class: center, middle, inverse, title-slide .title[ # Bayesian meta-regression models for the estimation of population trends in health risk factors ] .subtitle[ ## <span style="font-style: normal;">Annibale Cois </span><span style="font-size: 50%;">MEng, MPH, PhD</span> ] .author[ ### <span style="font-size: 80%; font-style:normal;">Division of Health Systems & Public Health, Department of Global Health, Stellenbosch University & <br/> Division of Epidemiology & Biostatistics, School of Public Health, University of Cape Town</span> ] .date[ ### <span style="color: #000000; position: relative; top: 180px; font-style:normal;">01/12/2022 • George • Western Cape • South Africa </span> ] --- class: hide_logo <div> <style type="text/css">.xaringan-extra-logo { width: 150px; height: 46px; z-index: 0; background-image: url(assets/sulogo_1.png); background-size: contain; background-repeat: no-repeat; position: absolute; bottom:1em;left:60px; } </style> <script>(function () { let tries = 0 function addLogo () { if (typeof slideshow === 'undefined') { tries += 1 if (tries < 10) { setTimeout(addLogo, 100) } } else { document.querySelectorAll('.remark-slide-content:not(.title-slide):not(.inverse):not(.hide_logo)') .forEach(function (slide) { const logo = document.createElement('div') logo.classList = 'xaringan-extra-logo' logo.href = null slide.appendChild(logo) }) } } document.addEventListener('DOMContentLoaded', addLogo) })()</script> </div> ## Outline <svg viewBox="0 0 512 512" style="height:1em;display:inline-block;fill:#561a34;position:fixed;top:38;right:50;" xmlns="http://www.w3.org/2000/svg"> <path d="M80 368H16a16 16 0 0 0-16 16v64a16 16 0 0 0 16 16h64a16 16 0 0 0 16-16v-64a16 16 0 0 0-16-16zm0-320H16A16 16 0 0 0 0 64v64a16 16 0 0 0 16 16h64a16 16 0 0 0 16-16V64a16 16 0 0 0-16-16zm0 160H16a16 16 0 0 0-16 16v64a16 16 0 0 0 16 16h64a16 16 0 0 0 16-16v-64a16 16 0 0 0-16-16zm416 176H176a16 16 0 0 0-16 16v32a16 16 0 0 0 16 16h320a16 16 0 0 0 16-16v-32a16 16 0 0 0-16-16zm0-320H176a16 16 0 0 0-16 16v32a16 16 0 0 0 16 16h320a16 16 0 0 0 16-16V80a16 16 0 0 0-16-16zm0 160H176a16 16 0 0 0-16 16v32a16 16 0 0 0 16 16h320a16 16 0 0 0 16-16v-32a16 16 0 0 0-16-16z"></path></svg> .black[ - ### Quantifying trends and distribution of risk factors for health - ### Alcohol consumption as a case in point ] .black[ - ### Why Bayes? - ### A Bayesian meta-regression model for alcohol consumption ] .black[ - ### (Some) results - ### Conclusion ] --- background-image: url(images/data.png) background-position: 50% 60% background-size: 60% ## Data <svg viewBox="0 0 512 512" style="height:1em;display:inline-block;fill:#561a34;position:fixed;top:38;right:50;" xmlns="http://www.w3.org/2000/svg"> <path d="M447.1 112c-34.2.5-62.3 28.4-63 62.6-.5 24.3 12.5 45.6 32 56.8V344c0 57.3-50.2 104-112 104-60 0-109.2-44.1-111.9-99.2C265 