• Should responder analyses be conducted on continuous outcomes?

    Type Journal Article
    Author Robert Abugov
    Author Jennifer Clark
    Author Laura Higginbotham
    Author Feng Li
    Author Lei Nie
    Author David Reasner
    Author Mark Rothmann
    Author Xin Yuan
    Author John Sharretts
    URL https://onlinelibrary.wiley.com/doi/abs/10.1002/pst.2273
    Volume n/a
    Issue n/a
    Publication Pharmaceutical Statistics
    ISSN 1539-1612
    Extra _eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1002/pst.2273
    DOI 10.1002/pst.2273
    Accessed 11/24/2022, 6:48:06 AM
    Library Catalog Wiley Online Library
    Language en
    Abstract Continuous outcomes are often dichotomized to classify trial subjects as responders or nonresponders, with the difference in rates of response between treatment and control defined as the “responder effect.” In this article, we caution that dichotomization of continuous interval outcomes may not be best practice. Defining clinical benefit or harm for continuous interval outcomes as the difference between the means of treatment and control, that is, the “continuous treatment effect,” we examine the case where treatment and control outcomes are normally distributed and differ only in location. For this case, continuous treatment effects may be considered clinically relevant if they exceed a prespecified minimum clinically important difference. In contrast, using minimum clinically important differences as dichotomization thresholds will not ensure clinically relevant responder effects. For example, in some situations, increasing the threshold may actually relax the criterion for effectiveness by increasing the calculated responder effect. Using responder effects to quantitatively assess benefit or risk of investigational drugs for continuous interval outcomes presents interpretational challenges. In particular, when the dichotomization threshold is halfway between the treatment and control outcome means, the responder effect is at a maximum with a magnitude monotonically related to the number of standard deviations between the mean outcomes of treatment and control. Large responder effect benefits may therefore reflect clinically unimportant continuous treatment effects amplified by small standard deviations, and small responder effect risks may reflect either clinically important continuous treatment effects minimized by large standard deviations, or selection of a dichotomization threshold not providing maximum responder effect.
    Date Added 11/24/2022, 6:48:06 AM
    Modified 11/24/2022, 6:55:25 AM

    Tags:

    • categorization
    • cutpoint
    • dichotimizing-continuous-variables
    • dichotomization
    • rct
    • responder-analysis
    • teaching
    • teaching-mds

  • Discarding Dichotomization: Retrieving Data in the Service of Patient Care

    Type Journal Article
    Author Alan L. Hutchison
    Author Adam S. Cifu
    Author Anjana A. Pillai
    URL https://onlinelibrary.wiley.com/doi/abs/10.1002/cld.1159
    Volume 19
    Issue 1
    Pages 12-16
    Publication Clinical Liver Disease
    ISSN 2046-2484
    Date 2022
    Extra _eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1002/cld.1159
    DOI 10.1002/cld.1159
    Accessed 1/26/2022, 2:53:47 PM
    Library Catalog Wiley Online Library
    Language en
    Abstract Content available: Author Interview and Audio Recording
    Short Title Discarding Dichotomization
    Date Added 1/26/2022, 2:53:47 PM
    Modified 1/26/2022, 2:55:09 PM

    Tags:

    • teaching-mds
    • cutpoints
    • dichotomization
    • categorization
    • cutpoint
    • medical
    • information-loss

  • Consequences of dichotomization

    Type Journal Article
    Author Valerii Fedorov
    Author Frank Mannino
    Author Rongmei Zhang
    URL http://dx.doi.org/10.1002/pst.331
    Volume 8
    Pages 50-61
    Publication Pharm Stat
    Date 2009
    Extra Citation Key: fed09con tex.citeulike-article-id= 13265728 tex.citeulike-attachment-1= fed09con.pdf; /pdf/user/harrelfe/article/13265728/1027987/fed09con.pdf; 7e1edf1558bbca47ebed9e0ccb36ec439f5e402d tex.citeulike-linkout-0= http://dx.doi.org/10.1002/pst.331 tex.posted-at= 2014-07-14 14:10:03 tex.priority= 0
    DOI 10.1002/pst.331
    Date Added 7/7/2018, 1:38:33 PM
    Modified 11/8/2019, 8:01:59 AM

    Tags:

    • teaching-mds
    • cutpoints
    • graphics
    • dichotomization
    • response
    • continuous-variables
    • categorization-of-outcome-variable
    • loss-of-information
    • loss-of-power
    • theoretical-calculations

    Notes:

    • optimal cutpoint depends on unknown parameters;should only entertain dichotomization when "estimating a value of the cumulative distribution and when the assumed model is very different from the true model";nice graphics

