The official twitter account for https://nitter.cf/t.co/Smhdl3aYG0, by the @adamcchang lab.
Singapore
Joined April 2018
- Tweets150
- Following9
- Followers602
- Likes131
③ Finally, we added a new metric deltas' g to DABEST, similar to Hedges' g, designed for delta-delta effect size comparisons, facilitating the analysis of metrics from diverse units. 🧵4/6
② We've now made the asymmetric Swarm plot from dabestr 'Lapis' the default option, enhancing the clarity and interpretability of underlying data distributions. 🧵3/6
① In the latest DABEST release, our paired proportion plot has evolved to incorporate Sankey diagrams' principles, showing a clear visualization of proportional changes between measurements. 🧵2/6
② Users may add a baseline error curve to shared control contrast plots, displayed below the control group. This is the distribution of the bootstrapped mean differences from comparing the control against itself and is a measure of inherent variability within the control group.
We have also added several features not yet present in the Python version of the package:
① As you may have noticed from the images in the thread below, we have adopted asymmetrical swarmplots, thereby better showing the distribution underlying the raw data.
④ Last but not least, we introduce the mini-meta plot, a quick way to do meta-analytic averaging from similar experiments. This provides an easy way to summarize results from multiple replicates. This makes meta-analysis of primary data available as a convenient tool.
③ Instead of Fisher’s exact test for the comparison of proportions, you can now use the new DABEST proportion plots. It plots the variance of the observed binary counts and the effect-size curve of the difference of proportions. This function can be used with repeated measures.
For example, ∆∆ plots will be useful for genotype × drug analyses or optogenetic (light × opsin) experiments. A major benefit of the ∆∆ plot is how it places focus on the overall effect size.
Repeated-measures plots enable you to see a series of effect sizes relative to a baseline measurement.
📢To our R users: We will soon release a new version of dabestr (acclab.github.io/dabestr/) with brand new goodies such as repeated measures, proportion plot, mini-meta and delta-delta. #rstats #datascience We want to know how you prefer to get the package (poll in next tweet): 1/2
④ Finally, we introduce the mini-meta plot, a quick way to do meta-analytic averaging of data from different experiments. This provides an easy way to summarize results from multiple replicates. This makes meta-analysis available as a routinely accessible tool. 11/13
ALT Image of a mini-meta plot.
③ The DABEST proportion plot can replace Fisher’s exact test for the comparison of proportions. It plots the variance of the observed binary counts and the effect-size curve of the difference of proportions. This includes Sankey diagrams for paired proportional data. 10/13
ALT Image of a bar plot for proportional data.
ALT Image of a Sankey diagram for paired proportional data.
This will be useful for genotype × drug analysis or optogenetic experiments as two examples. A major benefit of the ∆∆ plot is the way it places focus on the overall effect size. 9/13
Repeated-measures plots enable the analyst to see a series of effect sizes relative to a baseline measurement. 7/13
ALT Image of a repeated-measures plot.
Today we are excited to launch DABEST’s first major update. The Python library now offers four new functions: repeated measures, the ∆∆ plot (‘delta-delta’), proportional plot, and mini-meta plot. These expand DABEST’s capabilities to more complex experimental designs. 🧵1/13
ALT Image of a repeated-measures plot.
ALT Image of a delta-delta plot.
ALT Image of a Sankey diagram for paired proportional data.
ALT Image of a mini-meta plot.
It has come to our attention that some of our tweets are being marked as sensitive; we're trying to sort this out right now.
4. The mini-meta plot.
Calculates and plots a weighted delta (∆) for meta-analysis of experimental replicates, useful for summarizing data. When the observed values are known share a common metric, this makes meta-analysis available as a routinely accessible tool.
ALT Mini-meta plot
3. The ∆∆ plot. Calculates the delta-delta (∆∆) for 2 × 2 experimental designs and plots the four groups with their relevant effect sizes. This design can be used as a replacement for the 2 × 2 ANOVA.
ALT Delta-delta plot
ALT Paired delta-delta plot
2. Proportional data.
Generates proportional bar plots, proportional differences, and calculates Cohen's h. Also enables plotting Sankey diagrams for paired binary data. This is the estimation equivalent to a bar chart with Fischer's exact test.
ALT Bar plot for proportional data
ALT Sankey diagrams for multiple paired comparisons of proportional data