Andrew Grogan-Kaylor - Blog-ish Posts

Data Visualization With Stata

Visualizing Data With Stata

stats

dataviz

Stata

Stata is a powerful and intuitive data analysis program. However, Stata is often under-appreciated as data visualization software. Learning how to graph in Stata is an…

Andy Grogan-Kaylor

There Is Also Relevant Material in Stats Stuff

stats

dataviz

multilevel

Bayes

R

Stata

In addition to these blog posts, there is also sometimes relevant material in Stats Stuff

Andy Grogan-Kaylor

There Is Also Relevant Material in Teaching

stats

dataviz

multilevel

Bayes

R

Stata

In addition to these blog posts, there is also sometimes relevant material in Teaching

Andy Grogan-Kaylor

Mediation

stats

teaching

A quick placeholder post to share some thoughts on statistical mediation:

Andy Grogan-Kaylor

Interactions

stats

teaching

A quick placeholder post to share a link to my materials on interactions:

Andy Grogan-Kaylor

Visualizing Multilevel Models

An In Development Tutorial

stats

dataviz

multilevel

Stata

I have developed a book draft on multilevel modeling, entitled Multilevel Thinking. The book draft discusses multilevel modeling in the context of cross cultural, or…

Andy Grogan-Kaylor

Multilevel Workshop

An In-Development Workshop on Multilevel Modeling

stats

multilevel

book

teaching

I have developed a set of workshop materials based upon my draft book on multilevel modeling. The book is entitled Multilevel Thinking. The book draft discusses multilevel…

Andy Grogan-Kaylor

Missing Data

An Evolving Blog Post on a Complicated Issue

stats

Dealing with missing data is a complex issue. This is an evolving blog post on approaches to this issue.

Andy Grogan-Kaylor

Interactions in Logistic Regression

More complicated than you would think

stats

Stata

teaching

This is just a placeholder post to share a link to my materials on interactions in logistic regression, to help students and others find it: https://agrogan1.github.io/newstu…

Andy Grogan-Kaylor

A Very Short Introduction to Stata

Content updates and clarifications

stats

Stata

I’ve made updates to my Very Short Introduction to Stata: https://agrogan1.github.io/Stata/very-short-introduction/very-short-introduction.html.

Andy Grogan-Kaylor

Tables in Stata

With Particular Attention to Multilevel Models

stats

multilevel

workflow

Stata

I’ve developed two new handouts on making tables in Stata with the older estimates table and the newer etable command.

Andy Grogan-Kaylor

Why Stata Is Better (At Graphing) Than R

stats

dataviz

Stata

R

Both R and Stata are programs with strong data visualization and analysis capabilities. However, Stata’s capabilities as a data visualization program are sometimes…

Andy Grogan-Kaylor

Updated UNICEF Colors for Stata Graphs

stats

dataviz

I’ve updated my UNICEF Colors for Stata Graphs, using the most recent version of official colors for UNICEF.

Andy Grogan-Kaylor

Tajikstan is #67

Tajikstan is the 67th Country to Ban Corporal Punishment

corporal punishment

Tajikstan is the 67th country to ban corporal punishment: https://agrogan1.github.io/research/cpbans/

Andy Grogan-Kaylor

Updated Michigan Colors for R Graphs

stats

dataviz

I’ve updated my R package for Michigan colors for R Graphs at: https://agrogan1.github.io/michigancolors/

Andy Grogan-Kaylor

Tables in Stata for `sem`

stats

workflow

Stata

I have a new abbreviated handout on making tables for sem in Stata: https://agrogan1.github.io/Stata/tables-SEM/tables-SEM.html

Andy Grogan-Kaylor

Interactions Of Gender Inequality And Parental Discipline Predicting Child Aggression In Low- And Middle-Income Countries

multilevel

corporal punishment

MICS

We’ve just published an article entitled Interactions Of Gender Inequality And Parental Discipline Predicting Child Aggression In Low- And Middle-Income Countries.