333.8 320 269.2 320 192V36.6c0-11.4-8.1-21.3-19.3-23.5L237.8.5c-13-2.6-25.6 5.8-28.2 18.8L206.4 35c-2.6 13 5.8 25.6 18.8 28.2l30.7 6.1v121.4c0 52.9-42.2 96.7-95.1 97.2-53.4.5-96.9-42.7-96.9-96V69.4l30.7-6.1c13-2.6 21.4-15.2 18.8-28.2l-3.1-15.7C107.7 6.4 95.1-2 82.1.6L19.3 13C8.1 15.3 0 25.1 0 36.6V192c0 77.3 55.1 142 128.1 156.8C130.7 439.2 208.6 512 304 512c97 0 176-75.4 176-168V231.4c19.1-11.1 32-31.7 32-55.4 0-35.7-29.2-64.5-64.9-64zm.9 80c-8.8 0-16-7.2-16-16s7.2-16 16-16 16 7.2 16 16-7.2 16-16 16z"></path></svg> --- background-image: url(images/data1.png) background-position: 50% 60% background-size: 60% ## Data <svg viewBox="0 0 512 512" style="height:1em;display:inline-block;fill:#561a34;position:fixed;top:38;right:50;" xmlns="http://www.w3.org/2000/svg"> <path d="M447.1 112c-34.2.5-62.3 28.4-63 62.6-.5 24.3 12.5 45.6 32 56.8V344c0 57.3-50.2 104-112 104-60 0-109.2-44.1-111.9-99.2C265 333.8 320 269.2 320 192V36.6c0-11.4-8.1-21.3-19.3-23.5L237.8.5c-13-2.6-25.6 5.8-28.2 18.8L206.4 35c-2.6 13 5.8 25.6 18.8 28.2l30.7 6.1v121.4c0 52.9-42.2 96.7-95.1 97.2-53.4.5-96.9-42.7-96.9-96V69.4l30.7-6.1c13-2.6 21.4-15.2 18.8-28.2l-3.1-15.7C107.7 6.4 95.1-2 82.1.6L19.3 13C8.1 15.3 0 25.1 0 36.6V192c0 77.3 55.1 142 128.1 156.8C130.7 439.2 208.6 512 304 512c97 0 176-75.4 176-168V231.4c19.1-11.1 32-31.7 32-55.4 0-35.7-29.2-64.5-64.9-64zm.9 80c-8.8 0-16-7.2-16-16s7.2-16 16-16 16 7.2 16 16-7.2 16-16 16z"></path></svg> <br/> <br/> .font200[ .center[ Heterogeneous Sparse (often) biased ] ] --- background-image: url(images/sample.png) background-position: 10% 50% background-size: 40% ## Estimating alcohol consumption <svg viewBox="0 0 512 512" style="height:1em;display:inline-block;fill:#561a34;position:fixed;top:38;right:50;" xmlns="http://www.w3.org/2000/svg"> <path d="M507.31 72.57L439.43 4.69c-6.25-6.25-16.38-6.25-22.63 0l-22.63 22.63c-6.25 6.25-6.25 16.38 0 22.63l-76.67 76.67c-46.58-19.7-102.4-10.73-140.37 27.23L18.75 312.23c-24.99 24.99-24.99 65.52 0 90.51l90.51 90.51c24.99 24.99 65.52 24.99 90.51 0l158.39-158.39c37.96-37.96 46.93-93.79 27.23-140.37l76.67-76.67c6.25 6.25 16.38 6.25 22.63 0l22.63-22.63c6.24-6.24 6.24-16.37-.01-22.62zM179.22 423.29l-90.51-90.51 122.04-122.04 90.51 90.51-122.04 122.04z"></path></svg> .font140[ .pull-right[ <div style = "margin-top:120px; margin-bottom: 60px;">Large uncertainty <img src="images/ci.png", width = "200"></img></div> <div style = "margin-bottom: 50px;">Interval censored data <img src="images/censor.png", width = "100"></img></div> <div>Large <span style = "color:red;">downward</span> bias <img src="images/darrow.png", width = "50"></img></div></div> ] ] --- class: hide_logo background-image: url(images/coverage.png) background-position: 50% 50% background-size: 60% ## <svg viewBox="0 0 512 