Smoothed Maps. This is a Smoothed Map Ideas Behind Smoothing To avoid arbitrary political boundaries To adjust unstable estimates towards a global mean.

Slides:



Advertisements
Similar presentations
Sources and effects of bias in investigating links between adverse health outcomes and environmental hazards Frank Dunstan University of Wales College.
Advertisements

Global Clustering Tests. Tests for Spatial Randomness H 0 : The risk of disease is the same everywhere after adjustment for age, gender and/or other covariates.
Smoothed Seismicity Rates Karen Felzer USGS. Decision points #1: Which smoothing algorithm to use? National Hazard Map smoothing method (Frankel, 1996)?
Statistical approaches for detecting clusters of disease. Feb. 26, 2013 Thomas Talbot New York State Department of Health Bureau of Environmental and Occupational.
BEN ANDERSON PROJECT MANAGER UNIVERSITY OF LOUISVILLE CENTER FOR HAZARDS RESEARCH AND POLICY DEVELOPMENT Using Dasymetric Mapping.
3.3 Toward Statistical Inference. What is statistical inference? Statistical inference is using a fact about a sample to estimate the truth about the.
 Statistical approaches for detecting unexplained clusters of disease.  Spatial Aggregation Thomas Talbot New York State Department of Health Environmental.
Business Statistics - QBM117
Bayesian Methods for Monitoring Public Health Surveillance Data Owen Devine Division of STD Prevention National Center for HIV, STD and TB Prevention Centers.
Sample Size I: 1 Sample Size Determination In the Context of Estimation.
1 COMM 301: Empirical Research in Communication Kwan M Lee Lect5_1.
Spatial Statistics for Cancer Surveillance Martin Kulldorff Harvard Medical School and Harvard Pilgrim Health Care.
Mapping Rates and Proportions. Incidence rates Mortality rates Birth rates Prevalence Proportions Percentages.
Geographic Information Science
A Very spatial Presentation. ANCIENT BABYLONIAN CLAY TABLETS DEPICT THE EARTH AS A FLAT CIRCULAR DISK EARLIEST DIRECT EVIDENCE OF MAPPING COMES FROM THE.
University of Wisconsin-Milwaukee Geographic Information Science Geography 625 Intermediate Geographic Information Science Instructor: Changshan Wu Department.
Accuracy Assessment. 2 Because it is not practical to test every pixel in the classification image, a representative sample of reference points in the.
The Spatial Scan Statistic. Null Hypothesis The risk of disease is the same in all parts of the map.
01/20141 EPI 5344: Survival Analysis in Epidemiology Quick Review and Intro to Smoothing Methods March 4, 2014 Dr. N. Birkett, Department of Epidemiology.
Adaptive Kernel Density in Demographic Analysis Richard Lycan Institute on Aging Portland State University.
Spatial Statistics Applied to point data.
1/26/09 1 Community Health Assessment in Small Populations: Tools for Working With “Small Numbers” Region 2 Quarterly Meeting January 26, 2009.
EG3246 Spatial Science & Health Introduction to Basic Epidemiology Dr Mark Cresswell.
Term 4, 2005BIO656 Multilevel Models1 Hierarchical Models for Pooling: A Case Study in Air Pollution Epidemiology Francesca Dominici.
National Institute for Public Health and the Environment The Dutch RIF Experiences and possibilities.
Thomas Talbot Chief, Environmental Health Surveillance Section NYS Department of Health April 18, 2013.
Urbanisation and spatial inequalities in health in Brazil and India
DSc 3120 Generalized Modeling Techniques with Applications Part II. Forecasting.
Extending Spatial Hot Spot Detection Techniques to Temporal Dimensions Sungsoon Hwang Department of Geography State University of New York at Buffalo DMGIS.
2006 Summer Epi/Bio Institute1 Module IV: Applications of Multi-level Models to Spatial Epidemiology Instructor: Elizabeth Johnson Lecture Developed: Francesca.
Measures of Disease Frequency COURTNEY D. LYNCH, PhD MPH ASSISTANT PROFESSOR DEPT. OF OBSTETRICS & GYNECOLOGY
Applications of optimal control and EnKF to Flow Simulation and Modeling Florida State University, February, 2005, Tallahassee, Florida The Maximum.
Taking ‘Geography’ Seriously: Disaggregating the Study of Civil Wars. John O’Loughlin and Frank Witmer Institute of Behavioral Science University of Colorado.
1 ◄ ◄ Maternal and Infant Health data for California Choose one vital records indicator:  Preterm birth (birth prior to 37 weeks of pregnancy among singletons)
Ripley K – Fisher et al.. Ripley K - Issues Assumes the process is homogeneous (stationary random field). Ripley K was is very sensitive to study area.
EXAMPLES OF GRAPHS FOUND IN THE MEDIA Each graph was found on the website for the National Center for Health Statistics
A short introduction to epidemiology Chapter 9: Data analysis Neil Pearce Centre for Public Health Research Massey University Wellington, New Zealand.
Targeting of Public Spending Menno Pradhan Senior Poverty Economist The World Bank office, Jakarta.
L15 – Spatial Interpolation – Part 1 Chapter 12. INTERPOLATION Procedure to predict values of attributes at unsampled points Why? Can’t measure all locations:
Methods for point patterns. Methods consider first-order effects (e.g., changes in mean values [intensity] over space) or second-order effects (e.g.,
Point Pattern Analysis
Spatial Smoothing and Multiple Comparisons Correction for Dummies Alexa Morcom, Matthew Brett Acknowledgements.
Chapter 6 Conducting & Reading Research Baumgartner et al Chapter 6 Selection of Research Participants: Sampling Procedures.
Model Fusion and its Use in Earth Sciences R. Romero, O. Ochoa, A. A. Velasco, and V. Kreinovich Joint Annual Meeting NSF Division of Human Resource Development.
BPS - 3rd Ed. Chapter 191 Comparing Two Proportions.
A Temporal Filtering Algorithm to Reconstruct Daily Albedo Series Based on GLASS Albedo product Nanfeng Liu 1,2, Qiang Liu 1,2, Lizhao Wang 2, Jianguang.
Statistical Significance: Tests for Spatial Randomness.
01/20151 EPI 5344: Survival Analysis in Epidemiology Hazard March 3, 2015 Dr. N. Birkett, School of Epidemiology, Public Health & Preventive Medicine,
Quantifying Health Benefits with Local Scale Air Quality Modeling Presentation to CMAS October 7 th, 2008 Bryan Hubbell, Karen Wesson and Neal Fann U.S.
1 Part09: Applications of Multi- level Models to Spatial Epidemiology Francesca Dominici & Scott L Zeger.
Modeling the Impacts of Forest Carbon Sequestration on Biodiversity Andrew J. Plantinga Department of Agricultural and Resource Economics Oregon State.
1 Module IV: Applications of Multi-level Models to Spatial Epidemiology Francesca Dominici & Scott L Zeger.
L2 Sampling Exercise A possible solution.
Global burden of diseases
Figure 3.1. Lead poisoning and risk factors for Durham County block groups. From Health and Medical Geography, 4th edition, by Emch, Root, & Carrel. Copyright.
Spatial analysis Measurements - Points: centroid, clustering, density
Dept of Biostatistics, Emory University
Point-pattern analysis of Nashville, TN robberies: It’s all about that kernel Ingrid Luffman and Andrew Joyner, Department of Geosciences, East Tennessee.
Mary Charlton & Amanda kahl Iowa Cancer Registry
URBDP 422 Urban and Regional Geo-Spatial Analysis
Figure 3 Life expectancy at birth in all countries included
Geographies of Poverty:
Annie-Claire Nadeau-Fredette
Sampling Distribution of a Sample Proportion
Spatial mapping of acute diarrheal disease using GIS and estimation of relative risk using empirical Bayes approach  Velusamy Saravana Kumar, Shanmugasundaram.
Chapter 7: Introduction to Sampling Distributions
Xin-She Yang, Nature-Inspired Optimization Algorithms, Elsevier, 2014
Sampling Distributions
Incidence and Mortality of Childhood Cancer in China
Bayesian Mapping of Cancer Mortality in Japan: A Small Area Analysis
Presentation transcript:

