goodness of fit in dose response meta analysis
play

Goodness of fit in dose-response meta-analysis Alessio Crippa 1 - PowerPoint PPT Presentation

Introduction Estimation A measure of GOF Examples Conclusion Goodness of fit in dose-response meta-analysis Alessio Crippa 1 Nicola Orsini 1 1 Institute of Environmental Medicine, Karolinska Institutet Epi-Seminar 26th September 2013 Crippa


  1. Introduction Estimation A measure of GOF Examples Conclusion Goodness of fit in dose-response meta-analysis Alessio Crippa 1 Nicola Orsini 1 1 Institute of Environmental Medicine, Karolinska Institutet Epi-Seminar 26th September 2013 Crippa A., Orsini N. Institute of Environmental Medicine, KI GOF in dose-response meta-analysis

  2. Introduction Estimation A measure of GOF Examples Conclusion Contents Introduction Estimation A measure of GOF Practical Examples Conclusion Crippa A., Orsini N. Institute of Environmental Medicine, KI GOF in dose-response meta-analysis

  3. Introduction Estimation A measure of GOF Examples Conclusion Outline Introduction Estimation A measure of GOF Practical Examples Conclusion Crippa A., Orsini N. Institute of Environmental Medicine, KI GOF in dose-response meta-analysis

  4. Introduction Estimation A measure of GOF Examples Conclusion Meta-Analysis ◮ Increasing number of scientific publishing. ◮ Systematical literature review supported by statistical methods. ◮ Main goal: aggregate and contrast findings from several studies. ◮ Weighted average of common measure of effect size, with weights related to the precision of the estimates Crippa A., Orsini N. Institute of Environmental Medicine, KI GOF in dose-response meta-analysis

  5. Introduction Estimation A measure of GOF Examples Conclusion Dose-Response Meta-Analysis ◮ Specific type of meta-analysis ◮ Analyze summarized published data, where the exposure is usually categorized and the results (effect size) presented in a tabular way Table: Case-control data on alcohol and breast cancer risk (Rohan and Michael 1988) gday dose case n adjrr lb ub Ref. 0 165 337 1.00 1.00 1.00 < 2.5 2 74 167 0.80 0.51 1.27 2.5-9.3 6 90 186 1.16 0.73 1.85 > 9.3 11 122 212 1.57 0.99 2.51 Crippa A., Orsini N. Institute of Environmental Medicine, KI GOF in dose-response meta-analysis

  6. Introduction Estimation A measure of GOF Examples Conclusion Dose-Response Meta-Analysis ◮ Specific type of meta-analysis ◮ Analyze summarized published data, where the exposure is usually categorized and the results (effect size) presented in a tabular way Table: Case-control data on alcohol and breast cancer risk (Rohan and Michael 1988) gday dose case n adjrr lb ub Ref. 0 165 337 1.00 1.00 1.00 < 2.5 2 74 167 0.80 0.51 1.27 2.5-9.3 6 90 186 1.16 0.73 1.85 > 9.3 11 122 212 1.57 0.99 2.51 Crippa A., Orsini N. Institute of Environmental Medicine, KI GOF in dose-response meta-analysis

  7. Introduction Estimation A measure of GOF Examples Conclusion Dose-Response Meta-Analysis ◮ Specific type of meta-analysis ◮ Analyze summarized published data, where the exposure is usually categorized and the results (effect size) presented in a tabular way Table: Case-control data on alcohol and breast cancer risk (Rohan and Michael 1988) gday dose case n adjrr lb ub Ref. 0 165 337 1.00 1.00 1.00 < 2.5 2 74 167 0.80 0.51 1.27 2.5-9.3 6 90 186 1.16 0.73 1.85 > 9.3 11 122 212 1.57 0.99 2.51 Crippa A., Orsini N. Institute of Environmental Medicine, KI GOF in dose-response meta-analysis

  8. Introduction Estimation A measure of GOF Examples Conclusion 1.6 ◮ Define a dose-response Data Linear function for a single study Quadratic 1.4 ◮ Combine trends from several Log relative risk studies 1.2 ◮ Method formalized by Greenland and Longnecker 1.0 (1992) ◮ Number of dose-response meta-analyses increased 0.8 exponentially 0 2 4 6 8 10 Alcohol consumtion, grams/day Crippa A., Orsini N. Institute of Environmental Medicine, KI GOF in dose-response meta-analysis

  9. Introduction Estimation A measure of GOF Examples Conclusion ◮ Procedure developed in Stata 70 (glst command) by Orsini 60 (2006) Number of publications 50 ◮ 42 in the first 4 months of 40 2013 (2 every week) 30 ◮ 26 (60%) estimated linear trend 20 ◮ Only 17 (40%) investigated 10 non-linearity and provided a 0 graphical presentation 1995 2000 2005 2010 Years Crippa A., Orsini N. Institute of Environmental Medicine, KI GOF in dose-response meta-analysis

  10. Introduction Estimation A measure of GOF Examples Conclusion ◮ None overlaid the observed data points and the summary exposure-disease association ◮ Define the degree of consistency of prior knowledge around a pooled trend Aims ◮ Describe how to estimate dose-response association ◮ Clarify how observed and fitted relative risks can be compared ◮ Propose a measure of goodness of fit ◮ Implement the proposed method in an R package Crippa A., Orsini N. Institute of Environmental Medicine, KI GOF in dose-response meta-analysis