512" style="height:1em;display:inline-block;fill:#561a34;position:fixed;top:38;right:50;" xmlns="http://www.w3.org/2000/svg"> <path d="M507.31 72.57L439.43 4.69c-6.25-6.25-16.38-6.25-22.63 0l-22.63 22.63c-6.25 6.25-6.25 16.38 0 22.63l-76.67 76.67c-46.58-19.7-102.4-10.73-140.37 27.23L18.75 312.23c-24.99 24.99-24.99 65.52 0 90.51l90.51 90.51c24.99 24.99 65.52 24.99 90.51 0l158.39-158.39c37.96-37.96 46.93-93.79 27.23-140.37l76.67-76.67c6.25 6.25 16.38 6.25 22.63 0l22.63-22.63c6.24-6.24 6.24-16.37-.01-22.62zM179.22 423.29l-90.51-90.51 122.04-122.04 90.51 90.51-122.04 122.04z"></path></svg> .footnote[Probst, Shuper, and Rehm (2017)] --- class: hide_logo background-image: url(images/triang.png) background-position: 10% 60% background-size: 60% ## The WHO approach <svg viewBox="0 0 512 512" style="height:1em;display:inline-block;fill:#561a34;position:fixed;top:38;right:50;" xmlns="http://www.w3.org/2000/svg"> <path d="M507.31 72.57L439.43 4.69c-6.25-6.25-16.38-6.25-22.63 0l-22.63 22.63c-6.25 6.25-6.25 16.38 0 22.63l-76.67 76.67c-46.58-19.7-102.4-10.73-140.37 27.23L18.75 312.23c-24.99 24.99-24.99 65.52 0 90.51l90.51 90.51c24.99 24.99 65.52 24.99 90.51 0l158.39-158.39c37.96-37.96 46.93-93.79 27.23-140.37l76.67-76.67c6.25 6.25 16.38 6.25 22.63 0l22.63-22.63c6.24-6.24 6.24-16.37-.01-22.62zM179.22 423.29l-90.51-90.51 122.04-122.04 90.51 90.51-122.04 122.04z"></path></svg> .footnote[ WHO (2018), Rehm, Kehoe, Gmel, Stinson, Grant, and Gmel (2010), Kehoe, Gmel, Shield, Gmel, and Rehm (2012) ] -- <div style = "position: absolute; left: 65%; top:15%; width:25%;"> <img src = "images/assumptions.png" style="width: 200px; margin-left: 70px"></img> <ul> <li>Distribution shape</li> <li>Constant coverage across subpopulations</li> <li>Known prevalence of drinkers</li> </ul> </div> --- class: hide_logo background-image: url(images/steps.png) background-position: 50% 50% background-size: 100% --- background-image: url(images/bayes.png) background-position: 50% 50% background-size: 100% ## Why Bayes? <svg viewBox="0 0 512 512" style="height:1em;display:inline-block;fill:#561a34;position:fixed;top:38;right:50;" xmlns="http://www.w3.org/2000/svg"> <path d="M256 8C119 8 8 119 8 256s111 248 248 248 248-111 248-248S393 8 256 8zm0 448c-110.5 0-200-89.5-200-200S145.5 56 256 56s200 89.5 200 200-89.5 200-200 200z"></path></svg> <br/> - ## Principled integration of multiple data sources - ## Formal integration of (uncertain) assumptions as priors - ## Improved quantification of the estimation error - ## Recover of the full distribution of alcohol consumption --- class: hide_logo background-image: url(images/overview.png) background-position: 50% 65% background-size: 70% ## A meta-regression model <svg viewBox="0 0 640 512" style="height:1em;display:inline-block;fill:#561a34;position:fixed;top:38;right:50;" xmlns="http://www.w3.org/2000/svg"> <path d="M278.9 