First Prev Next Last Go Back Full Screen Close Quit
Computer Graphics
Drawing graphics in a window on the screen of a
computer is very similar to drawing by hand on a sheet
of paper.
We begin a drawing by getting out a clean piec
Statistics 120
Colourimetry
First Prev Next Last Go Back Full Screen Close Quit
Colour Matching
Much colour research was carried out in the 1920s and
1930s (mostly in the UK).
There were two goals for this research
To understand colour vision.
To deve
Statistics 120
Clusters and Surfaces
First Prev Next Last Go Back Full Screen Close Quit
High-Dimensional Data
A typical statistical data set can be laid out in a matrix
with rows corresponding to cases and columns to
variables.
If there are n cases and