  • The concept of residual confounding in regression models and some applications

    Type Journal Article
    Author Heiko Belcher
    Volume 11
    Pages 1747-1758
    Publication Stat Med
    Date 1992
    Extra Citation Key: bec92con tex.citeulike-article-id= 13263733 tex.posted-at= 2014-07-14 14:09:22 tex.priority= 0
    Date Added 7/7/2018, 1:38:33 PM
    Modified 11/8/2019, 8:01:59 AM

    Tags:

    • teaching-mds
    • confounding
    • cutpoints
    • categorizing-continuous-variables
    • information-loss

  • Problems in defining cutoff points of continuous prognostic factors: Example of tumor thickness in primary cutaneous melanoma

    Type Journal Article
    Author Petra Buettner
    Author Claus Garbe
    Author Irene Guggenmoos-Holzmann
    Volume 50
    Pages 1201-1210
    Publication J Clin Epi
    Date 1997
    Extra Citation Key: bue97pro tex.citeulike-article-id= 13263825 tex.posted-at= 2014-07-14 14:09:23 tex.priority= 0
    Date Added 7/7/2018, 1:38:33 PM
    Modified 11/8/2019, 8:01:59 AM

    Tags:

    • teaching-mds
    • cutpoints

    Notes:

    • choice of cut point depends on marginal distribution of predictor

  • Dichotomizing continuous outcome variables: Dependence of the magnitude of association and statistical power on the cutpoint

    Type Journal Article
    Author D. R. Ragland
    URL http://dx.doi.org/10.1097/00001648-199209000-00009
    Volume 3
    Pages 434-440
    Publication Epi
    Date 1992
    Extra Citation Key: rag92dic tex.citeulike-article-id= 13264722 tex.citeulike-linkout-0= http://dx.doi.org/10.1097/00001648-199209000-00009 tex.posted-at= 2014-07-14 14:09:40 tex.priority= 0 See letters to editor May 1993 P. 274-, Vol 4 No. 3
    DOI 10.1097/00001648-199209000-00009
    Date Added 7/7/2018, 1:38:33 PM
    Modified 11/8/2019, 8:01:59 AM

    Tags:

    • teaching-mds
    • cutpoints
    • categorization-of-continuous-variables

  • Quantifying the impact of different approaches for handling continuous predictors on the performance of a prognostic model

    Type Journal Article
    Author Gary S. Collins
    Author Emmanuel O. Ogundimu
    Author Jonathan A. Cook
    Author Yannick L. Manach
    Author Douglas G. Altman
    URL http://dx.doi.org/10.1002/sim.6986
    Volume 35
    Issue 23
    Pages 4124-4135
    Publication Stat Med
    ISSN 02776715
    Date 2016-10
    Extra Citation Key: col16qua tex.citeulike-article-id= 14257702 tex.citeulike-attachment-1= col16qua.pdf; /pdf/user/harrelfe/article/14257702/1098563/col16qua.pdf; 777d21c7dafcffd5012b9f8f9928c2aeac69dcbd tex.citeulike-linkout-0= http://dx.doi.org/10.1002/sim.6986 tex.day= 15 tex.posted-at= 2017-01-19 01:17:02 tex.priority= 4
    DOI 10.1002/sim.6986
    Date Added 7/7/2018, 1:38:33 PM
    Modified 11/8/2019, 8:01:59 AM

    Tags:

    • teaching-mds
    • cutpoints
    • categorizing-continuous-variables
    • dichotomization
    • categorization

    Notes:

    • used rms package hazard regression method (hare) for survival model calibration

  • Against quantiles: categorization of continuous variables in epidemiologic research, and its discontents

    Type Journal Article
    Author Caroline Bennette
    Author Andrew Vickers
    URL http://dx.doi.org/10.1186/1471-2288-12-21
    Volume 12
    Issue 1
    Pages 21+
    Publication BMC Med Res Methodol
    ISSN 1471-2288
    Date 2012-02
    Extra Citation Key: ben12aga tex.citeulike-article-id= 10398554 tex.citeulike-attachment-1= ben12aga.pdf; /pdf/user/harrelfe/article/10398554/1105032/ben12aga.pdf; 30d8b922169fca1fda79552f2539c4c5b4a6a32f tex.citeulike-linkout-0= http://dx.doi.org/10.1186/1471-2288-12-21 tex.citeulike-linkout-1= http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3353173/ tex.citeulike-linkout-2= http://view.ncbi.nlm.nih.gov/pubmed/22375553 tex.citeulike-linkout-3= http://www.hubmed.org/display.cgi?uids=22375553 tex.day= 29 tex.pmcid= PMC3353173 tex.pmid= 22375553 tex.posted-at= 2017-03-18 15:24:49 tex.priority= 0
    DOI 10.1186/1471-2288-12-21
    Abstract Quantiles are a staple of epidemiologic research: in contemporary epidemiologic practice, continuous variables are typically categorized into tertiles, quartiles and quintiles as a means to illustrate the relationship between a continuous exposure and a binary outcome. In this paper we argue that this approach is highly problematic and present several potential alternatives. We also discuss the perceived drawbacks of these newer statistical methods and the possible reasons for their slow adoption by epidemiologists. The use of quantiles is often inadequate for epidemiologic research with continuous variables.
    Date Added 7/7/2018, 1:38:33 PM
    Modified 11/8/2019, 8:01:59 AM

