Meta-analysis: basic principles and methods

Similar documents
Bird Strike Damage Rates for Selected Commercial Jet Aircraft Todd Curtis, The AirSafe.com Foundation

Kristina Ricks ISYS 520 VBA Project Write-up Around the World

Thanksgiving Holiday Period Traffic Fatality Estimate, 2017

GEOGRAPHY OF GLACIERS 2

Visitor Use Computer Simulation Modeling to Address Transportation Planning and User Capacity Management in Yosemite Valley, Yosemite National Park

Validation of Runway Capacity Models

Is Occupation as Air Transport Pilot a Stroke Risk?

Quantitative Analysis of the Adapted Physical Education Employment Market in Higher Education

Directional Price Discrimination. in the U.S. Airline Industry

Methodology and coverage of the survey. Background

Cross-sectional time-series analysis of airspace capacity in Europe

Airspace Complexity Measurement: An Air Traffic Control Simulation Analysis

NAPA VALLEY VISITOR INDUSTRY 2014 Economic Impact Report

NAPA VALLEY VISITOR INDUSTRY 2012 Economic Impact Report

Measuring Productivity for Car Booking Solutions

Risk Assessment in Winter Backcountry Travel

Demand, Load and Spill Analysis Dr. Peter Belobaba

Designing computer based training programs. Sam Chan Research Scientist. Posit Science Corporation, San Francisco, CA.

JULIAN DEAN, PETER IVANOV, SEAN COLLINS AND MARIA GARCIA MIRANDA

FIXED-SITE AMUSEMENT RIDE INJURY SURVEY, 2015 UPDATE. Prepared for International Association of Amusement Parks and Attractions Alexandria, VA

NAPA VALLEY VISITOR INDUSTRY 2016 Economic Impact Report

2015 Travel Survey. for the States of Guernsey Commerce & Employment Department RESEARCH REPORT ON Q1 2015

UK household giving new results on regional trends

Commissioned by: Economic Impact of Tourism. Stevenage Results. Produced by: Destination Research

Economic Impact of Tourism. Hertfordshire Results. Commissioned by: Visit Herts. Produced by:

Foodborne Diseases Active Surveillance Network (FoodNet)

Unit 6: Probability Plotting

Testing whether eco certifications sell tourism services

A Primer on Fatigue Damage Spectrum for Accelerated and Reliability Testing

SURVEY OF U3A MEMBERS (PART 1)

A stated preference survey for airport choice modeling.

Market power and its determinants of the Chinese airline industry

Name: Date: Period: Samples and Populations Investigation 1.1: Comparing Wait Times

LATENCY OF TOURISM PERMITS IN THE GREAT BARRIER REEF MARINE PARK AUDIT FOR THE YEAR 2000

Produced by: Destination Research Sergi Jarques, Director

HOW TO IMPROVE HIGH-FREQUENCY BUS SERVICE RELIABILITY THROUGH SCHEDULING

The Economic Contributions of Agritourism in New Jersey

1 Replication of Gerardi and Shapiro (2009)

FIXED-SITE AMUSEMENT RIDE INJURY SURVEY FOR NORTH AMERICA, 2016 UPDATE

An Assessment on the Cost Structure of the UK Airport Industry: Ownership Outcomes and Long Run Cost Economies

Baseline results of the 5 th Wild Dog & 3 rd Cheetah Photographic Census of Greater Kruger National Park

Predicting a Dramatic Contraction in the 10-Year Passenger Demand

Hickerson, B., & Henderson, K. A. (2010, May/June). Children s summer camp-based physical activity. Camping Magazine, 83(3),

REPORT 2014/065 INTERNAL AUDIT DIVISION. Audit of air operations in the United. Nations Assistance Mission in Afghanistan

Measures of Urban Trail Use in Minneapolis

Quantile Regression Based Estimation of Statistical Contingency Fuel. Lei Kang, Mark Hansen June 29, 2017

Somchanok Tiabtiamrat* and Supachok Wiriyacosol ABSTRACT

An Econometric Study of Flight Delay Causes at O Hare International Airport Nathan Daniel Boettcher, Dr. Don Thompson*

Analysis of Runway Incursion Data

Transport Performance and the Data Clubs Approach. Richard Anderson ESRC International Public Service Rankings 13 th December 2005

Demand Shifting across Flights and Airports in a Spatial Competition Model

Produced by: Destination Research Sergi Jarques, Director

Conceptual Design of a National Database of Air Passenger Survey Data

The Seychelles National Meteorological Services. Mahé Seychelles

Paper presented to the 40 th European Congress of the Regional Science Association International, Barcelona, Spain, 30 August 2 September, 2000.