Andy Grogan-Kaylor

Mathematics is My Secret

teaching

stats

science

I really like this quote by Julia Schanen, as it embodies much of what I feel about research and teaching.

Andy Grogan-Kaylor

Multiple Principled Solutions

stats

workflow

social justice

science

teaching

One of my most recent ideas about statistical workflows is that there are certainly wrong decisions that one can make with data.

Andy Grogan-Kaylor

Simpson’s Paradox

stats

Simpson’s Paradox (Simpson, 1951) is the idea that associations between variables that are found between two variables in the sample as a whole, can be very different (or…

Andy Grogan-Kaylor

Multilevel Multilingual

multilevel

stats

book

Analyzing Multilevel Data in Multiple Statistical Languages.

Andy Grogan-Kaylor

Multilevel Visualization

multilevel

stats

book

dataviz

Visualizing Multilevel Data in Multiple Statistical Languages.

Andy Grogan-Kaylor

Working Truths

science

social justice

stats

“… there is no way to know when our observations about complex events in nature are complete. Our knowledge is finite, Karl Popper emphasised, but our ignorance is infinite.…

Andy Grogan-Kaylor

Associations Between 11 Forms of Discipline and Child Outcomes Across 60 Countries

An ArcGIS StoryMap

multilevel

Bayes

corporal punishment

MICS

Last Fall, we published an article entitled “Associations Between 11 Forms of Discipline and Child Outcomes Across 60 Countries” in BMJ Open: https://bmjopen.bmj.com/content…

Andy Grogan-Kaylor

Building Statistical Models

stats

social justice

science

“In general, when building statistical models, we must not forget that the aim is to understand something about the real world. Or predict, choose an action, make a…

Andy Grogan-Kaylor

Associations Between 11 Forms of Discipline and Child Outcomes Across 60 Countries

multilevel

Bayes

corporal punishment

MICS

Last Fall, we published an article entitled “Associations Between 11 Forms of Discipline and Child Outcomes Across 60 Countries” in BMJ Open: https://bmjopen.bmj.com/content…

Andy Grogan-Kaylor

An Introduction to Bayesian Statistics

stats

Bayes

multilevel

Last Fall, I gave a talk on Bayesian statistics to a group of PHD students at Michigan.

Andy Grogan-Kaylor

Love Words, Agonize Over Sentences

teaching

stats

science

I have been thinking a lot about this wisdom from Susan Sontag, which I think has a lot of applicability to teaching, especially in teaching statistics and data analysis.

Andy Grogan-Kaylor

Complexity Hidden Inside Simplicity

Complex Answers To Seemingly Simple Questions

teaching

stats

science

I have been thinking a lot lately about the idea that statistical questions are often seemingly simple questions, that contain complex answers, or answers that have complex…

Andy Grogan-Kaylor

Lao PDR is #66

Lao PDR is the 66th Country to Ban Corporal Punishment

corporal punishment

Lao PDR is the 66th country to ban corporal punishment: https://agrogan1.github.io/research/cpbans/

Andy Grogan-Kaylor

How To Choose A Chart

A Statistically Informed Visual Guide With Stata Commands

stats

dataviz

Stata

I’ve updated my graphing tutorial for Stata: How To Choose A Chart - A Statistically Informed Visual Guide With Stata Commands

Andy Grogan-Kaylor

ArcGIS Storymaps

Experimenting with a new format for sharing research.

GIS

MICS

Locations of Countries in MICS

Andy Grogan-Kaylor

Theory

social justice

theory

science

A few ideas relevant to theory that have been on my mind.

Andy Grogan-Kaylor

Updated Michigan Colors for Stata Graphs

stats

dataviz

I’ve updated my Michigan Colors for Stata Graphs at: https://agrogan1.github.io/Stata/michigan-graph-scheme/.

