Spatial Statistics Point Patterns. Spatial Statistics Increasing sophistication of GIS allows archaeologists to apply a variety of spatial statistics.

Slides:



Advertisements
Similar presentations
CmpE 104 SOFTWARE STATISTICAL TOOLS & METHODS MEASURING & ESTIMATING SOFTWARE SIZE AND RESOURCE & SCHEDULE ESTIMATING.
Advertisements

Objectives (BPS chapter 24)
Zakaria A. Khamis GE 2110 GEOGRAPHICAL STATISTICS GE 2110.
Spatial Statistics II RESM 575 Spring 2010 Lecture 8.
Multivariate Methods Pattern Recognition and Hypothesis Testing.
Statistics II: An Overview of Statistics. Outline for Statistics II Lecture: SPSS Syntax – Some examples. Normal Distribution Curve. Sampling Distribution.
Sample size computations Petter Mostad
BCOR 1020 Business Statistics Lecture 28 – May 1, 2008.
Chapter 26: Comparing Counts. To analyze categorical data, we construct two-way tables and examine the counts of percents of the explanatory and response.
Pattern Statistics Michael F. Goodchild University of California Santa Barbara.
Review for Exam 2 Some important themes from Chapters 6-9 Chap. 6. Significance Tests Chap. 7: Comparing Two Groups Chap. 8: Contingency Tables (Categorical.
IB Math Studies – Topic 6 Statistics.
Point Pattern Analysis
The Chi-Square Test Used when both outcome and exposure variables are binary (dichotomous) or even multichotomous Allows the researcher to calculate a.
Statistical Analysis I have all this data. Now what does it mean?
Copyright © 2013, 2009, and 2007, Pearson Education, Inc. Chapter 12 Analyzing the Association Between Quantitative Variables: Regression Analysis Section.
Inference for regression - Simple linear regression
STA291 Statistical Methods Lecture 27. Inference for Regression.
© 2013 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part.
Basic Statistics. Basics Of Measurement Sampling Distribution of the Mean: The set of all possible means of samples of a given size taken from a population.
The Examination of Residuals. The residuals are defined as the n differences : where is an observation and is the corresponding fitted value obtained.
Topics: Statistics & Experimental Design The Human Visual System Color Science Light Sources: Radiometry/Photometry Geometric Optics Tone-transfer Function.
Chapter 15 Data Analysis: Testing for Significant Differences.
Introduction To Biological Research. Step-by-step analysis of biological data The statistical analysis of a biological experiment may be broken down into.
Statistical Analysis I have all this data. Now what does it mean?
+ Chapter 12: Inference for Regression Inference for Linear Regression.
Why Is It There? Getting Started with Geographic Information Systems Chapter 6.
Spatial Association Defining the relationship between two variables.
The Examination of Residuals. Examination of Residuals The fitting of models to data is done using an iterative approach. The first step is to fit a simple.
Chapter 11 Inference for Tables: Chi-Square Procedures 11.1 Target Goal:I can compute expected counts, conditional distributions, and contributions to.
Sampling Populations Ideal situation - Perfect knowledge Not possible in many cases - Size & cost Not necessary - appropriate subset  adequate estimates.
Copyright © 2014, 2011 Pearson Education, Inc. 1 Chapter 18 Inference for Counts.
Lecture 8 Simple Linear Regression (cont.). Section Objectives: Statistical model for linear regression Data for simple linear regression Estimation.
Inference for Regression Simple Linear Regression IPS Chapter 10.1 © 2009 W.H. Freeman and Company.
1 Chapter 6 – Analysis of mapped point patterns This chapter will introduce methods for analyzing and modeling the spatial distribution of mapped point.
Exploratory Data Analysis Observations of a single variable.
May 2004 Prof. Himayatullah 1 Basic Econometrics Chapter 5: TWO-VARIABLE REGRESSION: Interval Estimation and Hypothesis Testing.
Testing Hypothesis That Data Fit a Given Probability Distribution Problem: We have a sample of size n. Determine if the data fits a probability distribution.
Univariate Linear Regression Problem Model: Y=  0 +  1 X+  Test: H 0 : β 1 =0. Alternative: H 1 : β 1 >0. The distribution of Y is normal under both.
PPA 501 – Analytical Methods in Administration Lecture 6a – Normal Curve, Z- Scores, and Estimation.
Fitting probability models to frequency data. Review - proportions Data: discrete nominal variable with two states (“success” and “failure”) You can do.
1 Regression Analysis The contents in this chapter are from Chapters of the textbook. The cntry15.sav data will be used. The data collected 15 countries’
A Summary of An Introduction to Statistical Problem Solving in Geography Chapter 12: Inferential Spatial Statistics Prepared by W. Bullitt Fitzhugh Geography.
Agresti/Franklin Statistics, 1 of 88 Chapter 11 Analyzing Association Between Quantitative Variables: Regression Analysis Learn…. To use regression analysis.
Point Pattern Analysis Point Patterns fall between the two extremes, highly clustered and highly dispersed. Most tests of point patterns compare the observed.
Statistics What is statistics? Where are statistics used?
Dan Piett STAT West Virginia University Lecture 12.
Methods for point patterns. Methods consider first-order effects (e.g., changes in mean values [intensity] over space) or second-order effects (e.g.,
Probability and Distributions. Deterministic vs. Random Processes In deterministic processes, the outcome can be predicted exactly in advance Eg. Force.
The Practice of Statistics, 5th Edition Starnes, Tabor, Yates, Moore Bedford Freeman Worth Publishers CHAPTER 12 More About Regression 12.1 Inference for.
Statistical Inference Statistical inference is concerned with the use of sample data to make inferences about unknown population parameters. For example,
Chapter 14 – 1 Chi-Square Chi-Square as a Statistical Test Statistical Independence Hypothesis Testing with Chi-Square The Assumptions Stating the Research.
1 1 Slide © 2008 Thomson South-Western. All Rights Reserved Chapter 12 Tests of Goodness of Fit and Independence n Goodness of Fit Test: A Multinomial.
Review: Stages in Research Process Formulate Problem Determine Research Design Determine Data Collection Method Design Data Collection Forms Design Sample.
Objectives (BPS chapter 12) General rules of probability 1. Independence : Two events A and B are independent if the probability that one event occurs.
METU, GGIT 538 CHAPTER V MODELING OF POINT PATTERNS.
The Practice of Statistics, 5th Edition Starnes, Tabor, Yates, Moore Bedford Freeman Worth Publishers CHAPTER 12 More About Regression 12.1 Inference for.
Statistical principles: the normal distribution and methods of testing Or, “Explaining the arrangement of things”
GIS and Spatial Analysis1 Summary  Parametric Test  Interval/ratio data  Based on normal distribution  Difference in Variances  Differences are just.
Statistical Decision Making. Almost all problems in statistics can be formulated as a problem of making a decision. That is given some data observed from.
Goodness-of-Fit A test of whether the distribution of counts in one categorical variable matches the distribution predicted by a model is called a goodness-of-fit.
BINARY LOGISTIC REGRESSION
Chapter 4. Inference about Process Quality
CHAPTER 12 More About Regression
CHAPTER 12 More About Regression
Statistics II: An Overview of Statistics
CHAPTER 12 More About Regression
Chapter 14.1 Goodness of Fit Test.
Quadrat sampling & the Chi-squared test
Presentation transcript:

