You are here:
Vanderbilt Biostatistics Wiki
>
Main Web
>
Education
>
StatGraphCourse
>
RCTGraphics
(26 Nov 2019,
FrankHarrell
)
(raw view)
E
dit
A
ttach
---+ Graphics for Clinical Trials ---++ <small>Frank E Harrell Jr<br>Vanderbilt Department of Biostatistics<br>Office of Biostatistics FDA CDER</small> ---++ <small>DIA/FDA Statistics Forum, North Bethesda MD, 2017-04-24</small> In the never-ending quest to replace tables with graphics, new graphics solutions to common data display problems in clinical trials are becoming available. This short course will focus on high-information graphics that faithfully convey characteristics of data and summary statistics using such tools as extended box plots, dot charts, and spike histograms. With the rapid evolution of HTML5 and html notebooks, new possibilities now exist, and graphics can be less cluttered with more information made available by merely hovering with the mouse or clicking the legend to activate the display of additional data layers. Some of the learning objectives of this course are * learn principles of graph construction * learn which features of summary statistics should be emphasized in a graph * see examples of increasing information using modern graphics, whether static or interactive * understand features of html notebooks for statistical reports * learn how to use =RStudio= to make html notebooks * learn to use new functions in the R =Hmisc= package which use the R =plotly= package to produce somewhat interactive graphics * get ideas for constructing your own interactive graphics for statistical reports by seeing examples of placing supplemental information in initially hidden layers of graphics ---+++ Big Picture Graphics are generally excellent for * providing a more interpretable snapshot of study results * displaying trends and finding patterns * speeding up reviews * displaying data that are too messy to model (e.g., sites within countries within regions) * displaying marginal (unadjusted) estimates * replacing tables having many numbers, especially when continuous variables are involved * showing whole distribution of continuous variables * finding data problems * finding problematic data distributions including excessive ties * displaying results of complex statistical models Tables used to be good for * displaying finest levels of details * providing exact numeric values for elements of graphs This can now be better done by drilling down on a graph. In many cases, statistical models are the best descriptive statistics: * best way to handle confounding and outcome heterogeneity * accounts for more variables than any expert could understand in a graph * handles continuous variables optimally * handles censoring, incomplete data, large datasets, and heavy ties in data ---++ Course Material * [[https://www.youtube.com/watch?v=fSgEeI2Xpdc][Applying Human Factors Research to Statistical Graphics]] by John Rauser * %N% [[https://wbuchanan.github.io/nnerppDataVisualization][Guiding Principles for Effective Data Visualization]] by William Buchanan * %N% [[https://www.knowablemagazine.org/article/mind/2019/science-data-visualization][Why Scientists Need to be Better at Data Visualization]] by Betsy Mason * [[http://hbiostat.org/doc/graphscourse.pdf][Principles of Graph Construction]] (see Sections 2.4 and 2.5 for examples related to drug safety) * [[http://hbiostat.org/talks/greport.pdf][Clinical Trial Reports: R+LaTeX+pdf]] * Two [[http://hbiostat.org/R/greport][example reports]] with source files * See also [[Greport][this]] * [[http://hbiostat.org/talks/nextgenReports.html][R + =RStudio= + =Rmarkdown= + =knitr= + =plotly= + html]] * [[http://hbiostat.org/R/Hmisc/examples.html][R =Hmisc= package examples]] * [[http://hbiostat.org/R/rms/examples.html][R =rms= package examples]] (includes plots of predicted values + interactive survival curves) * R =hreport= package: html Clinical Trial Reports: * [[http://hbiostat.org/R/hreport/test.html Example report 1]] * [[http://hbiostat.org/R/hreport/report.html Example report 2]] * <small>(under development; funded by !NIH !NCATS !CTSA Vanderbilt Institute for Clinical and Translational Research)</small> * [[http://biostatdata.app.vumc.org/fh/R/other/safetyExplorer.nb.html][Safety Explorer example]] (Rmarkdown html notebook)<br><small>Authors: Becca Krouse, Spencer Childress, Jeremy Wildfire<br>Rho, Inc.