Andy Grogan-Kaylor

Some Thoughts About Science

theory

social justice

science

I’ve been reflecting on the quote below. The language is unfortunately gendered, but perhaps some context is that the author was writing around 1000 AD.

Andy Grogan-Kaylor

Workflow

Thoughts about data science / data analysis workflow.

stats

workflow

science

I have been thinking a lot recently about workflow, particularly in data science and data analysis projects. My thoughts are here: https://agrogan1.github.io/teaching/workflo…

Andy Grogan-Kaylor

Cohen’s d Calculator

Calculating and Visualizing Effect Sizes.

stats

Let’s imagine that you are studying an outcome like a mental health outcome.

Andy Grogan-Kaylor

Everything is Obvious Once You Know The Answer

Are the results of social science so ‘obvious’?

stats

social justice

science

I have been thinking a lot about the idea that Everything Is Obvious, Once You Know The Answer, as detailed in the book with this title by Duncan Watts.

Andy Grogan-Kaylor

GIS and Mapping

Notes for a GIS Course Under Development.

GIS

I’ve been working on some ideas for a GIS and Mapping Course that may happen some day.

Andy Grogan-Kaylor

Quantitative Literacy

stats

workflow

social justice

science

I have been thinking a lot about this idea.

Andy Grogan-Kaylor

Two Page Stata

Content updates and clarifications

stats

Stata

I’ve made updates to Two Page Stata: https://agrogan1.github.io/Stata/two-page-stata/TwoPageStata.pdf [HTML].

Andy Grogan-Kaylor

A Logic Model Using the `mermaid` Diagram Language

workflow

Logic models are used extensively in program development and program evaluation. I have worked on a logic model in graphviz. Here is an implementation using the mermaid graph…

Andy Grogan-Kaylor

Can Stata Make An Aesthetically Appealing Graph?

stats

dataviz

Stata

Another attempt to make an aesthetically appealing graph with Stata.

Andy Grogan-Kaylor

Can Stata Make A Beautiful Graph?

stats

dataviz

Stata

There is sometimes a debate–shall we say–about whether Stata can make beautiful graphs, particularly in comparison to using ggplot in R. Below, I try to use as many of…

Andy Grogan-Kaylor

Bar Charts in ggplot2

stats

dataviz

R

While ggplot2, and the ideas of an underlying “grammar of graphics”, make some kinds of graphing easier, ggplot2 can make other types of graphing more difficult.

Andy Grogan-Kaylor

Articles With UNICEF MICS Data

Articles on parenting and child development in global context.

multilevel

MICS

I have updated the list of articles published with the UNICEF Multiple Indicator Cluster Survey (MICS) data: https://agrogan1.github.io/research.html

Andy Grogan-Kaylor

Telling Stories With Data: Comparing Program Outcomes with ggplot2

dataviz

social justice

R

ggplot2 is a powerful graphing library that can make beautiful graphs. ggplot2 can also help us to understand ideas of an underlying “grammar of graphics”.

Andy Grogan-Kaylor

Logic Models

Proof of Concept for Creating a Logic Model in graphviz.

workflow

Logic models are used extensively in program development and program evaluation.

Andy Grogan-Kaylor

New Presentation on Meta-Analysis of Corporal Punishment

corporal punishment

I have created a new set of HTML slides presenting the results of our meta-analysis of 50 years of research on corporal punishment: https://agrogan1.github.io/research/cpmeta…

Andy Grogan-Kaylor

Cleaning Data

Resources for Stata and R

stats

workflow

R

Stata

I have developed a few resources for cleaning data and decided to list them all in one place.