    Tags:

    • teaching-mds
    • cutpoints
    • dichotomization
    • categorization
    • epidemiology

    Notes:

    • terrific graphical examples; nice display of outcome heterogeneity within quantile groups of PSA

  • Analysis by categorizing or dichotomizing continuous variables is inadvisable: An example from the natural history of unruptured aneurysms

    Type Journal Article
    Author O. Naggara
    Author J. Raymond
    Author F. Guilbert
    Author D. Roy
    Author A. Weill
    Author D. G. Altman
    URL http://www.ajnr.org/content/32/3/437.abstract
    Volume 32
    Issue 3
    Pages 437-440
    Publication Am J Neuroradiol
    Date 2011
    Extra Citation Key: nag11ana tex.citeulike-article-id= 13265917 tex.citeulike-linkout-0= http://dx.doi.org/10.3174/ajnr.A2425 tex.citeulike-linkout-1= http://www.ajnr.org/content/32/3/437.abstract tex.posted-at= 2014-07-14 14:10:07 tex.priority= 0
    DOI 10.3174/ajnr.A2425
    Abstract In medical research analyses, continuous variables are often converted into categoric variables by grouping values into ≥2 categories. The simplicity achieved by creating ≥2 artificial groups has a cost: Grouping may create rather than avoid problems. In particular, dichotomization leads to a considerable loss of power and incomplete correction for confounding factors. The use of data-derived "optimal" cut-points can lead to serious bias and should at least be tested on independent observations to assess their validity. Both problems are illustrated by the way the results of a registry on unruptured intracranial aneurysms are commonly used. Extreme caution should restrict the application of such results to clinical decision-making. Categorization of continuous data, especially dichotomization, is unnecessary for statistical analysis. Continuous explanatory variables should be left alone in statistical models.
    Date Added 7/7/2018, 1:38:33 PM
    Modified 11/8/2019, 8:01:59 AM

    Tags:

    • teaching-mds
    • cutpoints

  • Confidence intervals for the effect of a prognostic factor after selection of an `optimal' cutpoint

    Type Journal Article
    Author Norbert Holländer
    Author Willi Sauerbrei
    Author Martin Schumacher
    URL http://dx.doi.org/10.1002/sim.1611
    Volume 23
    Pages 1701-1713
    Publication Stat Med
    Date 2004
    Extra Citation Key: hol04con tex.citeulike-article-id= 13265374 tex.citeulike-linkout-0= http://dx.doi.org/10.1002/sim.1611 tex.posted-at= 2014-07-14 14:09:55 tex.priority= 0
    DOI 10.1002/sim.1611
    Date Added 7/7/2018, 1:38:33 PM
    Modified 11/8/2019, 8:01:59 AM

    Tags:

    • teaching-mds
    • cutpoints
    • categorization

    Notes:

    • true type I error can be much greater than nominal level;one example where nominal is 0.05 and true is 0.5;minimum P-value method;CART;recursive partitioning;bootstrap method for correcting confidence interval;based on heuristic shrinkage coefficient;"It should be noted, however, that the optimal cutpoint approach has disadvantages. One of these is that in almost every study where this method is applied, another cutpoint will emerge. This makes comparisons across studies extremely difficult or even impossible. Altman et al. point out this problem for studies of the prognostic relevance of the S-phase fraction in breast cancer published in the literature. They identified 19 different cutpoints used in the literature; some of them were solely used because they emerged as the `optimal' cutpoint in a specific data set. In a meta-analysis on the relationship between cathepsin-D content and disease-free survival in node-negative breast cancer patients, 12 studies were in included with 12 different cutpoints ... Interestingly, neither cathepsin-D nor the S-phase fraction are recommended to be used as prognostic markers in breast cancer in the recent update of the American Society of Clinical Oncology."; dichotomization; categorizing continuous variables; refs alt94dan, sch94out, alt98sub