An Exploration of LCC Competition in U.S. and Europe XINLONG TAN

Analysis of Air Transportation Systems. Airport Capacity

The Effectiveness of JetBlue if Allowed to Manage More of its Resources

IPSOS / REUTERS POLL DATA Prepared by Ipsos Public Affairs

DRONE SIGHTINGS ANALYSIS AND RECOMMENDATIONS

Revisiting the Relationship between Competition and Price Discrimination

PREFERENCES FOR NIGERIAN DOMESTIC PASSENGER AIRLINE INDUSTRY: A CONJOINT ANALYSIS

Water Quality Trends for Conscience Bay

Revalidation: Recommendations from the Task and Finish Group

Multiple comparison of green express aviation network path optimization research

Discriminate Analysis of Synthetic Vision System Equivalent Safety Metric 4 (SVS-ESM-4)

Statistical Evaluation of Seasonal Effects to Income, Sales and Work- Ocupation of Farmers, the Apples Case in Prizren and Korça Regions

Technical Documentation Wind Turbine Generator Systems with LNTE 50 Hz and 60 Hz

FIXED-SITE AMUSEMENT RIDE INJURY SURVEY, 2005 UPDATE. Prepared for International Association of Amusement Parks and Attractions Alexandria, Virginia

Sharpe Performance by Australian Property

The Traffic Management Act (TMA) 2004 and roadworks; and lane rental under the New Roads and Streetworks Act (1991) in England

Fewer air traffic delays in the summer of 2001

International Passenger Survey (IPS) Methodology. May 2017

STANDARDS MAP Basic Programs 1 and 2 English Language Arts Content Standards Grade Five

2013 Travel Survey. for the States of Guernsey Commerce & Employment Department RESEARCH REPORT ON Q1 2013

An Analytical Approach to the BFS vs. DFS Algorithm Selection Problem 1

Specialty Cruises. 100% Tally and Strip Cruises

Corporate Productivity Case Study

Water Quality Trends for Patchogue Bay

EUROPEANS EXPERIENCE WITH USING SHIPS AND PERCEPTIONS OF MARITIME SAFETY

ST 507 Practice Exam 1

Time-Space Analysis Airport Runway Capacity. Dr. Antonio A. Trani. Fall 2017

Potential of CO 2 retrieval from IASI

Solid waste generation and disposal by Hotels in Coimbatore City

Estimates of the Economic Importance of Tourism

Produced by: Destination Research Sergi Jarques, Director

HEATHROW COMMUNITY NOISE FORUM. Sunninghill flight path analysis report February 2016

Commissioned by: Visit Kent. Economic Impact of Tourism. Canterbury Results. Produced by: Destination Research

A Statistical Method for Eliminating False Counts Due to Debris, Using Automated Visual Inspection for Probe Marks

Produced by: Destination Research Sergi Jarques, Director

Produced by: Destination Research Sergi Jarques, Director

ANALYSIS OF THE CONTRIUBTION OF FLIGHTPLAN ROUTE SELECTION ON ENROUTE DELAYS USING RAMS

MECHANICAL HARVESTING SYSTEM AND CMNP EFFECTS ON DEBRIS ACCUMULATION IN LOADS OF CITRUS FRUIT

oneworld alliance: The Commission s investigation under Article 101 TFEU

Pre-9/11 and Post-9/11 Customer Service Outcomes at U.S. Airports for International Travelers to the U.S.

Figure 1.1 St. John s Location. 2.0 Overview/Structure

Analysis of Transit Fare Evasion in the Rose Quarter

Notes largely based on Statistical Methods for Reliability Data by W.Q. Meeker and L. A. Escobar, Wiley, 1998 and on their class notes.

Royal Parks Stakeholder Research Programme 2014

Making the most of school-level per-student spending data

Transcription:

Meta-analysis: basic principles and methods Bianca L De Stavola and Tim Collier LSHTM bianca.destavola@lshtm.ac.uk & tim.collier@lshtm.ac.uk 27 th November, 2012 Bianca L De Stavola and Tim Collier LSHTM /Meta-analysis: basic principles and methods 1/20

Contents 1 Introduction 2 Pooling effects 3 Fixed effect meta-analysis 4 Random effects meta-analysis 5 How to do it in Stata 6 Risk of Bias 7 Conclusions 8 References Bianca L De Stavola and Tim Collier LSHTM /Meta-analysis: basic principles and methods 2/20