511.5l-61-17.7c-6.4-1.8-10-8.5-8.2-14.9L346.2 8.7c1.8-6.4 8.5-10 14.9-8.2l61 17.7c6.4 1.8 10 8.5 8.2 14.9L293.8 503.3c-1.9 6.4-8.5 10.1-14.9 8.2zm-114-112.2l43.5-46.4c4.6-4.9 4.3-12.7-.8-17.2L117 256l90.6-79.7c5.1-4.5 5.5-12.3.8-17.2l-43.5-46.4c-4.5-4.8-12.1-5.1-17-.5L3.8 247.2c-5.1 4.7-5.1 12.8 0 17.5l144.1 135.1c4.9 4.6 12.5 4.4 17-.5zm327.2.6l144.1-135.1c5.1-4.7 5.1-12.8 0-17.5L492.1 112.1c-4.8-4.5-12.4-4.3-17 .5L431.6 159c-4.6 4.9-4.3 12.7.8 17.2L523 256l-90.6 79.7c-5.1 4.5-5.5 12.3-.8 17.2l43.5 46.4c4.5 4.9 12.1 5.1 17 .6z"></path></svg> --- class: hide_logo ## Data structure <svg viewBox="0 0 448 512" style="height:1em;display:inline-block;fill:#561a34;position:fixed;top:38;right:50;" xmlns="http://www.w3.org/2000/svg"> <path d="M224 352c-35.35 0-64 28.65-64 64s28.65 64 64 64 64-28.65 64-64-28.65-64-64-64zm0-192c35.35 0 64-28.65 64-64s-28.65-64-64-64-64 28.65-64 64 28.65 64 64 64zm192 48H32c-17.67 0-32 14.33-32 32v32c0 17.67 14.33 32 32 32h384c17.67 0 32-14.33 32-32v-32c0-17.67-14.33-32-32-32z"></path></svg> <br/> `\(s \in \{1,..S\}\)` = source survey `\(g \in \{1,2\}\)`, `\(a \in \{1,..A\}\)` = sex and age category; `\(k \in \{1,..K\}\)` = number of different consumption intervals; <br/> .font140[ `$$\require{color}\displaystyle\color{#FF0000}{pp_{s,g,a}, pse_{s,g,a}}$$` `$$\require{color}\displaystyle\color{#FF0000}{TC_{s,g,a,k} = \left\{lc_{s,g,a,k}; uc_{s,g,a,k}; pc_{s,g,a,k}; ne_{s,g,a}\right\}}$$` <br/> ] `\(lc_{s,g,a,k}, uc_{s,g,a,k}\)` = bounds of the consumption intervals [g/day]; `\(pc_{s,g,a,k}\)` = proportion of subjects belonging to the consumption interval; `\(ne_{s,g,a}\)` = effective sample size; --- ## Likelihood <svg viewBox="0 0 448 512" style="height:1em;display:inline-block;fill:#561a34;position:fixed;top:38;right:50;" xmlns="http://www.w3.org/2000/svg"> <path d="M224 352c-35.35 0-64 28.65-64 64s28.65 64 64 64 64-28.65 64-64-28.65-64-64-64zm0-192c35.35 0 64-28.65 64-64s-28.65-64-64-64-64 28.65-64 64 28.65 64 64 64zm192 48H32c-17.67 0-32 14.33-32 32v32c0 17.67 14.33 32 32 32h384c17.67 0 32-14.33 32-32v-32c0-17.67-14.33-32-32-32z"></path></svg> <br/> .font140[ `$$\require{color}\displaystyle \begin{align} &L = \color{#FF0000}{\prod pc_{s,g,a,k}\cdot ne_{s,g,a}} \cdot L^{'}_{s,g,a,k} \prod L^{''}_{s,g,a}\nonumber\\ \nonumber\\ &L^{'}_{s,g,a,k} = \left\{\begin{array}{l} \Gamma(uc_{s,g,a,k} \vert \alpha_{y,g,a},\beta_{y,g,a}/c_{s,g,a}) \qquad if \; uc_{\cdot} = lc_{\cdot}\\\\ \displaystyle \int_{x=lc_{s,g,a,k}}^{uc_{s,g,a,k}} \Gamma(x \vert \alpha_{y,g,a},\beta_{y,g,a}/c_{s,g,a})dx \qquad if \; uc_{\cdot} > lc_{\cdot} \end{array}\right.