Visualizations with statistical details: The 'ggstatsplot' approach

Patil, Indrajeet

doi:10.21105/joss.03167

Cited by 884 publications

(491 citation statements)

References 11 publications

Supporting

Mentioning

480

Contrasting

Unclassified

Order By: Relevance

“…All statistical analyses were performed in the R statistical environment (R Core Team 2016) [72], also using a number of libraries that extend the capabilities of the core version of the program. The most important R language libraries used in the analyses are: ggplot2 [73], ggstatsplot [74], rstatix [75], and gtsummary [76].…”

Section: Discussionmentioning

confidence: 99%

The Multi-Elemental Composition of the Aqueous Humor of Patients Undergoing Cataract Surgery, Suffering from Coexisting Diabetes, Hypertension, or Diabetic Retinopathy

Flieger

Dolar-Szczasny

Ręjdak

et al. 2021

IJMS

View full text Add to dashboard Cite

The aim of the study was the multi-elemental analysis of aqueous humor (AH) collected from patients undergoing cataract surgery. The study included: 16 patients with age-related macular degeneration AMD (99 controls), 10 patients with retinopathy (105 controls), 61 patients with hypertension (54 controls), and 33 patients with coexisting diabetes (82 controls). The control groups were recruited from patients with a lack of co-existing disease characterizing the specified studied group. The measurements were performed by the use of inductively coupled plasma optical emission spectrometry (ICP-OES). The statistical analysis was carried out using non-parametric testing (Mann–Whitney U). The level of significance was set at p = 0.05. The data obtained revealed substantial variations in elemental composition between the test groups in comparison to the controls. However, the significant variations concerned only a few elements. The phosphorous (P) level and the ratio of P/Ca were significant in retinopathy and diabetes, whereas cobalt (0.091 ± 0.107 mg/L vs. 0.031 ± 0.075 mg/L; p = 0.004) was significant in AMD. In co-existing hypertension, the levels of tin (0.293 ± 0.409 mg/L vs. 0.152 ± 0.3 mg/L; p = 0.031), titanium (0.096 ± 0.059 mg/L vs. 0.152 ± 0.192 mg/L; p = 0.045), and ruthenium (0.035 ± 0.109 mg/L vs. 0.002 ± 0.007 mg/L; p = 0.006) varied in comparison to the controls. The study revealed inter-elemental interactions. The correlation matrices demonstrated the domination of the positive correlations, whereas negative correlations mainly concerned sodium.

show abstract

Section: Discussionmentioning

confidence: 99%

The Multi-Elemental Composition of the Aqueous Humor of Patients Undergoing Cataract Surgery, Suffering from Coexisting Diabetes, Hypertension, or Diabetic Retinopathy

Flieger

Dolar-Szczasny

Ręjdak

et al. 2021

IJMS

View full text Add to dashboard Cite

show abstract

“…The variations in training volume (in seconds), TSS and HRV (lnRMSSD) averaged over each period for all the subjects were assessed by a pairwise post-hoc test for multiple comparisons of rank sums (Durbin-Conover) performed in ggstatplot (Patil, 2021). The HRV measure refers to the one taken the day after the training.…”

Section: Discussionmentioning

confidence: 99%

No evidence of association between HRV and training load in a pool of professional athletes before, during, and after the first COVID-19 lockdown.

Javaloyes¹,

Marinazzo²,

Sanabria³

et al. 2021

Preprint

View full text Add to dashboard Cite

PURPOSE: The COVID-19 crisis also affected elite sport severely, as elite athletes either stopped or drastically reduced their training regimen due to the lack of competitions and the mandatory lockdown. The aim of this study was to test whether heart rate variability was a reliable index of training load, which was dramatically altered due to the mandatory lockdown that occurred as a consequence of the COVID-19. METHODS: Training (volume and intensity) and heart rate variability of sixteen professional male (n = 8; body mass index = 22.2 ± 2.0) and female cyclists (n = 8; body mass index = 20.3 ± 1.1) before (4 weeks), during (7 weeks), and after (4 weeks) the mandatory lockdown in Spain were monitored. RESULTS: Individual analyses showed that the mandatory lockdown caused reliable reductions in training volume in 13 subjects (-96 to -7 % reductions in minutes), that were followed by an increase after the lockdown in all subjects (5 to 270%). In contrast, changes in training load were not homogenous across individuals. Moreover, such changes were not matched by comparable variations in heart rate variability. A mixed model of the heart rate variability as a function of training volume and intensity revealed no significant modulation by these two variables, and subject specific effects on the slope. CONCLUSIONS: In this study, we did not find evidence of association between heart rate variability and training load and/or intensity as many previous reports have suggested, even if training conditions changed dramatically overnight.

show abstract

“…Other ggplot2 extensions provide functions to generate publication-ready visualizations for specific types of models (e.g., metaviz, tidymv, sjPlot, survminer). For example, the ggstatsplot package (Patil, 2021) offers visualizations for statistical analysis of one-way factorial designs, and the plotmm package (Waggoner, 2020) supports specific types of mixture model objects. The fortify() function from ggfortify package (Horikoshi & Tang, 2018) does offer a unified plotting framework for a wide range of statistical models, although it is not as comprehensive as the see package because the easystats ecosystem covers a much larger collection of statistical models.…”

Section: Statement Of Needmentioning

confidence: 99%