Systematic reviews It all starts here... Briefly, from Alma s lecture: Define question, population, outcome, exposure, study design(s) Define search strategy Perform search Extract data (Alternatively: contact authors and collate individual data) Display and summarize findings: meta-analysis Bianca L De Stavola and Tim Collier LSHTM /Meta-analysis: basic principles and methods 3/20

Systematic reviews It all starts here... Briefly, from Alma s lecture: Define question, population, outcome, exposure, study design(s) Define search strategy Perform search Extract data (Alternatively: contact authors and collate individual data) Display and summarize findings: meta-analysis Bianca L De Stavola and Tim Collier LSHTM /Meta-analysis: basic principles and methods 3/20

Meta-analysis Meta-analysis is a two-stage approach: 1 study specific estimates of effect, ˆβ s, and precision, ŝe( ˆβ s ), No. Study ˆβ s ŝe( ˆβ s ) 1 MRC NSHD (UK) 0.093 0.113 2 HBCS I (Helsinki) 0.103 0.077 3 PSWG (Gothenburg) 0.201 0.142...... S examination of heterogeneity 2 Overall summary Bianca L De Stavola and Tim Collier LSHTM /Meta-analysis: basic principles and methods 4/20

Meta-analysis Meta-analysis is a two-stage approach: 1 study specific estimates of effect, ˆβ s, and precision, ŝe( ˆβ s ), No. Study ˆβ s ŝe( ˆβ s ) 1 MRC NSHD (UK) 0.093 0.113 2 HBCS I (Helsinki) 0.103 0.077 3 PSWG (Gothenburg) 0.201 0.142...... S 2 examination of heterogeneity 3 Overall summary Bianca L De Stavola and Tim Collier LSHTM /Meta-analysis: basic principles and methods 5/20

An example Birth weight and breast cancer incidence Forest plot of rate relative risks (ES) and 95% confidence intervals Study ID ES (95% CI) MRC NSHD (UK) 2000 HBCS I (Helsinki) 2001 PSWG (Gothenburg) 2001 CSHRR (Copenhagen) 2003 UBCoS Multigen (Uppsala) 2003 SOUHCB(Trondheim) 2005 NCI DES (US) 2006 Aberdeen Children of the 1950s (Aberdeen) UP EPIC (Norfolk) UP HBCS II (Helsinki) UP HBCS III (Helsinki) UP SYFBC (Sweden) UP UKWCS (UK) 2007 MDC Study (Malmo) 2004 SPNFBC (Uppsala-Orebro) 1997 NYSEOBC (New York) 2000 TBPCCS (Trondheim-Bergen) 2002 DPCCS (Jutland) 2003 Seattle BCYW (Washington) 1996 Seattle BCMW (Washington) 1996 SBCS (Shanghai) 2002 CmsBCS (US) 2002 CBCS (North Carolina) 2004 CARE (US) UP 1.10 (0.88, 1.37) 1.11 (0.95, 1.29) 1.22 (0.93, 1.62) 1.02 (0.98, 1.05) 1.02 (0.93, 1.13) 1.07 (0.95, 1.19) 0.97 (0.83, 1.14) 1.03 (0.80, 1.33) 0.92 (0.84, 1.01) 1.04 (0.90, 1.22) 1.06 (0.85, 1.31) 1.35 (1.01, 1.81) 1.01 (0.94, 1.08) 1.14 (0.91, 1.42) 1.03 (0.96, 1.11) 1.13 (0.79, 1.62) 1.12 (1.00, 1.26) 1.05 (0.97, 1.13) 1.01 (0.92, 1.11) 0.90 (0.80, 1.00) 0.93 (0.79, 1.08) 1.01 (0.97, 1.05) 0.89 (0.72, 1.10) 0.98 (0.94, 1.02).7 1 2 Box represents precision Sorted by publication year Bianca L De Stavola and Tim Collier LSHTM /Meta-analysis: basic principles and methods 6/20