\nonumber\\ \nonumber\\ &L^{''}_{s,g,a} = \mathcal{N}(pp_{s,g,a} \vert p_{y,g,a},pse_{s,g,a})\nonumber \end{align}$$` ] --- ## Smooth temporal trends <svg viewBox="0 0 448 512" style="height:1em;display:inline-block;fill:#561a34;position:fixed;top:38;right:50;" xmlns="http://www.w3.org/2000/svg"> <path d="M224 352c-35.35 0-64 28.65-64 64s28.65 64 64 64 64-28.65 64-64-28.65-64-64-64zm0-192c35.35 0 64-28.65 64-64s-28.65-64-64-64-64 28.65-64 64 28.65 64 64 64zm192 48H32c-17.67 0-32 14.33-32 32v32c0 17.67 14.33 32 32 32h384c17.67 0 32-14.33 32-32v-32c0-17.67-14.33-32-32-32z"></path></svg> <br/> .red[.center[Average consumption among drinkers]] `$$\alpha_{y,g,a}=\left(\frac{\mu_{y,g,a}}{sd_{y,g,a}}\right)^2 \qquad;\qquad \beta_{y,g,a}=\alpha_{y,g,a}/\mu_{y,g,a}$$` `$$\log(\mu_{y,g,a}) = \sum_{i=1}^{dc_1} \sum_{j=1}^{dc_2} s^{'}_{g,i,j} \Psi^{'}_i(year) \Phi^{'}_j(age) \qquad \forall g \in \{1,2\}$$` `$$c_{s,g,a} = c_{s}^{'} \cdot c_{g,a}^{''}$$` .red[.center[Proportion of drinkers]] `$$logit(p_{y,g,a}) = \sum_{i=1}^{dp_1} \sum_{j=1}^{dp_2} s^{''}_{g,i,j} \Psi^{''}_i(year) \Phi^{''}_j(age) \qquad \forall g \in \{1,2\}$$` --- ## (Soft) constraints/1<svg viewBox="0 0 448 512" style="height:1em;display:inline-block;fill:#561a34;position:fixed;top:38;right:50;" xmlns="http://www.w3.org/2000/svg"> <path d="M224 352c-35.35 0-64 28.65-64 64s28.65 64 64 64 64-28.65 64-64-28.65-64-64-64zm0-192c35.35 0 64-28.65 64-64s-28.65-64-64-64-64 28.65-64 64 28.65 64 64 64zm192 48H32c-17.67 0-32 14.33-32 32v32c0 17.67 14.33 32 32 32h384c17.67 0 32-14.33 32-32v-32c0-17.67-14.33-32-32-32z"></path></svg> <br/> <br/> <br/> .red[.center[Shape parameter &thickapprox; constant]] `$$\alpha_{y,g,a} = \sim \mathcal{N}(r_g,rs_g) \quad \forall y \in \{1,...Y\},\forall g \in \{1,2\},\forall a \in \{1,...A\}$$` <br/> .red[.center[Total consumption per capita matches the APC form administrative data]] `$$\sum_{g=1}^{2}\sum_{a=1}^{A} \mu_{y,g,a} \cdot pop_{y,g,a} \cdot p_{y,g,a} \sim \mathcal{N}((1-w) \cdot apc_y,apcse_y) \qquad \forall y \in \{1,...Y\}$$` --- class: hide_logo background-image: url(images/softbound.png) background-position: 25% 80% background-size: 30% ## (Soft) constraints/2<svg viewBox="0 0 448 512" style="height:1em;display:inline-block;fill:#561a34;position:fixed;top:38;right:50;" xmlns="http://www.w3.org/2000/svg"> <path d="M224 352c-35.35 0-64 28.65-64 64s28.65 64 64 64 64-28.65 64-64-28.65-64-64-64zm0-192c35.35 0 64-28.65 64-64s-28.65-64-64-64-64 28.65-64 64 28.65 64 64 64zm192 48H32c-17.67 0-32 14.33-32 32v32c0 17.67 14.33 32 32 32h384c17.67 0 32-14.33 32-32v-32c0-17.67-14.33-32-32-32z"></path></svg> <br/> .red[.center[Average daily consumption (very) unlikely above 150 g]] .pull-left[ $$\begin{align} f(x)= \begin{cases} \dfrac{0.975}{150} & x<150\\ \nonumber\\ 0.0250e^{-0.26(x-150)} & x>=150\nonumber \end{cases} \end{align}$$</div> ] .pull-right[ $$\begin{align} 97.5^{th}\: percentile = \beta_0 + \beta_1 \mu + \beta_2 \alpha + \beta_3 \mu \alpha\nonumber \end{align}$$ ] <img src = "images/approxquant.png" style = "position:absolute; left: 