Category: Academics
“I think the author of this post should study more Periodontics, and not only statistics…”
When I got a comment with that sentence (on a blogpost on Clinical Relevance and Confusion about the P-value) I actually had to smile. What a misconception! Isn’t it so that clinicians need to (in fact must) study more statistics in order to avoid becoming victims of unsubstantiated claims, being made by industry, crooks or uninformed thought leaders. Or erroneously fall for what was seemingly logic?
During my career as a periodontists, dedicated teacher and curious scientist I had always welcomed biostatisticians who did not get tired to warn me, teach me and guide, even help, me when it came to the analysis of periodontal data. And these were actually quite special (the data), and treating them statistically utterly demanding as they were sampled, in multitude, from the oral cavities of our patients. I had lately even dedicated a lengthy blogpost to the respective myths and mysteries.
In 2004, one of my studies conducted when at Heidelberg University was cited as a negative example. In one table, I had regressed percent change and difference between baseline and post treatment scores on baseline scores. When using original data of two published studies (not mine), Tu et al. (2004) made clear that, “[u]se of ratio variables seriously violated the assumptions underpinning the statistical methods utilised […], and consequently […] conclusions were [commonly] substantially misleading.” The topics of ratio variables, mathematical coupling, or collinearity found in regression analyses not only in the dental field, as well as the phenomenon of regression towards the mean had apparently drawn the authors’ attention which led to a series of papers over the next 10 years or so, see, for instance, some results found in GoogleScholar.
Continue readingSubmit What is Hot and Get it Accepted
Update September 15, 2013 below
The most frequently visited science integrity watchdogs and post publication discussion sites (Retractionwatch, Science Integrity Digest, PubPeer etc.) have so far missed an honest confession of a young climate scientist who was lucky enough to publish in Nature and writes, in an article published in The Free Press,
I Left Out the Full Truth to get My Climate Change Paper Published.
Patrick T. Brown, who has apparently left his institution in the meantime and even Academia at large over much frustation (which he explains in his The Free Press article) claims that, only because he stuck to a common narrative (about wildfires and climate change), he got his paper published. The Nature article is behind a paywall, so I can’t check it. From its Abstract,
So far, anthropogenic warming has enhanced the aggregate expected frequency of extreme daily wildfire growth by 25% (5–95 range of 14–36%), on average, relative to preindustrial conditions. But for some fires, there was approximately no change, and for other fires, the enhancement has been as much as 461%. When historical fires are subjected to a range of projected end-of-century conditions, the aggregate expected frequency of extreme daily wildfire growth events increases by 59% (5–95 range of 47–71%) under a low SSP1–2.6 emissions scenario compared with an increase of 172% (5–95 range of 156–188%) under a very high SSP5–8.5 emissions scenario, relative to preindustrial conditions.
Brown, P.T., Hanley, H., Mahesh, A. et al. Climate warming increases extreme daily wildfire growth risk in California. Nature (2023). https://doi.org/10.1038/s41586-023-06444-3
In his The Free Press article, Brown explains,
Continue readingMild Criticism of the New Staging and Grading System of Periodontitis
Exactly five years too late appeared a critical appraisal of the 2017 AAP/EFP consensus for a new classification of periodontitis by Raittio and Baelum (2023). The two authors came apparently across a checklist (Doust et al. 2017) of the same year the AAP/EFP World Workshop took place, which was supposed to provide guidelines in case an established disease was to be modified. The checklist (Doust et al. 2017) aims were as follows:
- To delineate the precise distinction between the previous and the new definition
- To estimate the changes to prevalence and incidence following from a new definition
- To be clear and open about the trigger(s) for the proposed new definition
- To assess the changes in prognostic ability resulting from the implementation of a new definition
- To estimate the repeatability, reproducibility and accuracy of the new definition
- To be clear about the incremental benefit to patients of being diagnosed according to the new definition
- To be clear about the incremental harms to patients being diagnosed according to the new definition
- To assess the net benefits and net harms of a applying a new definition rather than the current.
Although the AAP/EFP World Workshop on the new classification took place in November 2017, it obviously did not consider the above checklist. I would assume, however, that some participants of the workshop, in particular those in charge of preparing the position papers, could have come across the July 2017 publication by Doust et al. Anyway, in 2018 , when the proceedings were finally published in 23 articles as supplements in both the J Periodontol and J Clin Periodontol, the paper by Doust et al. was not cited in any paper.
Thus, the recent endeavor by Raitto and Baelum (2023) may not even be too late but also in vain.
Let’s consider some of the items in detail.
Continue readingPeriodontal Myths and Mysteries Series (XI) – Aggregate Vs. Site-specific Analyses
[T]he data suggest that the major but by no means the sole factor determining the variability of attachment level or pocket depth changes is the nature of the local factors.
Haffajee AD, Socransky SS, Goodson JM, Lindhe J. Intraclass correlations of periodontal measurements. J Clin Periodontol 1985; 12: 216-24
The above quote is found in an old paper by leading periodontal scientists of the time who had been criticized by statisticians that their way to analyze hundreds of site-specific observations in a given patient as if they were independently sampled was fundamentally flawed. As the last author, Jan Lindhe, was the preeminent EiC of the then (and many years to come) most prestigious journal in dentistry, the paper could be read as a, well, defiant response which was supposed to solve the annoying issue once and for all.
The authors had re-analyzed their already published data of changes, after various forms of periodontal treatments, in key periodontal measurements, i.e. attachment levels (AL), pocket depth (PD) as well as gingival and plaque index scores. The data were subjected to comparing variance components and calculate intraclass correlation coefficents. Technically, in this scenario, the intraclass correlation coefficient (ICC) is the ratio of the variance attributable to subjects divided by the total of subject and error variances. By calculating it one gets an idea how strong the changes resembled each other at the patient level.
Ignoring the patient as random effect, statisticians had often demurred (seemingly without actually suggesting a suitable alternative) that, because observations were not independent as standard statistical analyses require, p-values would be inflated and hypothesis testing thus flawed.
As Haffajee et al. found out, ICCs were low or very low, in particular for probing measurements, AL (0.011 to 0.165) or PD (-0.009 to 0.178; read the later paper by Bruno Giraudeau on problems with negative ICCs).
The Constructive Advice of the Outstanding Editor-in-Chief of “The Journal“
I want to mention this early paper by Haffajee et al. (1985) as I had referred to it in 1985 when having submitted my series of some of my, as to my subjective judgment spectacular, early cases to “The Journal” (as young periodontists in Germany, and elsewhere, generally referred to the Journal of Clinical Periodontology) [1]. I wanted to make the point when writing to professor Jan Lindhe that my statistical analysis, ignoring patient effects, was justifiable in view of Haffajee’s results of low or very low ICCs.
Continue readingMy Periodontal Medicine Evening Seminar in Berlin
Early in 2016, I had been invited by the Berlin Society of Periodontology for giving an evening seminar at the University Dental School of Charité. As I had dedicated considerable time and effort for unveiling details and peculiarities of the so-called Engebretson scandal which had concomitantly been published on this blog, I found the invitation an excellent opportunity to share my views on the scandal with a distinguished auditorium of Berlin periodontists who, after all, had been trained and educated by late Professor Jean-Pierre Bernimoulin. Bernimoulin had passed in September 2015 and I confirmed in the introduction of my seminar that he had actually been the only periodontist in Germany (he was originally from Belgium) of international stature in his time.
Continue reading
Periodontology 