An example Birth weight and breast cancer incidence Forest plot of rate relative risks (ES) and 95% confidence intervals Study ID ES (95% CI) MRC NSHD (UK) 2000 HBCS I (Helsinki) 2001 PSWG (Gothenburg) 2001 CSHRR (Copenhagen) 2003 UBCoS Multigen (Uppsala) 2003 SOUHCB(Trondheim) 2005 NCI DES (US) 2006 Aberdeen Children of the 1950s (Aberdeen) UP EPIC (Norfolk) UP HBCS II (Helsinki) UP HBCS III (Helsinki) UP SYFBC (Sweden) UP UKWCS (UK) 2007 MDC Study (Malmo) 2004 SPNFBC (Uppsala-Orebro) 1997 NYSEOBC (New York) 2000 TBPCCS (Trondheim-Bergen) 2002 1.10 (0.88, 1.37) 1.11 (0.95, 1.29) 1.22 (0.93, 1.62) 1.02 (0.98, 1.05) 1.02 (0.93, 1.13) 1.07 (0.95, 1.19) 0.97 (0.83, 1.14) 1.03 (0.80, 1.33) 0.92 (0.84, 1.01) 1.04 (0.90, 1.22) 1.06 (0.85, 1.31) 1.35 (1.01, 1.81) 1.01 (0.94, 1.08) 1.14 (0.91, 1.42) 1.03 (0.96, 1.11) 1.13 (0.79, 1.62) 1.12 (1.00, 1.26) DPCCS (Jutland) 2003 1.05 (0.97, 1.13) Seattle BCYW (Washington) 1996 Seattle BCMW (Washington) 1996 SBCS (Shanghai) 2002 CmsBCS (US) 2002 CBCS (North Carolina) 2004 CARE (US) UP 1.01 (0.92, 1.11) Is it appropriate to summarize this into just one value? Are the effect consistent across studies? 0.90 (0.80, 1.00) 0.93 (0.79, 1.08) 1.01 (0.97, 1.05) 0.89 (0.72, 1.10) 0.98 (0.94, 1.02).7 1 2 Box represents precision Sorted by publication year Bianca L De Stavola and Tim Collier LSHTM /Meta-analysis: basic principles and methods 6/20

Assessing heterogeneity 1 Cochran s Q statistic: Q = w s ( ˆβ s β) 2 where w s = 1/ŝe( ˆβ s ), and ˆβ is a weighted mean of the ˆβ s. Used to test whether all studies are evaluating the same effect, but has low power 2 Higgins and Thompson s I 2 : I 2 = (Q df )/Q 100 the proportion of total variability explained by heterogeneity Values < 25% re thought to be low... Bianca L De Stavola and Tim Collier LSHTM /Meta-analysis: basic principles and methods 7/20

Assessing heterogeneity 1 Cochran s Q statistic: Q = w s ( ˆβ s β) 2 where w s = 1/ŝe( ˆβ s ), and ˆβ is a weighted mean of the ˆβ s. Used to test whether all studies are evaluating the same effect, but has low power 2 Higgins and Thompson s I 2 : I 2 = (Q df )/Q 100 the proportion of total variability explained by heterogeneity In the example: Q = 28.99(df=23) p=0.18, I 2 =20.7% Values < 25% re thought to be low... Bianca L De Stavola and Tim Collier LSHTM /Meta-analysis: basic principles and methods 7/20

Pooling effects Two main ways to summarize (or pool) the separate study effects: Fixed effects model Assume each study measures the same effect: ˆβ s = β + e s where β: true common effect; e s : sampling error with variance σ 2 e Bianca L De Stavola and Tim Collier LSHTM /Meta-analysis: basic principles and methods 8/20

Pooling effects Two main ways to summarize (or pool) the separate study effects: Fixed effects model Assume each study measures the same effect: ˆβ s = β + e s where β: true common effect; e s : sampling error with variance σ 2 e Random effects model Assume the true effects in each study differs according to some distribution: ˆβ s = β + u s + ɛ s u s : rv with mean 0 and variance τ 2 ; β s = β + u s ; ɛ s : within study random error with variance σ 2 ɛ Bianca L De Stavola and Tim Collier LSHTM /Meta-analysis: basic principles and methods 8/20

What the models imply Log(relative risk) -.4 -.2 0.2.4.6 0 5 10 15 20 25 Study Bianca L De Stavola and Tim Collier LSHTM /Meta-analysis: basic principles and methods 9/20

What the models imply Log(relative risk) -.4 -.2 0.2.4.6 The difference between β s and β could be treated as due to random fluctuation or partly systematic (but random) 0 5 10 15 20 25 Study Bianca L De Stavola and Tim Collier LSHTM /Meta-analysis: basic principles and methods 9/20

Estimation by fixed effect meta-analysis Estimation via weighted average of the separate estimated study effects: β FE = s w s ˆβ s With a choice of weights: s w s a) inverse of the variance of the study effect estimate: w s = 1 se( ˆβ s ) b) Mantel-Haenszel weights (for ORs) c) Peto s weights (for ORs) 2 Bianca L De Stavola and Tim Collier LSHTM /Meta-analysis: basic principles and methods 10/20