60%; top: 40%; width: 30%;"></img> <div style = "position:absolute; left: 70%; top: 70%; "> $$\begin{align} \begin{cases} \beta_0=3.259e^{-12}\\\nonumber \beta_0=6.397\\\nonumber \beta_0=-1.887e^{-12}\\\nonumber \beta_0=-2.884\\\nonumber \end{cases} \end{align}$$ </div> --- class: hide_logo background-image: url(images/stanlogo.jpg),url(images/rlogo.png),url(images/server.png),url(images/dot.png) background-position: 20% 25%,40% 25%,10% 70%, 95% 55% background-size: 10%, 10%,10%, 32% ## Implementation & Computation <svg viewBox="0 0 512 512" style="height:1em;display:inline-block;fill:#561a34;position:fixed;top:38;right:50;" xmlns="http://www.w3.org/2000/svg"> <path d="M173.898 439.404l-166.4-166.4c-9.997-9.997-9.997-26.206 0-36.204l36.203-36.204c9.997-9.998 26.207-9.998 36.204 0L192 312.69 432.095 72.596c9.997-9.997 26.207-9.997 36.204 0l36.203 36.204c9.997 9.997 9.997 26.206 0 36.204l-294.4 294.401c-9.998 9.997-26.207 9.997-36.204-.001z"></path></svg> <div style = "position:fixed; left: 22%; top: 50%; "> CPU: Intel® Xeon® E5-1650 v3@3.5GHz<br/> RAM: 16Gb RAM<br/> OS: Linux Ubuntu 20.0<br/> <br/> NUTS sampler <br/> 110 000 samples (60% discarded) </div> <div style = "position:fixed; left: 70%; top: 40%; font-size: 140%;"> For all parameters: <br/> R < 1.024 <br/> ESS > 539 <br/> MCSE < 5% <br/> </div> .footnote[StanDevelopmentTeam (2019), RCoreTeam (2019),] --- class: hide_logo background-image: url(images/log_post_1.png),url(images/log_post_2.png),url(images/log_post_3.png), url(images/ppcheck.png) background-position: 5% 25%,5% 55%,5% 85%, 85% 50% background-size: 40%,40%,40%,40%,30% ## Model checking <svg viewBox="0 0 512 512" style="height:1em;display:inline-block;fill:#561a34;position:fixed;top:38;right:50;" xmlns="http://www.w3.org/2000/svg"> <path d="M173.898 439.404l-166.4-166.4c-9.997-9.997-9.997-26.206 0-36.204l36.203-36.204c9.997-9.998 26.207-9.998 36.204 0L192 312.69 432.095 72.596c9.997-9.997 26.207-9.997 36.204 0l36.203 36.204c9.997 9.997 9.997 26.206 0 36.204l-294.4 294.401c-9.998 9.997-26.207 9.997-36.204-.001z"></path></svg> --- class: hide_logo background-image: url(images/time.png) background-position:50% 60% background-size: 45% ## Results/1 <svg viewBox="0 0 512 512" style="height:1em;display:inline-block;fill:#561a34;position:fixed;top:38;right:50;" xmlns="http://www.w3.org/2000/svg"> <path d="M496 384H64V80c0-8.84-7.16-16-16-16H16C7.16 64 0 71.16 0 80v336c0 17.67 14.33 32 32 32h464c8.84 0 16-7.16 16-16v-32c0-8.84-7.16-16-16-16zM464 96H345.94c-21.38 0-32.09 25.85-16.97 40.97l32.4 32.4L288 242.75l-73.37-73.37c-12.5-12.5-32.76-12.5-45.25 0l-68.69 68.69c-6.25 6.25-6.25 16.38 0 22.63l22.62 22.62c6.25 6.25 16.38 6.25 22.63 0L192 237.25l73.37 73.37c12.5 12.5 32.76 12.5 45.25 0l96-96 32.4 32.4c15.12 15.12 40.97 4.41 40.97-16.97V112c.01-8.84-7.15-16-15.99-16z"></path></svg> .footnote[Cois, Matzopoulos, Pillay-van