Sign up to save your podcasts
Or
Share Science Research Weekly
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
Science Research Weekly
By Mark R WilliamsonScience
Science Research Weekly episodes
- Episode 35: Turkey v. Tukey
In this episode, I skimmed over a dimension estimator, skipped past a piecewise linear curve, and slipped by the launch of a simple data science ebook.
References:
- The generalized ratios intrinsic dimension estimator
- The area under a piecewise linear curve
- Adapted Randomization
- confusing statistical term #13: missing at random and missing completely at random
- When to Use plotly?
- PCA for Categorical Variables in R
- How to combine Multiple Plots in R
- RObservations #42: Using the jinjar and tidyRSS packages to make a simple newsletter template
- Ebook launch – Simple Data Science (R)
R-packages:
- ASRgenomics: 'ASReml-R' Genomics Tools
- flashr: Create Flashcards of Terms and Definitions
- scistreer: Maximum-Likelihood Perfect Phylogeny Inference at Scale
3 min - Episode 34: Genomics, My Dear Watson
In this episode, I dusted off my genomic gloves with the HCLC-FC and CLIMB methods, waxed poetic with Python’s latest alpha release, and solved plotting mysteries with R-package ‘sherlock’.
References:
- Regression discontinuity threshold optimization
- Explaining predictive factors in patient pathways using autoencoders
- HCLC-FC: A novel statistical method for phenome-wide association studies
- Uncertainty-aware mixed-variable machine learning for materials design
- Closed-form continuous-time neural networks
- New statistical method improves genomic analyzes
- synr: Analyze stimulus-color consistency test data
- Profile plots in SAS
- Optimal linear profile plots in SAS
- Python 3.12.0 alpha 2 released
- What is Interactive Analytics?
- Top 9 Highest Paying Programming Languages (2023)
- How to Analyze Likert Scale Data?
- Top 10 Data Visualisation Tools Every Data Science Enthusiast Must Know
- Open source is a hard requirement for reproducibility
R-packages:
- exactLTRE: An Exact Method for Life Table Response Experiment (LTRE) Analysis
- sherlock: Graphical Displays to Aid Structured Problem Solving and Diagnosis
- cipheR: Encryption and Decryption with Text Ciphers
- rjtools: Preparing, Checking, and Submitting Articles to the 'R Journal'
- commafree: Call Functions Without Commas Between Arguments
7 min - Episode 33: Healthy Heaping of Free Stats
In this episode, I took advantage of more than one free data science course, mused over mappings for R, and helped myself to a heap of helper functions with R package ‘mlmhelpr’.
References:
- The Hybrid Model of Autoregressive Integrated Moving Average and Fuzzy Time Series Markov Chain on Long Memory Data
- Predicting prediction: A systematic workflow to analyze factors affecting the classification performance in genomic biomarker discovery
- A supervised topic embedding model and its application
- Shrinkage estimators of large covariance matrices with Toeplitz targets in array signal processing
- SAS® Fast-KPCA: An efficient and innovative nonlinear principal components method
- TDApplied version 2.0.0
- Issues While Switching R to UTF-8 and UCRT on Windows
- Datacamp Free Access Week
- Map any region in the world with R – Part II: Obtaining the coordinates
- R ggmap – How to Visualize Spatial Data in R
R-packages:
- cauchypca: Robust Principal Component Analysis Using the Cauchy Distribution
- nett: Network Analysis and Community Detection
- pwrss: Power and Sample Size Calculation Tools
- SASdates: Convert the Dates to 'SAS' Formats
- planningML: A Sample Size Calculator for Machine Learning Applications in Healthcare
- mlmhelpr: Multilevel/Mixed Model Helper Functions
- ExomeDepth: Calls Copy Number Variants from Targeted Sequence Data
6 min - Episode 32: Spooky Scary Statistics
In this episode, I waved my hand across several financial data journal articles, took advantage of free data science tutorials, learned how to run a dev environment from a flash drive, and did a double take at a seeming CRAN package duplication.