  11. Introduction Estimation A measure of GOF Examples Conclusion Outline Introduction Estimation A measure of GOF Practical Examples Conclusion Crippa A., Orsini N. Institute of Environmental Medicine, KI GOF in dose-response meta-analysis

  12. Introduction Estimation A measure of GOF Examples Conclusion Estimate a pooled dose-response relation Two stage procedure: First stage Define and estimate the dose-response association for the j -th study, j = 1 , . . . , m (linear, polynomials, splines): Second stage Combine these estimates to obtain an overall pooled dose-response association. Crippa A., Orsini N. Institute of Environmental Medicine, KI GOF in dose-response meta-analysis

  13. Introduction Estimation A measure of GOF Examples Conclusion Model definition Log linear model for a single study (linear trend): y i = β 1 X i + ǫ i (1) where y i are the log of non referent relative risks, X i the corresponding levels of exposure ( x = 0 correspond to the reference category). NB: The model in equation (1) has no intercept: the log relative risk for the referent exposure is set equal to 0 (RR=1). Crippa A., Orsini N. Institute of Environmental Medicine, KI GOF in dose-response meta-analysis

  14. Introduction Estimation A measure of GOF Examples Conclusion GLS estimation ǫ i are not independent, Cov ( ǫ i ) = Σ Σ can be estimated from the published data. β can be efficiently estimated by gls: ˆ β = ( X ′ Σ X ) − 1 X ′ Σ − 1 y (2) V = Cov (ˆ β ) = ( X ′ Σ X ) − 1 (3) Crippa A., Orsini N. Institute of Environmental Medicine, KI GOF in dose-response meta-analysis

  15. Introduction Estimation A measure of GOF Examples Conclusion Second stage Let consider m studies. � � Aim: pooling of ˆ β 1 , . . . ˆ ˆ β = β m Multivariate random-effect meta-analysis: ˆ β j ∼ N p ( β, V j + ψ ) (4) Different methods for estimation: (full) maximum likelihood, restricted maximum likelihood or methods of moments Crippa A., Orsini N. Institute of Environmental Medicine, KI GOF in dose-response meta-analysis

  16. Introduction Estimation A measure of GOF Examples Conclusion Fit statistics Assess and quantify heterogeneity (second stage analysis): ◮ m � � � ( β j − ˆ ( β j − ˆ β f ) ′ V − 1 Q = β f ) (5) j j = 1 ◮ I 2 = Q − df (6) Q ◮ Information Criteria, such as AIC = − 2 l (ˆ β, ˆ ψ ) + 2 p (7) Crippa A., Orsini N. Institute of Environmental Medicine, KI GOF in dose-response meta-analysis

  17. Introduction Estimation A measure of GOF Examples Conclusion Outline Introduction Estimation A measure of GOF Practical Examples Conclusion Crippa A., Orsini N. Institute of Environmental Medicine, KI GOF in dose-response meta-analysis

  18. Introduction Estimation A measure of GOF Examples Conclusion Motivating example Table: Case-control data on alcohol and breast cancer risk (Rohan and Michael 1988) gday dose case control n crudeor adjrr lb ub Ref. 0 165 172 337 1.00 1.00 1.00 1.00 < 2.5 2 74 93 167 0.83 0.80 0.51 1.27 2.5-9.3 6 90 96 186 0.98 1.16 0.73 1.85 > 9.3 11 122 90 212 1.41 1.57 0.99 2.51 Linear trend: log ( adjrr ) = β 1 X i + ǫ i Crippa A., Orsini N. Institute of Environmental Medicine, KI GOF in dose-response meta-analysis

  19. Introduction Estimation A measure of GOF Examples Conclusion library(dosresmeta) data(cc_ex) mod <- dosresmeta(formula = logrr ~ 0 + dose, study="cc", cov =c(case, n), se=c(loglb, logub), data=cc _ ex) mod$Param id Estimate Std. Error z value Pr(>z) 1 1 dose 0.046 0.02051 2.24 0.025 mod$fit.stat id Q Pr(>chi2) log ll 1 1 1.93 0.382 0.790 Crippa A., Orsini N. Institute of Environmental Medicine, KI GOF in dose-response meta-analysis

  20. Introduction Estimation A measure of GOF Examples Conclusion 1.6 Data Linear 1.4 Log relative risk 1.2 1.0 0.8 0 2 4 6 8 10 Alcohol consumtion, grams/day Figure: Comparison between corrected and uncorrected prediction Crippa A., Orsini N. Institute of Environmental Medicine, KI GOF in dose-response meta-analysis

  21. Introduction Estimation A measure of GOF Examples Conclusion De-correlate data points: a single study Consider y , X and Σ : L is the Cholesky decomposition of Σ , Σ = LL ′ y ∗ = L − 1 y (8) X ∗ = L − 1 X Model in equation (1) can be re-formulated as: y ∗ = X ∗ β ∗ + ǫ ∗ (9) β ∗ = ˆ NB: Parameter estimates do not change: ˆ β Crippa A., Orsini N. Institute of Environmental Medicine, KI GOF in dose-response meta-analysis

Recommend


More recommend