Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
5 views

Lecture 8 Spatial Data Analysis

Uploaded by

sharontao
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
5 views

Lecture 8 Spatial Data Analysis

Uploaded by

sharontao
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 17

Environmental Data analysis

Lecture 8

Dr. Zhi NING


Spatial data analysis

• Introduction
– Detect patterns in the locations of objects in space
– Quantify correlation between the spatial locations
for two types of objects,
– Measure the spatial autocorrelation for the values
of a variable measured over space, and
– study the correlation between two variables
measured over space when one or both of those
variables displays autocorrelation.
Types of spatial data

• Quadrat counts
– the area of interest is divided into many square,
rectangular or circular study plots,
– and the number of objects of interest is counted in
either all of the study plots or a sample of them.

• Example
Quadrat counts
Distance from Distance along beach (m)
low water (m) 0 20 40 60 80 100 120 140 160 180 200
Counts of A
0 1 0 4 0 0 0 3 0 2 0 0
10 0 0 0 0 104 0 0 0 1 0 0
20 7 24 0 0 240 0 0 103 1 0 0
30 20 0 0 0 0 0 3 250 7 0 0
40 20 0 2 4 0 222 0 174 4 0 58
50 0 0 11 0 0 126 0 62 7 6 29
60 0 0 7 0 0 0 0 0 23 7 29
70 0 0 0 0 89 0 0 7 8 0 30

Counts of B
0 0 0 1 0 0 0 0 0 0 0 0
10 0 0 0 0 7 0 0 0 0 0 0
20 0 0 0 0 9 0 0 3 6 0 0
30 0 0 0 0 0 0 0 0 0 0 0
40 1 0 0 5 0 0 0 7 0 0 10
50 0 0 0 0 0 7 0 10 1 1 19
60 0 0 0 0 0 0 0 0 0 0 2
70 0 0 0 0 2 0 0 2 0 0 16
Quadrat counts

• Question
– Are the counts for A and B randomly distributed
over the study area, or is there evidence of either
a uniform spread or clustering
– Random or clustering or uniform?
• Types of Distributions
– Random: any point is equally likely to occur at any location, and
the position of any point is not affected by the position of any other
point.
– Uniform: every point is as far from all of its neighbors as possible:
“unlikely to be close”.
– Clustered: many points are concentrated close together, and there
are large areas that contain very few, if any, points: “unlikely to be
distant”
What do we mean by spatially random?

RANDOM UNIFORM/ CLUSTERED


DISPERSED
Quadrat counts

• To determine randomness (spread out).


• Complete spatial randomness
– Individual items are equally likely to be anywhere,
independent of each other.
– Counts in quadrats will have a Poisson distribution

P(k)=

l Is the expected value (mean) of the counts


k is the number of counts
Quadrat counts

Poisson distribution
Average=Variance

l is the expected value (mean) of the counts;


k is the number of counts.
VMR

• Test of R=variance/mean (VMR)


– Treat each cell as an observation and count the
number of points within it, to create the variable X

• For a uniform distribution, the variance is zero.


– Therefore, we expect a variance-mean ratio close to 0
• For a random distribution, the variance and mean are
the same.
– Therefore, we expect a variance-mean ratio around 1
• For a clustered distribution, the variance is relatively
large
– Therefore, we expect a variance-mean ratio above 1
VMR
Significance test

• A significance test for VMR can be conducted


based upon the chi-square frequency;
χ²
• The test will ascertain if a pattern is
significantly more clustered than would be
expected by chance (but does not test for a
uniformity)
• The values of the test statistics in our cases
would be:
random uniform clustered

60-(202)/10 40-(202)/10 200-(202)/10 80


= 10 = 0
=

2 2 2
Significance test

• For degrees of freedom: N - 1 = 10 - 1 = 9,


the value of chi-square at the 1% level is
21.666. CHISQ.INV(0.99,9)
• Thus, there is only a 1% chance of obtaining
a value of 21.666 or greater if the points had
been allocated randomly. Since our test
statistic for the clustered pattern is 80, we
conclude that there is (considerably) less
than a 1% chance that the clustered pattern
could have resulted from a random process
Kolmogorov-Smirnov (K-S) Test

• Frequency Distribution Comparison


• In addition to VMR, we can compare observed
frequencies in the quadrats (Q= number of quadrats)
with expected frequencies:
– a random process (modeled by the Poisson frequency
distribution)
– a clustered process (e.g. one cell with P points, Q-1 cells
with 0 points)
– a uniform process (e.g. each cell has P/Q points)
• The standard Kolmogorov-Smirnov test for comparing
two frequency distributions can then be applied
Kolmogorov-Smirnov (K-S) Test

• The test statistic “D” is simply given by:


D = max [ Cum Obser. Freq – Cum Expect. Freq]

The largest difference (irrespective of sign) between observed


cumulative frequency and expected cumulative frequency

• The critical value at the 5% level is given by:


D (at 5%) = 1.36 where Q is the number of quadrats
sqrt(Q)
Kolmogorov-Smirnov (K-S) Test

• Expected frequencies for a random spatial


distribution are derived from the Poisson frequency
distribution and can be calculated with:
λ
p(0) = e- = 1 / (2.71828P/Q) and p(x) = p(x - 1) * λ /x

Where x = number of points in a quadrat and p(x) = the


probability of x points

P = total number of points Q = number of quadrats


λ = P/Q (the average number of points per quadrat)

• Example
Quadrat sampling

Exhaustive census Random sampling Frequency counts by


--used for secondary --useful in field work Quadrat would be:
(e.g census) data
Census Q = 64 Sampling Q = 38
Number
of points
in Proportio
Quadrat Count Proportion Count n
0 51 0.797 29 0.763
1 11 0.172 8 0.211
2 2 0.031 1 0.026
3 0 0.000 0 0.000

Q = # of quadarts
P = # of points = 15

Quadrats don’t have to be square


--and their size has a big influence

16
Weakness of Quadrat Analysis

• Results may depend on quadrat size /orientation


– test different sizes (or orientations) to determine the effects of
each test on the results
• Measure of dispersion, not really pattern,
– based primarily on the density of points, and not their
arrangement in relation to one another
For example, quadrat analysis cannot
distinguish between these two, obviously
different, patterns
• Results in a single measure for the entire
distribution, so variations within the region are not
recognized (could have clustering locally in some
areas, but not overall)
For example, overall pattern here is
dispersed, but there are some local
clusters 17

You might also like