</small> ----- ---++ Links * [[http://biostatdata.app.vumc.org/fh/talks/RCTGraphics/RCTGraphics.zip][Zip file containing all files above]] * [[https://github.com/RhoInc/safetyexploreR/wiki][Safety Explorer]] - this can be used in conjunction with the =hreport= package, =knitr=, and =RStudio= to produce highly interactive tables with small graphics, will drill-down capability from body systems to preferred terms within body systems. A self-contained =html= report can be produced, and the user interacts without installing any software or using an internet connection. * [[https://jenthompson.me/2018/02/09/flexdashboards-monitoring Flex dashboards]] for monitoring clinical studies * [[https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3638193 Presentation of clinical laboratory results: an experimental comparison of four visualization techniques]] * %N% [[https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5333215 Novel clinical trial graphics]] by Song, Hsu, Taira * %N% [[https://academic.oup.com/jamia/article/25/8/1069/4951737 Tendril plots]] for AEs * [[https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2995657 The design and evaluation of a graphical display for laboratory data]] * [[https://www.cs.tufts.edu/~nr/cs257/archive/edward-tufte/Graphical%20Summary%20of%20Patient.pdf Graphical summary of patient status]] by Powsner and Tufte * http://www.datavisualisation-r.com/ * [[http://biostat.mc.vanderbilt.edu/wiki/pub/Main/StatGraphCourse/TEB.pdf][Effective Displays of Data Need More Attention in Statistics Education]] by Thomas Bradstreet, Michael Nessly, and Thomas Short * [[http://biostat.mc.vanderbilt.edu/wiki/pub/Main/StatGraphCourse/levine.pdf][Graphics for Clinical Trials]] by Jonathan Levine * [[http://biostat.mc.vanderbilt.edu/wiki/pub/Main/FHHandouts/gsksafety.pdf][Exploratory Analysis of Clinical Safety Data to Detect Safety Signals]] (Frank Harrell and Thomas Burgan). * http://motioninsocial.com/tufte/ * [[https://graphicsprinciples.github.io][Graphics Principles Cheat Sheet]] * Schwarz' [[http://people.stat.sfu.ca/~cschwarz/Stat-650/Notes/PDF/ChapterBadgraphs.pdf][Tour of Bad Graphs]] * https://www.rstudio.com * http://rmarkdown.rstudio.com * http://rmarkdown.rstudio.com/r_notebooks.html * http://yihui.name/knitr/ * http://biostat.mc.vanderbilt.edu/Hmisc * http://biostat.mc.vanderbilt.edu/Rrms * https://plot.ly/r * https://plot.ly/r/getting-started * ggplotly: a function that converts any ggplot2 graphic to a plotly interactive graphic: https://plot.ly/ggplot2 * [[https://github.com/harrelfe?tab=repositories][Github Repositories]] ----- ---++ DIA/ASA Biopharm Safety Graphics Working Group * Organization: https://github.com/ASA-DIA-InteractiveSafetyGraphics * eDish Repo with readme: https://github.com/ASA-DIA-InteractiveSafetyGraphics/safety-eDISH * Interactive eDish example: https://asa-dia-interactivesafetygraphics.github.io/safety-eDISH/test/ ----- ---++ Fundamentals * Color palettes: https://www.data-imaginist.com/2018/scico-and-the-colour-conundrum * Color choices and response times: https://idl.cs.washington.edu/files/2018-QuantitativeColor-CHI.pdf * [[http://ejb.github.io/2018/06/03/interactives.html What interactives can do (that articles can't)]] by Elliot Bentley * [[http://socviz.co Data Visualization]] by Kieran Healy
E
dit
|
A
ttach
|
P
rint version
|
H
istory
: r28
<
r27
<
r26
<
r25
|
B
acklinks
|
V
iew topic
|
Edit
w
iki text
|
M
ore topic actions
Topic revision: r28 - 26 Nov 2019,
FrankHarrell
Main
Department Home Page
Biostatistics Graduate Program
Vanderbilt University Medical Center
Main Web
Main Web Home
Search
Recent Changes
Changes
Topic list
Biostatistics Webs
Archive
Main
Sandbox
System
Register
|
Log In
Copyright © 2013-2022 by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding Vanderbilt Biostatistics Wiki?
Send feedback