Random vs. systematic sampling J. Gallego, MARS AGRI4CAST.

Slides:



Advertisements
Similar presentations
1 ESTIMATION IN THE PRESENCE OF TAX DATA IN BUSINESS SURVEYS David Haziza, Gordon Kuromi and Joana Bérubé Université de Montréal & Statistics Canada ICESIII.
Advertisements

It is 2 o C The temperature drops by 3 degrees What temperature is it now? -1 o C.
Definitions Periodic Function: f(t +T) = f(t)t, (Period T)(1) Ex: f(t) = A sin(2Πωt + )(2) has period T = (1/ω) and ω is said to be the frequency (angular),
Regional Impact Assessment AgMIP SSA Kickoff Workshop John Antle AgMIP Regional Econ Team Leader 1 Accra, Ghana Sept
Estimating a Population Variance
Chapter 10 Parameter Estimation. Alternatives to Hypothesis Testing? Some people say that the analysis I just presented, as well as some other things,
Sampling Strategy for Establishment Surveys International Workshop on Industrial Statistics Beijing, China, 8-10 July 2013.
Correlation and Autocorrelation
MISUNDERSTOOD AND MISUSED
Dr. Chris L. S. Coryn Spring 2012
Chapter 8 Estimation: Single Population
ISSUES RELATED TO SAMPLING Why Sample? Probability vs. Non-Probability Samples Population of Interest Sampling Frame.
Ratio estimation with stratified samples Consider the agriculture stratified sample. In addition to the data of 1992, we also have data of Suppose.
Sampling Methods for Estimating Accuracy and Area of Land Cover Change.
Mathematical Statistics Lecture Notes Chapter 8 – Sections
Inferential Statistics
1 JRC – Ispra Area frames for land cover estimation: Improving the European LUCAS survey Javier Gallego Jacques Delincé.
United Nations Workshop on the 2010 World Programme on Population and Housing Censuses: Census Evaluation and Post Enumeration Surveys, Amman, Jordan,
Target population-> Study Population-> Sample 1WWW.HIVHUB.IR Target Population: All homeless in country X Study Population: All homeless in capital shelters.
Sampling Design  M. Burgman & J. Carey Types of Samples Point samples (including neighbour distance samples) Transects line intercept sampling.
Mapping the future Converting storylines to maps Nasser Olwero GMP, Bangkok April
Analysis of Monte Carlo Integration Fall 2012 By Yaohang Li, Ph.D.
Definitions Observation unit Target population Sample Sampled population Sampling unit Sampling frame.
Near East Regional Workshop - Linking Population and Housing Censuses with Agricultural Censuses. Amman, Jordan, June 2012 Improving Efficiency.
STA Lecture 161 STA 291 Lecture 16 Normal distributions: ( mean and SD ) use table or web page. The sampling distribution of and are both (approximately)
CRIM 483 Measuring Variability. Variability  Variability refers to the spread or dispersion of scores  Variability captures the degree to which scores.
Lecture 14 Dustin Lueker. 2  Inferential statistical methods provide predictions about characteristics of a population, based on information in a sample.
Basic Statistical Concepts  M. Burgman & J. Carey 2002.
The Role of Over-Sampling of the Wealthy in the SCF Arthur B. Kennickell Federal Reserve Board Opinions are those of the presenter alone and do not necessarily.
Support to the Global Forest Resource Assessment process Organisations: Food and Agriculture Organization of the United Nations (FAO) + European Commission.
May 4 th (4:00pm) Multiple choice (50 points) Short answer (50 points)
Variability.  Reflects the degree to which scores differ from one another  Usually in reference to the mean value  A measure of the central tendency.
The Semivariogram in Remote Sensing: An Introduction P. J. Curran, Remote Sensing of Environment 24: (1988). Presented by Dahl Winters Geog 577,
United Nations Regional Workshop on the 2010 World Programme on Population and Housing Censuses: Census Evaluation and Post Enumeration Surveys, Bangkok,
Chapter 7 The Logic Of Sampling The History of Sampling Nonprobability Sampling The Theory and Logic of Probability Sampling Populations and Sampling Frames.
Development of an EnKF to estimate CO 2 fluxes from realistic distributions of X CO2 Liang Feng, Paul Palmer
Copyright 2010, The World Bank Group. All Rights Reserved. Part 1 Sample Design Produced in Collaboration between World Bank Institute and the Development.