References:
- Analyzing Intraday Financial Data in R: The highfrequency Package
- A Practitioner's Guide and MATLAB Toolbox for Mixed Frequency State Space Models
- spsur: An R Package for Dealing with Spatial Seemingly Unrelated Regression Models
- Bias reduction in the logistic model parameters with the LogF(1,1) penalty under MAR assumption
- The Annals of Statistics Volume 50 Issue 5
- R 4.2.2 is released
- Call for proposals to organize a hybrid useR! in 2023 or 2024
- A trick to combine and split strings
- 365 Data Science courses free until November 21
- A Linux Live USB as a statistical programming dev environment
- Top 5 Shiny UI Add-On Packages
- September 2022: “Top 40” New CRAN Packages
R-packages:
- ExomeDepth: Calls Copy Number Variants from Targeted Sequence Data
- minsample1: The Minimum Sample Size
- minsample2: The Minimum Sample Size
- palaeoverse: Prepare and Explore Data for Palaeobiological Analyses
- SAP: Statistical Analysis and Programming
- tidyfit: Regularized Linear Modeling with Tidy Data
- robustbetareg: Robust Beta Regression
8 min - Episode 31: Awash in Acronyms
In this episode, I tried to keep my acronyms straight, dealt with big and tall (data), poked the ribs of SPSS, and contrasted the PIC with the AIC (more acronyms on the march!)
References:
- Fast Penalized Regression and Cross Validation for Tall Data with the oem Package
- synthACS: Spatial Microsimulation Modeling with Synthetic American Community Survey Data
- BGVAR: Bayesian Global Vector Autoregressions with Shrinkage Priors in R
- Facilitating time series classification by linear law-based feature space transformation
- Severe testing with high-dimensional omics data for enhancing biomedical scientific discovery
- Visualize dependencies of missing values
- Formatting your Microsoft Excel output using ODS Excel
- How to use the image function in R
- How to create a heatmap in R
- The pheatmap function in R
- SAS or R-Yould Should Know!
- Understanding ShinyApps
R-packages:
- worrrd: Generate Wordsearch and Crossword Puzzles
- picR: Predictive Information Criteria for Model Selection
7 min - Episode 30: The GitHub Secret Sauce
In this episode, I spilled the secret sauce behind my research methods, predicted extreme events, pursued plots off the beaten ggplot path, and added another simulation-based power analysis tool to my belt.
References:
- Statistics Weekly Research GitHub Repository
- Flexible time-to-event models for double-interval-censored infectious disease data with clearance of the infection as a competing risk
- Predicting the data structure prior to extreme events from passive observables using echo state network
- SCpubr: Generate high quality, publication-ready plots of single-cell transcriptomics data
- Concordances
- the difference between chi square tests of independence and homogeneity
- How to create a ggalluvial plot in R?
- How to create a Sankey plot in R?
- Understanding the Basics of Package Writing in R
R-packages:
- VIGoR: Variational Bayesian Inference for Genome-Wide Regression
- ggstats: Extension to 'ggplot2' for Plotting Stats
- mlpwr: A Power Analysis Toolbox to Find Cost-Efficient Study Designs
- ARIMAANN: Time Series Forecasting using ARIMA-ANN Hybrid Model
- makeunique: Make Character Strings Unique
7 min - Episode 29: Business or Bust
In this episode, I contributed to the Python Developers Survey, wiped a sweaty brow over the Isoband Incident, and booted up package 'bupaverse' for business process analytics.
References:
- The R Journal Volume 14/1
- gsDesign 3.4.0 is released
- Improvements in handling bytes encoding
- Join the Python Developers Survey 2022: Share and learn about the community
- Who rotated my cookie?
- CRAN and the Isoband Incident – Is Your Project at Risk and How to Fix It
- Map any region in the world with R – Part I: The basic map
R-packages:
- dfms: Dynamic Factor Models
- precmed: Precision Medicine
- RobustANOVA: Robust One-Way ANOVA Tests under Heteroscedasticity and Nonnormality
- bakR: Analyze and Compare Nucleotide Recoding RNA Sequencing Datasets
- nestedmodels: Tidy Modelling for Nested Data
- powRICLPM: Perform Power Analysis for the Random Intercept Cross-Lagged Panel Model
- bupaverse: Easily Install and Load the 'bupaverse'
7 min - Episode 28: Everything’s Coming Up Machine Learning
In this episode, I netted new ways to knock neural networks out of the park, let R do my calculus calculations for me, garnered gentle overviews to many machine learning topics, and made sure my phylogenic trees were publication ready with the R package ‘CancerEvolutionVisualization'.