Spatial Statistics Point Patterns

Spatial Statistics Increasing sophistication of GIS allows archaeologists to apply a variety of spatial statistics to their data –Predictive Modeling –Intra-site Spatial Analysis

Predictive Modeling 1 Goal is to predict where sites will be located Usually involves two samples: known sites, surveyed areas where sites have not been found For each group, we collect data: slope, aspect, distance to water, soil, vegetation zone, etc

Predictive Modeling 2 Must convert nominal scales to dichotomies or an interval scale of some kind Analysis by logistic regression or discriminant functions For new areas we compute the probability that a site will be found

Predictive Modeling 3 Problems: –Usually purely inductive –Goal is management not anthropology –Independent variables are those gathered for other reasons

Intra-Site Spatial Analyses Nearest Neighbor –Can use on any point plot data (sites, houses, artifacts) –Find distance to nearest neighbor for each item –Mean nearest neighbor compared to expected value (random distribution)

Nearest Neighbor If observed mean distance is significantly less than expected, the points are clustered If the mean distance is significantly more than expected, the points are evenly spread But problems with borders

Mean Distance = 1.04 Expected Dist = 0.81 Probability = * R = Mean/Exp = 1.29 Mean Distance =.74 Expected Dist = 0.63 Probability = R = Mean/Exp = 1.18 Mean Distance = 0.52 Expected Dist = 0.78 Probability = * R = Mean/Exp = 0.67 ClusteredRandomRegular