Estimation by random effects meta-analysis Estimation via weighted average of the separate estimated study effects: β RE == s w s ˆβ s where weights are: w s = 1 se( ˆβ s ) 2 s w s and τ 2 is estimated from the Q statistic + ˆτ 2 (DerSimonian and Laird method) Bianca L De Stavola and Tim Collier LSHTM /Meta-analysis: basic principles and methods 11/20

The example revisited Fixed effect meta-analysis Study ID ES (95% CI) % Weight MRC NSHD (UK) 2000 HBCS I (Helsinki) 2001 PSWG (Gothenburg) 2001 CSHRR (Copenhagen) 2003 UBCoS Multigen (Uppsala) 2003 SOUHCB(Trondheim) 2005 NCI DES (US) 2006 Aberdeen Children of the 1950s (Aberdeen) UP EPIC (Norfolk) UP HBCS II (Helsinki) UP HBCS III (Helsinki) UP SYFBC (Sweden) UP UKWCS (UK) 2007 MDC Study (Malmo) 2004 SPNFBC (Uppsala-Orebro) 1997 NYSEOBC (New York) 2000 TBPCCS (Trondheim-Bergen) 2002 DPCCS (Jutland) 2003 Seattle BCYW (Washington) 1996 Seattle BCMW (Washington) 1996 SBCS (Shanghai) 2002 CmsBCS (US) 2002 CBCS (North Carolina) 2004 CARE (US) UP Overall (I-squared = 20.7%, p = 0.181) 1.10 (0.88, 1.37) 1.11 (0.95, 1.29) 1.22 (0.93, 1.62) 1.02 (0.98, 1.05) 1.02 (0.93, 1.13) 1.07 (0.95, 1.19) 0.97 (0.83, 1.14) 1.03 (0.80, 1.33) 0.92 (0.84, 1.01) 1.04 (0.90, 1.22) 1.06 (0.85, 1.31) 1.35 (1.01, 1.81) 1.01 (0.94, 1.08) 1.14 (0.91, 1.42) 1.03 (0.96, 1.11) 1.13 (0.79, 1.62) 1.12 (1.00, 1.26) 1.05 (0.97, 1.13) 1.01 (0.92, 1.11) 0.90 (0.80, 1.00) 0.93 (0.79, 1.08) 1.01 (0.97, 1.05) 0.89 (0.72, 1.10) 0.98 (0.94, 1.02) 1.01 (0.99, 1.03) 0.55 1.18 0.35 27.45 2.68 2.16 1.05 0.43 3.48 1.16 0.59 0.32 5.71 0.56 5.31 0.21 1.99 4.67 2.90 2.24 1.09 16.49 0.61 16.83 100.00.7 1 2 Bianca L De Stavola and Tim Collier LSHTM /Meta-analysis: basic principles and methods 12/20

The example revisited Random effect meta-analysis Study ID ES (95% CI) % Weight MRC NSHD (UK) 2000 HBCS I (Helsinki) 2001 PSWG (Gothenburg) 2001 CSHRR (Copenhagen) 2003 UBCoS Multigen (Uppsala) 2003 SOUHCB(Trondheim) 2005 NCI DES (US) 2006 Aberdeen Children of the 1950s (Aberdeen) UP EPIC (Norfolk) UP HBCS II (Helsinki) UP HBCS III (Helsinki) UP SYFBC (Sweden) UP UKWCS (UK) 2007 MDC Study (Malmo) 2004 SPNFBC (Uppsala-Orebro) 1997 NYSEOBC (New York) 2000 TBPCCS (Trondheim-Bergen) 2002 DPCCS (Jutland) 2003 Seattle BCYW (Washington) 1996 Seattle BCMW (Washington) 1996 SBCS (Shanghai) 2002 CmsBCS (US) 2002 CBCS (North Carolina) 2004 CARE (US) UP Overall (I-squared = 20.7%, p = 0.181) 1.10 (0.88, 1.37) 1.11 (0.95, 1.29) 1.22 (0.93, 1.62) 1.02 (0.98, 1.05) 1.02 (0.93, 1.13) 1.07 (0.95, 1.19) 0.97 (0.83, 1.14) 1.03 (0.80, 1.33) 0.92 (0.84, 1.01) 1.04 (0.90, 1.22) 1.06 (0.85, 1.31) 1.35 (1.01, 1.81) 1.01 (0.94, 1.08) 1.14 (0.91, 1.42) 1.03 (0.96, 1.11) 1.13 (0.79, 1.62) 1.12 (1.00, 1.26) 1.05 (0.97, 1.13) 1.01 (0.92, 1.11) 0.90 (0.80, 1.00) 0.93 (0.79, 1.08) 1.01 (0.97, 1.05) 0.89 (0.72, 1.10) 0.98 (0.94, 1.02) 1.01 (0.99, 1.03) 0.94 1.91 0.60 16.51 3.97 3.30 1.71 0.73 4.92 1.89 0.99 0.55 7.16 0.94 6.80 0.36 3.07 6.18 4.24 3.40 1.79 13.45 1.02 13.58 100.00 NOTE: Weights are from random effects analysis.7 1 2 Bianca L De Stavola and Tim Collier LSHTM /Meta-analysis: basic principles and methods 13/20

