Appendix 2.1:RDS and TLS An Overview of Probability-Based Sampling Methods For Key Populations.

Slides:



Advertisements
Similar presentations
Claudia Cappa Statistics and Monitoring Section, UNICEF, NY Webinar Series on the Measurement of Child Protection Overview of methods to collect data on.
Advertisements

Survey design. What is a survey?? Asking questions – questionnaires Finding out things about people Simple things – lots of people What things? What people?
Statistics for Managers Using Microsoft® Excel 5th Edition
Sampling Mathsfest Why Sample? Jan8, 2003 Air Midwest Flight 5481 from Douglas International Airport in North Carolina stalled after take off, crashed.
STRATEGIES FOR SAMPLING IDU FOR SURVEILLANCE Tasnim Azim Kolkata April 2007.
Sampling.
Sample Design (Click icon for audio) Dr. Michael R. Hyman, NMSU.
© 2002 Prentice-Hall, Inc.Chap 1-1 Statistics for Managers using Microsoft Excel 3 rd Edition Chapter 1 Introduction and Data Collection.
Who and How And How to Mess It up
Sampling.
Sampling and Sample Size Determination
Sampling Prepared by Dr. Manal Moussa. Sampling Prepared by Dr. Manal Moussa.
The Logic of Sampling. Political Polls and Survey Sampling In the 2000 Presidential election, pollsters came within a couple of percentage points of estimating.
Sampling Adolescents/Young Key Populations (A/YKP) at Risk of HIV Exposure Using Respondent Driven Sampling (RDS) LISA G. JOHNSTON
The Excel NORMDIST Function Computes the cumulative probability to the value X Business Statistics: A First Course, 5e © 2009 Prentice-Hall, Inc
SAMPLING Chapter 7. DESIGNING A SAMPLING STRATEGY The major interest in sampling has to do with the generalizability of a research study’s findings Sampling.
Basic Business Statistics (8th Edition)
Efsa LEARNING PROGRAMME Module 4 - Session 4.5a Non - Probability Sampling Methods.
Sampling Methods.
Chapter 5 Copyright © Allyn & Bacon 2008 This multimedia product and its contents are protected under copyright law. The following are prohibited by law:
Sampling Moazzam Ali.
SAMPLING METHODS Chapter 5.
1 IMPROVING VALIDITY IN WEB SURVEYS WITH HARD-TO-REACH TARGETS: ONLINE RDS METHODOLOGY Aigul Mavletova, PhD National Research University – Higher School.
McGraw-Hill/Irwin McGraw-Hill/Irwin Copyright © 2009 by The McGraw-Hill Companies, Inc. All rights reserved.
C M Clarke-Hill1 Collecting Quantitative Data Samples Surveys Pitfalls etc... Research Methods.
Sampling. Concerns 1)Representativeness of the Sample: Does the sample accurately portray the population from which it is drawn 2)Time and Change: Was.
Chapter Fifteen Sampling and Sample Size. Sampling A sample represents a microcosm of the population you wish to study If the sample is representative.
Sampling: Theory and Methods
1 Research Methods CJ490 Susan Wind Welcome!. 2 Sampling The MOST important part of research process.
Introduction To Research 589(A)
Multiple Indicator Cluster Surveys Survey Design Workshop Sampling: Overview MICS Survey Design Workshop.
SAMPLING.
1 Hair, Babin, Money & Samouel, Essentials of Business Research, Wiley, Learning Objectives: 1.Understand the key principles in sampling. 2.Appreciate.
Sampling Methods.
© 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.
Chapter 7 The Logic Of Sampling. Observation and Sampling Polls and other forms of social research rest on observations. The task of researchers is.
Tahir Mahmood Lecturer Department of Statistics. Outlines: E xplain the role of sampling in the research process D istinguish between probability and.
Sampling Chapter 1. EQT 373 -L2 Why Sample? Selecting a sample is less time-consuming than selecting every item in the population (census). Selecting.
Respondent Driven Sampling (RDS) Part 2 Keith Chan BC CfE.
Chapter 15 Sampling and Sample Size Winston Jackson and Norine Verberg Methods: Doing Social Research, 4e.
5-4-1 Unit 4: Sampling approaches After completing this unit you should be able to: Outline the purpose of sampling Understand key theoretical.
Learning Objectives Explain the role of sampling in the research process Distinguish between probability and nonprobability sampling Understand the factors.
Sociological Research Methods
Basic Business Statistics, 11e © 2009 Prentice-Hall, Inc. Chap 7-1 Chapter 7 Sampling and Sampling Distributions Basic Business Statistics 11 th Edition.
1 Ch. 4, Sampling: How to Select a Few to Represent the Many (Pt. 1) Neumann, pp
Efsa LEARNING PROGRAMME Module 4 - Session 4.5a Sampling.
Basic Business Statistics
Chapter 3 Surveys and Sampling © 2010 Pearson Education 1.
INFO 271B LECTURE 9 COYE CHESHIRE Sampling. Agenda Info 271B 2 Non-probability Sampling Probability Sampling Probability Distributions.
SAMPLING Why sample? Practical consideration – limited budget, convenience, simplicity. Generalizability –representativeness, desire to establish the broadest.
Investigating the Potential of Using Non-Probability Samples Debbie Cooper, ONS.
1 Ch. 4, Sampling: How to Select a Few to Represent the Many (Pt. 1) Neumann, pp
Sampling. Census and Sample (defined) A census is based on every member of the population of interest in a research project A sample is a subset of the.
PRESENTED BY- MEENAL SANTANI (039) SWATI LUTHRA (054)
Sampling Dr Hidayathulla Shaikh. Contents At the end of lecture student should know  Why sampling is done  Terminologies involved  Different Sampling.
Using Surveys to Design and Evaluate Watershed Education and Outreach Day 5 Methodologies for Implementing Mailed Surveys Alternatives to Mailed Surveys.
Session Six Jeff Driskell, MSW, PhD
Sampling From Populations
Marketing Research Aaker, Kumar, Leone and Day Eleventh Edition
Graduate School of Business Leadership
4 Sampling.
Meeting-6 SAMPLING DESIGN
Welcome.
Chapter 7 Sampling Distributions
Sampling.
Business and Management Research
Business Statistics: A First Course (3rd Edition)
Sampling: How to Select a Few to Represent the Many
NON -PROBABILITY SAMPLING
Using Respondent-Drive Sampling to Identify Study Participants
Presentation transcript:

Appendix 2.1:RDS and TLS An Overview of Probability-Based Sampling Methods For Key Populations

Session Overview  Discussion of Sampling Hard to Reach Populations  Presentation, comparison, and discussion of:  Time Location Sampling (TLS)  Respondent Driven Sampling (RDS)

How to Reach Hard to Reach Populations  ….. Let’s Discuss!

What Makes RDS and TLS Unique for Sampling Key Populations? They are probability-based sampling methods  Every respondent has a non-zero, known probability of being selected to participate in the study  With weighting, the sample can be made representative of the target population  Characteristics of the sample are valid estimates of the characteristics of the target population

Time Location Sampling (TLS)  The method is known by several names  Venue Day Time (VDT) sampling  Temporal-spatial sampling (TSS)  Time Venue Sampling (TVS)  Variation of Targeted Sampling (TS)  Venue-Based Sampling (VBS)  The idea is to sample the target population at randomly selected venues where members of the population are known to congregate

Basic Principles of TLS  Approximates random cluster sampling 1. Target population is divided into clusters or groups 2. Groups of individuals are randomly selected for sampling 3. Individuals in selected groups are randomly sampled  In TLS, the sampling clusters are known as venue-day- times (VDTs). VDTs are the:  Places  Day of the Week  And times where target population can be found

Basic Steps for TLS 1. Identify the universe of venues-day-time (VDT) periods attended by the target population 2. Build a sampling frame of VDTs 3. Randomly select VDTs for recruitment events 4. Systematic Sampling: Intercept, consent, interview, and VCT at event 5. Data management 6. Analysis, interpretation 7. Use the data!

Venues-Day-Time (Cluster Sampling Frame) NameAddressPhoneMonTuesWedThursFriSatSun Power Fitness th St 6-10pm West End Video 1984 West End Place pm-12am Café Noir28 Sheppard pm 10pm- 12am 6-10 pm 10 pm- 12am 4 -8pm Men’s Choir 1438 Oak St. N/A8-9pm Creating a complete universe of venues-day-times is a lot of work!