Area estimation in the MARS project. A summary history J. Gallego,– MARS AGRI4CAST.
Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc Chapter 10 Introduction to Estimation.
Geo479/579: Geostatistics Ch4. Spatial Description.
Properties of Estimators Statistics: 1.Sufficiency 2.Un-biased 3.Resistance 4.Efficiency Parameters:Describe the population Describe samples. But we use.
Data Collection & Sampling Dr. Guerette. Gathering Data Three ways a researcher collects data: Three ways a researcher collects data: By asking questions.
NTTS 2011 Brussels February 22, Joint Research Centre (JRC) Sampling Very High Resolution Images for Area Estimation
Lecture 6 Your data and models are never perfect… Making choices in research design and analysis that you can defend.
Autoregressive (AR) Spectral Estimation
Sampling Theory and Some Important Sampling Distributions.
Contact © European Union, 2012 Use of low-resolution satellites for permanent pasture yield estimation at regional scale. Lorenzo.
LUCAS 2006 J. Gallego, MARS AGRI4CAST. Sampling scheme Adaptation of the Italian AGRIT First phase: Systematic sampling of unclustered points (single.
Sampling Designs Outline
Chapter 8 Estimation ©. Estimator and Estimate estimator estimate An estimator of a population parameter is a random variable that depends on the sample.
Rotating Panels – Especially with Regards to Business Statistics Peter Tibert Stoltze Statistical Methodology Forum for Sample Survey and Estimation April.
United Nations Regional Workshop on the 2010 World Programme on Population and Housing Censuses: Census Evaluation and Post Enumeration Surveys, Addis.
Survey sampling Outline (1 hr) Survey sampling (sources of variation) Sampling design features Replication Randomization Control of variation Some designs.
Heights  Put your height in inches on the front board.  We will randomly choose 5 students at a time to look at the average of the heights in this class.
Lecture 13 Dustin Lueker. 2  Inferential statistical methods provide predictions about characteristics of a population, based on information in a sample.
Exposure Prediction and Measurement Error in Air Pollution and Health Studies Lianne Sheppard Adam A. Szpiro, Sun-Young Kim University of Washington CMAS.
Introduction For inference on the difference between the means of two populations, we need samples from both populations. The basic assumptions.
Lecture 19: Spatial Interpolation II
Sampling scheme for LUCAS 2015
الأستاذ المساعد بقسم المناهج وطرق التدريس
2. Stratified Random Sampling.
Workshop on Area Sampling Frame Key features of area sampling frame
Chapter 8: Weighting adjustment
Sampling scheme for LUCAS 2015
Statistical Inference
Item 5.1 of the agenda Preliminary results of LUCAS 2009 Part III
The European Statistical Training Programme (ESTP)
STA 291 Spring 2008 Lecture 13 Dustin Lueker.
Chapter 8 Estimation.
Presentation transcript:

Random vs. systematic sampling J. Gallego, MARS AGRI4CAST

Geographic systematic sampling Positive More efficient than random sampling if the spatial autocorrelation is a decreasing function of the distance More difficult to manipulate: it gives more confidence Important if the results are politically sensitive

Geographic systematic sampling (2) Negative It may introduce a distortion in the variance if the landscape is repetitive Chess board effect if the size and orientation of the cells is the same as the sampling step This can be an issue in small pilot regions Unlikely in large complex regions There is no unbiased estimator of the variance The usual variance estimators are conservative (overestimate the variance)

Variance estimation in LUCAS Usual variance estimator for two-phase random sampling (incomplete stratification) The estimated variance of Y in stratum h can be written This estimator is strongly biased for systematic sampling The bias is reduced with a local estimator of the variance of Y:

Example of sophisticated sampling scheme TREES-2: estimation of tropical deforestation Very efficient in terms of variance, but strongly attacked in the political forum

Alternative by FAO for general land cover monitoring One tile of 10x10 or 20x20 km each lat-long degree Half-rate above 60º Problem of bias Less problematic in tropical countries