Point Patterns in R Package spatstat Create a ppp object (point process) Plotting and analytical tools are extensive

# Fix duplicate coordinates by adding 1-2 mm to each load("C:/Users/Carlson/Documents/Courses/Anth642/R/Data/BTF3a.RData") Win3a <- data.frame(x=c(982,982,983,983,984.5,985,985,987,987,986.2, 985,985,984.5,984,983.5,983,982.7,982.5), y=c(1015.5,1021,1021,1022,1022,1021.3,1018,1018,1017.6,1017, 1017,1016.9,1016.8,1016.6,1016.3,1016,1015.6,1015.5)) # coordinates must be counterclockwise Win3a <- Win3a[order(as.numeric(rownames(Win3a)), decreasing=TRUE),] library(spatstat) BTF3a.p <- ppp(BTF3a$East, BTF3a$North, window=owin(poly=Win3a, unitname=c("meter", "meters")), marks=BTF3a$Type) summary(BTF3a.p) plot(BTF3a.p, main="Bifacial Thinning Flakes", cex=.75, chars=16, cols=c("red", "blue", "green")) legend("topright", c("BTF", "CBT", "NCBT"), pch=16, col=c("red", "blue", "green")) plot(split(BTF3a.p), main="Bifacial Thinning Flakes") mtext("BTF = Fragments CBT = Cortex NCBT = No Cortex", side=1)

Marked planar point pattern: 230 points Average intensity 12.8 points per square meter Multitype: frequency proportion intensity BTF CBT NCBT Window: polygonal boundary single connected closed polygon with 18 vertices enclosing rectangle: [982, 987]x[1015.5, 1022]meters Window area = square meters Unit of length: 1 meter

plot(982, 982, xlim=c(982, 987), ylim=c(1015, 1022), main="Bifacial Thinning Flakes", xlab="", ylab="", axes=FALSE, asp=1, type="n") contour(density(BTF3a.p, adjust=.5), add=TRUE) polygon(Win3a) points(BTF3a.p, pch=20, cex=.75) plot(density(BTF3a.p, adjust=.5), main="Bifacial Thinning Flakes") polygon(Win3a, lwd=2) points(BTF3a.p, pch=20, cex=.75) plot(density(BTF3a.p, adjust=.5), main="Bifacial Thinning Flakes") polygon(Win3a, lwd=2) points(BTF3a.p, pch=20, cex=.75) windows(10, 5) V <- split(BTF3a.p) A <- lapply(V, density, adjust=.5) plot(as.listof(A), main="Bifacial Thinning Flakes")

Tab <- quadratcount(BTF3a.p, xbreaks=982:987, ybreaks=1015:1022) quadrat.test(Tab) # Warning: Some expected counts are small; chi^2 approximation may # be inaccurate # Chi-squared test of CSR using quadrat counts # data: # X-squared = , df = 19, p-value < 2.2e-16 # Quadrats: 20 tiles (levels of a pixel image) E <- kstest(BTF3a.p, "x") plot(E) N <- kstest(BTF3a.p, "y") plot(N) E N

Spatial Kolmogorov-Smirnov test of CSR data: covariate 'x' evaluated at points of 'BTF3a.p' and transformed to uniform distribution under CSRI D = , p-value = alternative hypothesis: two-sided Spatial Kolmogorov-Smirnov test of CSR data: covariate 'y' evaluated at points of 'BTF3a.p' and transformed to uniform distribution under CSRI D = , p-value < 2.2e-16 alternative hypothesis: two-sided

Gest(BTF3a.p) plot(Gest(BTF3a.p), main="Nearest Neighbor Function G") # Above poisson is clustered, below is regular plot(envelope(BTF3a.p, Gest, nsim=39, rank=1), main="Nearest Neighbor Envelope") # The test is constructed by choosing a fixed value of r, and rejecting the null # hypothesis if the observed function value lies outside the envelope at this # value of r. This test has exact significance level alpha = 2 * nrank/(1 + nsim). plot(envelope(BTF3a.p, Gest, nsim=19, rank=1, global=TRUE), main="Global Nearest Neighbor Envelope") # The estimated K function for the data transgresses these limits if and only if # the D-value for the data exceeds Dmax. Under H0 this occurs with probability # 1/(M + 1). Thus, a test of size 5% is obtained by taking M = 19. plot(alltypes(BTF3a.p, "G")) plot(alltypes(BTF3a.p, "Gdot"))