Assumptions of TLS  “Map universe” of all the places where and when the target population can be found  Randomly sampling enough places and times provides everyone in the target population equal chance of being in study  If not equal chance, there are methods to “weight” sample according to who are more or less likely to be at the venues

Ethical Challenges in TLS  Ensuring anonymity  Returning results, ensuring appropriate care  Drawing unwanted attention to safe havens (police, public)  Intoxicated participants  Balancing random sample with outreach and prevention

Chain-Referral (Snowball) Sampling  Recruitment through a network  Participants recruit individuals from their personal network to participate  Strength:  Reaches respondents who avoid public venues and institutions  May have greater coverage because respondents are reached through their social networks  Weakness:  This is a convenience sample rather than a probability sample  Characteristics of the sample are NOT valid estimates of the characteristics of the target population

Respondent-Driven Sampling (RDS)  RDS combines sampling coverage and probability sampling methods  Combines a modified form of chain-referral with a mathematical system for weighting the sample to compensate for its not having been drawn randomly  Based on the premise that peers are better able than outreach workers and researchers to locate and recruit other members of a hidden population  Unlike other chain referral methods, gives valid population point estimates with standard errors

Wave 1 Wave 2 Wave 3 Wave 4 Wave 5 Controlled Recruitment = Penetration / Sample Size Growth

Wave 1 Wave 2 Wave 3 Wave 4 Wave 5 Controlled Recruitment = Penetration / Sample Size Growth

Wave 1 Wave 2 Wave 3 Wave 4 Wave 5 Controlled Recruitment = Penetration / Sample Size Growth

Wave 1 Wave 2 Wave 3 Wave 4 Wave 5 Controlled Recruitment = Penetration / Sample Size Growth

Wave 1 Wave 2 Wave 3 Wave 4 Wave 5

Controlled Recruitment = Penetration / Sample Size Growth Wave 1 Wave 2 Wave 3 Wave 4 Wave 5

RDS Weighting RDS has two types of weighting:  Recruitment pattern weighting  Used to adjust for differential recruitment between groups  Network size weighting  Well-connected individuals tend to be over-sampled because many recruitment paths lead to them

Requirements of RDS  Four requirements:  Document who recruited whom  Recruiter and recruit must know one another  Ration recruitment so a few cannot do all the recruiting (i.e., three recruits/recruiter)  Must ask recruiter and recruit about personal network sizes  If a study does not include these features, it is not RDS

Steps in RDS Identify, Recruit and Interview Seeds Provide seeds info on who and how to recruit Give coupons to each seed Recruits bring valid coupons to the study site; If eligible they are recruited Every new recruit is then asked and given coupons The recruiter is rewarded for every coupon redeemed “Coupon Manager” tracks coupons/links recruiters and peers

RDS Assumption (Heckathorn) 1. Individuals know each other as members of the population in question 2. Target population forms one single large network 3. Report network size accurately 4. Recruit randomly from network 5. Sampling with replacement

Advantages of RDS  Maintains privacy of population  Team can be centrally located  Less logistical needs  Ease of field operations  Moderate formative research/mapping  Target members recruit for you  Reach less visible segments of population  Good external validity  Minimal number of additional questions needed  Computer software available  Generally lower cost

Challenges of RDS  Coupons can be slow in being redeemed  Population must be networked  Must be able to verify group membership  Must track links between recruiters and recruits-coupon management  Appropriate incentive levels  Very difficult to deal with selective non response bias  Analysis is complex

Breakout (20 minutes): TLS vs. RDS Which methodology might be more appropriate for the target population here in the Bahamas? a) Do individuals in the target population frequent venues? b) Could the target population be identified at these venues? c) Could the target population be accessed at these venues without drawing them unwanted attention? d) Might we miss some population groups at these venues? e) Are individuals in the target population well-networked? f) Are there distinct sub-populations? g) Do sub-populations interact with each other? h) Can members of the target population identify each other? i) Will the target population be motivated to participate?

Thank You Working Together to Plan, Implement, and Use HIV Surveillance Systems