The example revisited Random effect meta-analysis Study ID ES (95% CI) % Weight MRC NSHD (UK) 2000 HBCS I (Helsinki) 2001 PSWG (Gothenburg) 2001 CSHRR (Copenhagen) 2003 UBCoS Multigen (Uppsala) 2003 SOUHCB(Trondheim) 2005 NCI DES (US) 2006 Aberdeen Children of the 1950s (Aberdeen) UP EPIC (Norfolk) UP HBCS II (Helsinki) UP HBCS III (Helsinki) UP SYFBC (Sweden) UP UKWCS (UK) 2007 MDC Study (Malmo) 2004 SPNFBC (Uppsala-Orebro) 1997 NYSEOBC (New York) 2000 TBPCCS (Trondheim-Bergen) 2002 DPCCS (Jutland) 2003 Seattle BCYW (Washington) 1996 Seattle BCMW (Washington) 1996 SBCS (Shanghai) 2002 1.10 (0.88, 1.37) 1.11 (0.95, 1.29) 1.22 (0.93, 1.62) 1.02 (0.98, 1.05) 1.02 (0.93, 1.13) 1.07 (0.95, 1.19) 0.97 (0.83, 1.14) 1.03 (0.80, 1.33) 0.92 (0.84, 1.01) 1.04 (0.90, 1.22) 1.06 (0.85, 1.31) 1.35 (1.01, 1.81) 1.01 (0.94, 1.08) 1.14 (0.91, 1.42) 1.03 (0.96, 1.11) 1.13 (0.79, 1.62) 1.12 (1.00, 1.26) 1.05 (0.97, 1.13) 1.01 (0.92, 1.11) 0.90 (0.80, 1.00) 0.93 (0.79, 1.08) 0.94 1.91 0.60 16.51 3.97 3.30 1.71 0.73 4.92 1.89 0.99 0.55 7.16 0.94 6.80 0.36 3.07 6.18 4.24 3.40 1.79 CmsBCS (US) 2002 1.01 (0.97, 1.05) CBCS (North Carolina) 2004 CARE (US) UP RE model gives greater weights to smaller studies Overall (I-squared = 20.7%, p = 0.181) 0.89 (0.72, 1.10) 0.98 (0.94, 1.02) 1.01 (0.99, 1.03) 13.45 1.02 13.58 100.00 NOTE: Weights are from random effects analysis.7 1 2 Bianca L De Stavola and Tim Collier LSHTM /Meta-analysis: basic principles and methods 13/20

How to do it in Stata Bianca L De Stavola and Tim Collier LSHTM /Meta-analysis: basic principles and methods 14/20

Risk of Bias Summary estimate may be affected by bias because: 1 varying quality of the data: outcome (e.g. via incomplete follow-up) exposure (e.g. varying definitions) 2 publication bias: studies with significant effects are more likely to be published non-english language papers may not be fully represented 3 unmeasured confounding: relevant for meta-analysis of observational studies... Bianca L De Stavola and Tim Collier LSHTM /Meta-analysis: basic principles and methods 15/20