  • Odds ratios for a continuous outcome variable without dichotomizing

    Type Journal Article
    Author Barry K. Moser
    Author Laura P. Coombs
    Volume 23
    Pages 1843-1860
    Publication Stat Med
    Date 2004
    Extra Citation Key: mos04odd tex.citeulike-article-id= 13265376 tex.posted-at= 2014-07-14 14:09:55 tex.priority= 0
    Date Added 7/7/2018, 1:38:33 PM
    Modified 11/8/2019, 8:01:59 AM

    Tags:

    • teaching-mds
    • cutpoints
    • categorization
    • cutpoint
    • dichotomizing-continuous-response-variable
    • response

    Notes:

    • large loss of efficiency and power;embeds in a logistic distribution, similar to proportional odds model;categorization;dichotomization of a continuous response in order to obtain odds ratios often results in an inflation of the needed sample size by a factor greater than 1.5

  • Suboptimal analysis using `optimal' cutpoints

    Type Journal Article
    Author Douglas G. Altman
    Volume 78
    Pages 556-557
    Publication Brit J Cancer
    Date 1998
    Extra Citation Key: alt98sub tex.citeulike-article-id= 13265377 tex.posted-at= 2014-07-14 14:09:55 tex.priority= 0
    Date Added 7/7/2018, 1:38:33 PM
    Modified 11/8/2019, 8:01:59 AM

    Tags:

    • teaching-mds
    • cutpoints
    • categorization
    • dichotomizing-continuous-variables

  • Dichotomizing continuous predictors in multiple regression: a bad idea

    Type Journal Article
    Author Patrick Royston
    Author Douglas G. Altman
    Author Willi Sauerbrei
    URL http://dx.doi.org/10.1002/sim.2331
    Volume 25
    Pages 127-141
    Publication Stat Med
    Date 2006
    Extra Citation Key: roy06dic tex.citeulike-article-id= 13265458 tex.citeulike-linkout-0= http://dx.doi.org/10.1002/sim.2331 tex.posted-at= 2014-07-14 14:09:57 tex.priority= 0
    DOI 10.1002/sim.2331
    Date Added 7/7/2018, 1:38:33 PM
    Modified 11/8/2019, 8:01:59 AM

    Tags:

    • teaching-mds
    • cutpoints
    • dichotomization
    • categorization
    • regression
    • clinical-research
    • continuous-covariates
    • efficiency
    • residual-confounding

    Notes:

    • destruction of statistical inference when cutpoints are chosen using the response variable; varying effect estimates when change cutpoints;difficult to interpret effects when dichotomize;nice plot showing effect of categorization; PBC data

  • Finding what is not there through the unfortunate binning of results: The Mendel effect

    Type Journal Article
    Author Howard Wainer
    Volume 19
    Issue 1
    Pages 49-56
    Publication Chance
    Date 2006
    Extra Citation Key: wai06fin tex.citeulike-article-id= 13265473 tex.posted-at= 2014-07-14 14:09:57 tex.priority= 0
    Date Added 7/7/2018, 1:38:33 PM
    Modified 11/8/2019, 8:01:59 AM

    Tags:

    • teaching-mds
    • cutpoints
    • bad

    Notes:

    • can find bins that yield either positive or negative association;especially pertinent when effects are small;"With four parameters, I can fit an elephant; with five, I can make it wiggle its trunk." - John von Neumann

  • Bivariate median splits and spurious statistical significance

    Type Journal Article
    Author S. E. Maxwell
    Author H. D. Delaney
    URL http://dx.doi.org/10.1037//0033-2909.113.1.181
    Volume 113
    Pages 181-190
    Publication Psych Bull
    Date 1993
    Extra Citation Key: max93biv tex.citeulike-article-id= 13265286 tex.citeulike-linkout-0= http://dx.doi.org/10.1037//0033-2909.113.1.181 tex.posted-at= 2014-07-14 14:09:53 tex.priority= 0
    DOI 10.1037//0033-2909.113.1.181
    Date Added 7/7/2018, 1:38:33 PM
    Modified 11/8/2019, 8:01:59 AM

    Tags:

    • teaching-mds
    • cutpoints
    • dichotomization
    • categorization-of-continuous-variables

  • Outcome-oriented cutpoints in quantitative exposure

    Type Journal Article
    Author G. Schulgen
    Author B. Lausen
    Author J. Olsen
    Author M. Schumacher
    Volume 120
    Pages 172-184
    Publication Am J Epi
    Date 1994
    Extra Citation Key: sch94out tex.citeulike-article-id= 13265375 tex.posted-at= 2014-07-14 14:09:55 tex.priority= 0
    Date Added 7/7/2018, 1:38:33 PM
    Modified 11/8/2019, 8:01:59 AM