Smoothed Maps

This is a Smoothed Map

Ideas Behind Smoothing To avoid arbitrary political boundaries To adjust unstable estimates towards a global mean To borrow strength from neighboring areas

Spatial Smoothing Techniques Rates/RRs in disjoint areas such as counties Empirical Bayes Headbanging Spatial Filters / Kernel Smoothers All techniques may be used for rates, proportions or relative risks. The latter also for probabilities.

Empirical Bayes Global smoothers adjust each area estimate towards a global mean. Local smoothers adjust each area estimate up or down depending on the data in neighboring areas. Review: Devine OJ, Louis TA, Halloran ME. Empirical Bayes methods for stabilizing incidence rates before mapping. Epidemiology, 5: , 1994.

Headbanging Adjusts estimates in an area by borrowing strength from neighbouring areas. Hansen KM. Headbanging: Robust smoothing in the plane. IEEE Transactions on Geoscience and Remote Sensing, 29: , Mungiole M, Pickle LW, Simonson KH. Application of a weighted head-banging algorithm to mortality data maps. Statistics in Medicine, 18:3201, 1999.

Pickle et al: United States Mortality Atlas

Spatial Filters / Kernel Smoothers Calculates rates / RRs in multiple overlapping circular areas. The rate / RRs for each circle is depicted at the center of that circle.

x x x x x x x x x x x x x x x x x x x

Spatial Filters / Kernel Smoothers Larger Circles = More smoothing and more stable estimates Smaller Circles = Less smoothing but higher geographical resolution

Spatial Filters / Kernel Smoothers Circles of fixed geographical size provides equal geographical resolution across the map. Circles of fixed population size provides equally reliable estimates across the map.

Spatial Filters / Kernel Smoothers Rather than a simple circle, one can use a kernel with a higher weight in the center and gradually lower weights further away as one moves away from the center.

Smoothed Probability Maps Provides contours of p-values

Low Birth Weight in Des Moines, Iowa Rushton & Lolonis Statistics in Medicine 1996

Spatial Filters / Kernel Smoothers Kafadar K. Smoothing geographical data, particularly rates of disease. Statistics in Medicine, 15: , Rushton G, Lolonis P. Exploratory spatial analysis of birth defect rates in an urban population. Statistics in Medicine, 15: , Talbot TO, et al. Evaluation of spatial filters to create smoothed maps of health data. Statistics in Medicine, 19: , References

Exploratory/Descriptive Techniques Maps of rates or relative risks Probability maps Smoothed rates or relative risks Smoothed probability maps

Maps of rates and probability maps are very useful for descriptive purposes Problem Maps of Rates: No statistical testing Probability Maps: Multiple testing Solution Tests for Spatial Randomness: One test