References:
- Pathogen.jl: Infectious Disease Transmission Network Modeling with Julia
- calculus: High-Dimensional Numerical and Symbolic Calculus in R
- Deep Image Prior for medical image denoising, a study about parameter initialization
- On Physics-Informed Neural Networks for Quantum Computers
- Not frequentist enough.
- ggradar: radar plots with ggplot in R
- Mastering Debugging in R
- Understanding leaf node numbers when using rpart and rpart.rules
- A Gentle Introduction to using Support Vector Machines for Classification
- Boosting in Machine Learning: A Brief Overview
- Algorithm Classifications in Machine Learning
R-packages:
- pirouette: Create a Bayesian Posterior from a Phylogeny
- CancerEvolutionVisualization: Publication Quality Phylogenetic Tree Plots
- odetector: Outlier Detection Using Partitioning Clustering Algorithms
- stats4teaching: Simulate Pedagogical Statistical Data
- camcorder: Record Your Plot History
- openxlsx2: Read, Write and Edit 'xlsx' Files
6 min - Episode 27: Statistical Models on the Quick
In this episode, I kept it quick with appropriate microbial resistance data procedures, using a TI 83 calculator for statistics, and hoping for an easy entry to NEON data wrangling with package ‘neonOS’.
References:
- Statistical Network Analysis with Bergm
- ParMA: Parallelized Bayesian Model Averaging for Generalized Linear Models
- AMR: An R Package for Working with Antimicrobial Resistance Data
- new version of package declared
- 3 ways to enhance productivity with AI
- TI 83 for Statistics: Easy Steps for Common Problems
- Hazard Ratio: Interpretation & Definition
- Writing Functions in R
- August 2022: “Top 40” New CRAN Packages
R-packages:
- easydb: Easily Connect to Common Types of Databases
- neonOS: Basic Data Wrangling for NEON Observational Data
- getpublist: Obtain a List of Publications from 'PubMed' and 'Google Scholar'
- adjustedCurves: Confounder-Adjusted Survival Curves and Cumulative Incidence Functions
5 min - Episode 26: Random Learning on the Short
In this episode, I kept it short and sweet with a new statistical journal reference, data science job scraping, and random learning for R-packages.
References:
- Generalized resilience and robust statistics
- Stochastic continuum-armed bandits with additive models: Minimax regrets and adaptive algorithm
- Generate random ID values for subjects in SAS
- Linear Regression Equation Explained
- An Example of Specifying Within-Subjects Factors in Repeated Measures
- Designing Online Data Science Training for the Modern Age
- Optimizing my search for Data scientist jobs by scraping Indeed with R
- Seeking Inspiration from Random Learning
R-packages:
- BiOFI: Feature Identification Between Metabolome and Microbiome in Disease and Health
- glmmrBase: Specification of Generalised Linear Mixed Models
- REDCapTidieR: Extract 'REDCap' Databases into Tidy 'Tibble's
- verbaliseR: Make your Text Mighty Fine
- betaSandwich: Robust Confidence Intervals for Standardized Regression Coefficients
- DynForest: Random Forest with Multivariate Longitudinal Predictors
- roBTT: Robust Bayesian T-Test
- alqrfe: Adaptive Lasso Quantile Regression with Fixed Effects
- recurrentpseudo: Creates Pseudo-Observations and Analysis for Recurrent Event Data
- alkahest: Pre-Processing XY Data from Experimental Methods
5 min
About Science Research Weekly
From the publisher's feed
A weekly overview of helpful scientific research topics and the successor of the podcast Statistics Weekly. Every week, I will cover 3 topic areas: Research Articles, Research Tools, and Research…
Funding. Science On.