Wyk, and Bradshaw (2021)] --- class: hide_logo background-image: url(images/age.png) background-position:50% 70% background-size: 80% ## Results/2 <svg viewBox="0 0 512 512" style="height:1em;display:inline-block;fill:#561a34;position:fixed;top:38;right:50;" xmlns="http://www.w3.org/2000/svg"> <path d="M496 384H64V80c0-8.84-7.16-16-16-16H16C7.16 64 0 71.16 0 80v336c0 17.67 14.33 32 32 32h464c8.84 0 16-7.16 16-16v-32c0-8.84-7.16-16-16-16zM464 96H345.94c-21.38 0-32.09 25.85-16.97 40.97l32.4 32.4L288 242.75l-73.37-73.37c-12.5-12.5-32.76-12.5-45.25 0l-68.69 68.69c-6.25 6.25-6.25 16.38 0 22.63l22.62 22.62c6.25 6.25 16.38 6.25 22.63 0L192 237.25l73.37 73.37c12.5 12.5 32.76 12.5 45.25 0l96-96 32.4 32.4c15.12 15.12 40.97 4.41 40.97-16.97V112c.01-8.84-7.15-16-15.99-16z"></path></svg> --- class: hide_logo background-image: url(images/cats.png) background-position:50% 60% background-size: 80% ## Results/3 <svg viewBox="0 0 512 512" style="height:1em;display:inline-block;fill:#561a34;position:fixed;top:38;right:50;" xmlns="http://www.w3.org/2000/svg"> <path d="M496 384H64V80c0-8.84-7.16-16-16-16H16C7.16 64 0 71.16 0 80v336c0 17.67 14.33 32 32 32h464c8.84 0 16-7.16 16-16v-32c0-8.84-7.16-16-16-16zM464 96H345.94c-21.38 0-32.09 25.85-16.97 40.97l32.4 32.4L288 242.75l-73.37-73.37c-12.5-12.5-32.76-12.5-45.25 0l-68.69 68.69c-6.25 6.25-6.25 16.38 0 22.63l22.62 22.62c6.25 6.25 16.38 6.25 22.63 0L192 237.25l73.37 73.37c12.5 12.5 32.76 12.5 45.25 0l96-96 32.4 32.4c15.12 15.12 40.97 4.41 40.97-16.97V112c.01-8.84-7.15-16-15.99-16z"></path></svg> --- class: hide_logo background-image: url(images/coverage1.png) background-position:50% 60% background-size: 60% ## Results/4 <svg viewBox="0 0 512 512" style="height:1em;display:inline-block;fill:#561a34;position:fixed;top:38;right:50;" xmlns="http://www.w3.org/2000/svg"> <path d="M496 384H64V80c0-8.84-7.16-16-16-16H16C7.16 64 0 71.16 0 80v336c0 17.67 14.33 32 32 32h464c8.84 0 16-7.16 16-16v-32c0-8.84-7.16-16-16-16zM464 96H345.94c-21.38 0-32.09 25.85-16.97 40.97l32.4 32.4L288 242.75l-73.37-73.37c-12.5-12.5-32.76-12.5-45.25 0l-68.69 68.69c-6.25 6.25-6.25 16.38 0 22.63l22.62 22.62c6.25 6.25 16.38 6.25 22.63 0L192 237.25l73.37 73.37c12.5 12.5 32.76 12.5 45.25 0l96-96 32.4 32.4c15.12 15.12 40.97 4.41 40.97-16.97V112c.01-8.84-7.15-16-15.99-16z"></path></svg> --- class: hide_logo ## Conclusions <svg viewBox="0 0 448 512" style="height:1em;display:inline-block;fill:#561a34;position:fixed;top:38;right:50;" xmlns="http://www.w3.org/2000/svg"> <path d="M400 32H48C21.5 32 0 53.5 0 80v352c0 26.5 21.5 48 48 48h352c26.5 0 48-21.5 48-48V80c0-26.5-21.5-48-48-48z"></path></svg> .pull-left[ - Plausible results - Credible intervals includes uncertainty due to APC estimates, distribution shape, consumtpion limits... - Relaxed assumptions