1 - Quality of the data Stratifying by source of exposure data Study ID ES (95% CI) % Weight Birth record MRC NSHD (UK) 2000 HBCS I (Helsinki) 2001 PSWG (Gothenburg) 2001 UBCoS Multigen (Uppsala) 2003 SOUHCB(Trondheim) 2005 NCI DES (US) 2006 Aberdeen Children of the 1950s (Aberdeen) UP HBCS II (Helsinki) UP HBCS III (Helsinki) UP SYFBC (Sweden) UP MDC Study (Malmo) 2004 SPNFBC (Uppsala-Orebro) 1997 NYSEOBC (New York) 2000 TBPCCS (Trondheim-Bergen) 2002 DPCCS (Jutland) 2003 CBCS (North Carolina) 2004 Subtotal (I-squared = 0.0%, p = 0.809). Parental recall in childhood CSHRR (Copenhagen) 2003 Subtotal (I-squared =.%, p =.). Adult report EPIC (Norfolk) UP UKWCS (UK) 2007 Seattle BCYW (Washington) 1996 Seattle BCMW (Washington) 1996 SBCS (Shanghai) 2002 CmsBCS (US) 2002 CARE (US) UP Subtotal (I-squared = 22.0%, p = 0.262). NOTE: Weights are from random effects analysis 1.10 (0.88, 1.37) 1.11 (0.95, 1.29) 1.22 (0.93, 1.62) 1.02 (0.93, 1.13) 1.07 (0.95, 1.19) 0.97 (0.83, 1.14) 1.03 (0.80, 1.33) 1.04 (0.90, 1.22) 1.06 (0.85, 1.31) 1.35 (1.01, 1.81) 1.14 (0.91, 1.42) 1.03 (0.96, 1.11) 1.13 (0.79, 1.62) 1.12 (1.00, 1.26) 1.05 (0.97, 1.13) 0.89 (0.72, 1.10) 1.05 (1.02, 1.09) 1.02 (0.98, 1.05) 1.02 (0.98, 1.05) 0.92 (0.84, 1.01) 1.01 (0.94, 1.08) 1.01 (0.92, 1.11) 0.90 (0.80, 1.00) 0.93 (0.79, 1.08) 1.01 (0.97, 1.05) 0.98 (0.94, 1.02) 0.98 (0.95, 1.01) 2.33 4.95 1.47 11.27 9.07 4.39 1.80 4.87 2.48 1.34 2.34 22.32 0.86 8.37 19.59 2.54 100.00 100.00 100.00 9.40 14.14 8.02 6.36 3.27 29.23 29.57 100.00.7 1 2 Bianca L De Stavola and Tim Collier LSHTM /Meta-analysis: basic principles and methods 16/20

1 - Quality of the data Stratifying by source of exposure data Study ID ES (95% CI) % Weight Birth record MRC NSHD (UK) 2000 1.10 (0.88, 1.37) HBCS I (Helsinki) 2001 1.11 (0.95, 1.29) PSWG (Gothenburg) 2001 1.22 (0.93, 1.62) UBCoS Multigen (Uppsala) 2003 1.02 (0.93, 1.13) SOUHCB(Trondheim) 2005 1.07 (0.95, 1.19) NCI DES (US) 2006 0.97 (0.83, 1.14) Aberdeen Children of the 1950s (Aberdeen) UP 1.03 (0.80, 1.33) HBCS II (Helsinki) UP 1.04 (0.90, 1.22) HBCS III (Helsinki) UP 1.06 (0.85, 1.31) SYFBC (Sweden) UP 1.35 (1.01, 1.81) MDC Study (Malmo) 2004 1.14 (0.91, 1.42) SPNFBC (Uppsala-Orebro) 1997 1.03 (0.96, 1.11) NYSEOBC (New York) 2000 1.13 (0.79, 1.62) TBPCCS (Trondheim-Bergen) 2002 1.12 (1.00, 1.26) DPCCS (Jutland) 2003 1.05 (0.97, 1.13) CBCS (North Carolina) 2004 0.89 (0.72, 1.10) Subtotal (I-squared = 0.0%, p = 0.809) 1.05 (1.02, 1.09). Parental recall in childhood CSHRR (Copenhagen) 2003 1.02 (0.98, 1.05) Subtotal (I-squared =.%, p =.) 1.02 (0.98, 1.05). Adult report EPIC (Norfolk) UP 0.92 (0.84, 1.01) UKWCS (UK) 2007 1.01 (0.94, 1.08) Seattle BCYW (Washington) 1996 1.01 (0.92, 1.11) Seattle BCMW (Washington) 1996 0.90 (0.80, 1.00) SBCS (Shanghai) 2002 0.93 (0.79, 1.08) CmsBCS (US) 2002 CARE (US) UP Greater homogeneity within first sub-group ( Birth records ).7 1 2 but not the last ( self-report ) Subtotal (I-squared = 22.0%, p = 0.262). NOTE: Weights are from random effects analysis 1.01 (0.97, 1.05) 0.98 (0.94, 1.02) 0.98 (0.95, 1.01) 2.33 4.95 1.47 11.27 9.07 4.39 1.80 4.87 2.48 1.34 2.34 22.32 0.86 8.37 19.59 2.54 100.00 100.00 100.00 9.40 14.14 8.02 6.36 3.27 29.23 29.57 100.00 Bianca L De Stavola and Tim Collier LSHTM /Meta-analysis: basic principles and methods 16/20