Andy Grogan-Kaylor

Why Excel Is A Bad Format For Storing Data

stats

workflow

Excel is sometimes used as a program to collect and store data. Excel may sometimes be used because sometimes it is the only program that individuals or agencies have for…

Andy Grogan-Kaylor

Visualizing Categorical Data

Alternative approaches to visualizing categorical data

stats

dataviz

R

Visualizing categorical data–that that come in the form 1/0 or yes vs. no–can be a challenging task. I have put together some thoughts on visualizing categorical data, as…

Andy Grogan-Kaylor

Visualizing Disparities in a Categorical Risk Factor or Outcome

Telling Stories With Data

stats

dataviz

social justice

R

Visualizing categorical data presents unique challenges. A common solution is a bar graph, which may often be the best data visualization solution.

Andy Grogan-Kaylor

Visualizing Disparities in a Continuous Risk Factor or Outcome

Telling Stories With Data

stats

dataviz

social justice

R

In this post, I am trying to think through some best practices in showing disparities in a continuous risk factor or continuous outcome, like levels of depression or levels…

Andy Grogan-Kaylor

Working With Dates in Stata

stats

Stata

Dates in any statistical software (Stata, R) are complicated.

Andrew Grogan-Kaylor

Bar Charts to Pie Charts: Another Look

stats

dataviz

R

A quick look at moving from bar charts to pie charts.

Andy Grogan-Kaylor

‘Criticizing a musican is easy…’

workflow

social justice

science

I have always thought this proverb shared by Professor César Hidalgo was both valuable and profound.

Andy Grogan-Kaylor

Simpson’s Paradox and The Aggregation Paradox

An evolving blog post

stats

multilevel

This is an evolving blog post.

Andy Grogan-Kaylor

Telling Stories With Data: Bar Charts and Pie Charts

Conceptual Relationships Among Graphs, and the Grammar of Graphics

stats

dataviz

R

In this document, I talk about bar charts, stacked bar charts, and pie charts. I want to focus on the conceptual relationships between these kinds of graphs, using the idea…

Andy Grogan-Kaylor

Making a ‘Big Number’ (And Circle) With R

dataviz

R

Sometimes a large number (and accompanying circle) can represent a compelling visualization. This flipbook explains how to make such visualizations in R: https://agrogan1.git…

Andy Grogan-Kaylor

A Simple Visual Explanation of Simpsons Paradox

Results of an analysis or visualization may be very different depending on the number of factors accounted for.

stats

Simpson’s Paradox is the idea that associations that are found between two variables in the sample as a whole, can be very different (or even reversed) when we analyze the…

Andy Grogan-Kaylor

It’s not just what you’re born with

Sung by Dick Gaughn

poetry

It’s not just what you’re born with,

Written by Si Kahn

Transcendental Etude

poetry

“… a lifetime is too narrow

Why can’t numbers be beautiful too?

poetry

“Why can’t numbers be beautiful too?

You Have To Get Your Data From Somewhere

stats

dataviz

R

In learning R, as well as RMarkdown, one of the most difficult tasks seems to be understanding how to import data.

Andy Grogan-Kaylor

Welcome To My Blog

news

This is the first post in a Quarto blog. Welcome!

Andy Grogan-Kaylor

Interviewed in The Lancet Child & Adolescent Health

I was quoted in this interview in The Lancet Child & Adolescent Health on corporal punishment

corporal punishment

I was quoted in this interview in The Lancet Child & Adolescent Health on corporal punishment: The Strange Endurance of Corporal Punishment

Mauritius is #65

Mauritius is the 65th Country to Ban Corporal Punishment

corporal punishment

Mauritius is the 65th country to ban corporal punishment: https://agrogan1.github.io/research/cpbans/

Andy Grogan-Kaylor

Bar Charts in ggplot With Multiple Outcomes

stats

dataviz

R

By default, geom_col() assumes stat = 'identity' i.e. y is the height of the bar.

Andy Grogan-Kaylor

DSO Faculty Award

news

teaching

I was pleased to learn that I was chosen as this year’s recipient of the University of Michigan School of Social Work Doctoral Student Faculty Award.

Andy Grogan-Kaylor