regarding prevalence of drinkers and constant coverage - Full characterisation of the distribution - Flexibility ] -- .pull-right[ .center[ ## Future developments ] - Including a spatial dimension into the model - Covariates - Variable coverage across drinking categories - Computational efficiency <div style = "position: fixed; top: 270px; left: 59%; width: 40%;"><img src = "images/future.png"></img></div> ] --- class: hide_logo .pull-left[ # Credits .font80[ Richard Matzopoulos Debbie Bradshaw Colleagues of BODRU at SAMRC Rosana Pacella Charlotte Probst Charles Parry Nicole Vellio Katherine Sorsdahl Jurgen Rehm ] # Funding .font80[ This study has been partailly funded by the South African Medical Research Council (SAMRC) Flagship Awards Project SAMRC-RFAIFSP-01-2013/SA CRA 2. ] ] <div style = "text-align: right; position: fixed; right: 100px; top: 70%;"> <img src = "images/github.png" width = "85"></img> <br/> .font70[ This presentation is available from: <br/> <a href = "https://annibalecois,github.io/metaregression">https://annibaleaois.github.io/metaregression</a> ] </div> --- class: hide_logo ## References <br/> .font80[ Cois, A., R. Matzopoulos, V. Pillay-van Wyk, et al. (2021). "Bayesian modelling of population trends in alcohol consumption provides empirically based country estimates for South Africa". In: _Population Health Metrics_ 19.1, pp. 43-43. DOI: [10.1186/s12963-021-00270-3](https://doi.org/10.1186%2Fs12963-021-00270-3). URL: [https://doi.org/10.1186/s12963-021-00270-3](https://doi.org/10.1186/s12963-021-00270-3). Kehoe, T., G. Gmel, K. D. Shield, et al. (2012). "Determining the Best Population-Level Alcohol Consumption Model and Its Impact on Estimates of Alcohol-Attributable Harms". In: _Population health metrics_ 10.1, pp. 6-6. Probst, C., P. A. Shuper, and J. Rehm (2017). "Coverage of Alcohol Consumption by National Surveys in South Africa". In: _Addiction_ 112.4, pp. 705-710-705-710. DOI: [10.1111/add.13692](https://doi.org/10.1111%2Fadd.13692). RCoreTeam (2019). "R: A Language and Environment for Statistical Computing v 3.6". . Publisher: R Foundation for Statistical Computing. Rehm, J., T. Kehoe, G. Gmel, et al. (2010). "Statistical Modeling of Volume of Alcohol Exposure for Epidemiological Studies of Population Health: The US Example". In: _Population Health Metrics_ 8.1, pp. 3-3. DOI: [10.1186/1478-7954-8-3](https://doi.org/10.1186%2F1478-7954-8-3). StanDevelopmentTeam (2019). "Stan Modeling Language: User's Guide and Reference Manual. Version 2.19.0." URL: [http://mc-stan.org](http://mc-stan.org). WHO (2018). _Global status report on alcohol and health 2018_. World Health Organization. URL: [https://apps.who.int/iris/bitstream/handle/10665/274603/9789241565639-eng.pdf?ua=1](https://apps.who.int/iris/bitstream/handle/10665/274603/9789241565639-eng.pdf?ua=1). ]