2 - Publication bias Funnel plots Studies with low precision will show a wide variation in effects while studies with high precision will show much less variation, Funnel plot with pseudo 95% confidence limits.15.2 s.e. of lnor.1.05 0 -.4 -.2 0.2.4 lnor Bianca L De Stavola and Tim Collier LSHTM /Meta-analysis: basic principles and methods 17/20

Meta-regression Combining results from multiple studies with regression, accounting for differences in precision: Log(relative risk) -.1 0.1.2.3 birth record parental self Source of information Bianca L De Stavola and Tim Collier LSHTM /Meta-analysis: basic principles and methods 18/20

Fixed or random effects? We should remember that this is a model fitting exercise The pooled summary represents: 1 Fixed effect model: the common effect shared by all studies, 2 Random effects model: is the average of the study specific effects. In general random effects pooled estimates are more appropriate If little variation across studies the choice is not crucial In most settings, investigation of sources of heterogeneity should be the focus Bianca L De Stavola and Tim Collier LSHTM /Meta-analysis: basic principles and methods 19/20

References 1 Egger M, Davey Smith G, Altman DG. Systematic Reviews in Health Care: Meta-Analysis in Context. BMJ Books: London, 2000. 2 DerSimonian R, Laird N. Meta-analysis in clinical trials. Controlled Clinical Trials 1986; 7:177188. 3 Higgins JP et al. Measuring inconsistency in meta-analysis. BMJ 2003; 327:557-560 4 Sutton AJ, Higgins JP. Recent developments in meta-analysis. Stat Med. 2008, 27: 625-650 5 Sutton AJ, Abrams KR, Jones DR, Sheldon TA, Song F. Methods for Meta-Analysis in Medical Research. Wiley: London, 2000. 6 Thompson SG, Sharp SJ. Explaining heterogeneity in meta-analysis: a comparison of methods. Statistics in Medicine 1999; 18:26932708. Bianca L De Stavola and Tim Collier LSHTM /Meta-analysis: basic principles and methods 20/20

Meta Analysis in Stata Tim Collier Medical Statistics Department LSHTM

Outline Getting started in Stata FE & RE models with data in different formats using metan (GUI & syntax) Forest plots Investigating small study effects using metafunnel and metabias Investigating heterogeneity with meta regression using metareg

Getting Started

Getting Started

Getting Started

Getting Started

Getting Started Install commands from Boston College SSC Takes just a few seconds Repeat for metareg, metafunnel, metabias, etc.

The Data

The Data counts (2x2 tables) pe_int = number with PE in intervention group nope_int = number without PE in intervention group pe_con = number with PE in control group nope_con = number without PE in control group

The Data effect & CI

The Data estimate & SE

Graphical User Interface: db metan

db metan count data (2x2 tables) Yes No Int. a b Con. c d

.322 1 3.1 Study ID RR (95% CI) % Weight LRC-CPPT 4S WOSCOPS CARE AF/Tex-CAPS LIPID Post-CABG MIRACL GREACE LIPS HPS PROSPER ALLHAT ASCOT ALERT PROVE-IT CARDS A TO Z TNT Overall (I-squared = 52.4%, p = 0.004) 0.83 (0.67, 1.01) 0.69 (0.62, 0.77) 0.70 (0.58, 0.84) 0.77 (0.65, 0.91) 0.60 (0.43, 0.83) 0.78 (0.70, 0.86) 0.80 (0.59, 1.08) 0.92 (0.75, 1.13) 0.46 (0.32, 0.66) 0.69 (0.47, 1.01) 0.74 (0.68, 0.80) 0.87 (0.77, 0.98) 0.91 (0.79, 1.03) 0.65 (0.50, 0.83) 0.67 (0.50, 0.90) 0.87 (0.71, 1.08) 0.65 (0.46, 0.92) 0.89 (0.77, 1.02) 0.79 (0.70, 0.89) 0.78 (0.75, 0.80) 3.10 10.27 4.10 4.53 1.57 11.83 1.42 2.78 1.47 1.00 20.03 7.79 6.95 2.55 1.72 2.85 1.28 5.71 9.05 100.00

random effects count data

fixed v random Fixed (M H pooled RR) 0.775 95% CI(0.748, 0.804) Random (D L pooled RR) 0.772 95% CI(0.728, 0.818) Heterogeneity chi squared 37.83 (18df) p = 0.004 I squared = 52.4%

Demo of Stata Syntax

2024 © travelsdocbox.com Privacy Policy | Terms of Service | Feedback