    Tags:

    • teaching-mds
    • cutpoints
    • categorizing-continuous-variables
    • dichotomization

  • Binary regression with continuous outcomes

    Type Journal Article
    Author Samy Suissa
    Author Lucie Blais
    URL http://dx.doi.org/10.1002/sim.4780140303
    Volume 14
    Pages 247-255
    Publication Stat Med
    Date 1995
    Extra Citation Key: sui94bin tex.citeulike-article-id= 13264922 tex.citeulike-linkout-0= http://dx.doi.org/10.1002/sim.4780140303 tex.posted-at= 2014-07-14 14:09:45 tex.priority= 0
    DOI 10.1002/sim.4780140303
    Date Added 7/7/2018, 1:38:33 PM
    Modified 11/8/2019, 8:01:59 AM

    Tags:

    • teaching-mds
    • cutpoints
    • categorizing-continuous-variables

  • Practical p-value adjustment for optimally selected cutpoints

    Type Journal Article
    Author S. G. Hilsenbeck
    Author G. M. Clark
    Volume 15
    Pages 103-112
    Publication Stat Med
    Date 1996
    Extra Citation Key: hil96pra tex.citeulike-article-id= 13264296 tex.posted-at= 2014-07-14 14:09:32 tex.priority= 0
    Date Added 7/7/2018, 1:38:33 PM
    Modified 11/8/2019, 8:01:59 AM

    Tags:

    • teaching-mds
    • cutpoints
    • dichotimizing-continuous-variables

  • Evaluating the effect of optimized cutoff values in the assessment of prognostic factors

    Type Journal Article
    Author B. Lausen
    Author M. Schumacher
    URL http://dx.doi.org/10.1016/0167-9473(95)00016-X
    Volume 21
    Issue 3
    Pages 307-326
    Publication Comp Stat Data Analysis
    Date 1996
    Extra Citation Key: lau96eva tex.citeulike-article-id= 13264466 tex.citeulike-linkout-0= http://dx.doi.org/10.1016/0167-9473(95)00016-X tex.posted-at= 2014-07-14 14:09:36 tex.priority= 0
    DOI 10.1016/0167-9473(95)00016-X
    Date Added 7/7/2018, 1:38:33 PM
    Modified 11/8/2019, 8:01:59 AM

    Tags:

    • teaching-mds
    • cutpoints
    • dichotomizing-continuous-variables

  • Categorising continuous covariates (letter to the editor)

    Type Journal Article
    Author D. G. Altman
    Volume 64
    Pages 975
    Publication Brit J Cancer
    Date 1991
    Extra Citation Key: alt91cat tex.citeulike-article-id= 13263691 tex.posted-at= 2014-07-14 14:09:21 tex.priority= 0
    Date Added 7/7/2018, 1:38:33 PM
    Modified 11/8/2019, 8:01:59 AM

    Tags:

    • teaching-mds
    • cutpoints
    • dichotomizing-continuous-variables

  • Dangers of using `optimal' cutpoints in the evaluation of prognostic factors

    Type Journal Article
    Author D. G. Altman
    Author B. Lausen
    Author W. Sauerbrei
    Author M. Schumacher
    Volume 86
    Pages 829-835
    Publication J Nat Cancer Inst
    Date 1994
    Extra Citation Key: alt94dan tex.citeulike-article-id= 13263692 tex.posted-at= 2014-07-14 14:09:21 tex.priority= 0
    Date Added 7/7/2018, 1:38:33 PM
    Modified 11/8/2019, 8:01:59 AM

    Tags:

    • teaching-mds
    • cutpoints
    • dichotomizing-continuous-variables

  • A simulation study of cross-validation for selecting an optimal cutpoint in univariate survival analysis

    Type Journal Article
    Author David Faraggi
    Author Richard Simon
    Volume 15
    Pages 2203-2213
    Publication Stat Med
    Date 1996
    Extra Citation Key: far96sim tex.citeulike-article-id= 13264063 tex.posted-at= 2014-07-14 14:09:28 tex.priority= 0
    Date Added 7/7/2018, 1:38:33 PM
    Modified 11/8/2019, 8:01:59 AM

    Tags:

    • teaching-mds
    • cutpoints
    • information-loss

    Notes:

    • bias in point estimate of effect from selecting cutpoints based on P-value; loss of information from dichotomizing continuous predictors