Data Analysis: A look at Basecamp support

Basecamp has made some very impressive improvements to their support response times in the past year:

Thanks largely to that investment in getting to 24/7 coverage, we continued to make a dent in response times this year, with the median time to response across the entire year falling slightly to 3 minutes. For comparison, back in 2011 and 2012 our median response time for email cases was over 2 hours.

An effort to increase weekend coverage had dramatic results:

Not surprisingly, the biggest impact on response time was seen on the weekends, where we cut median response time from about 8 hours to 6 minutes. We made a dent on weekdays too, with median response time falling from ~10 minutes to ~3 minutes.

Noah Lorang’s quantitative look at Basecamp support is both inspiring from a support perspective and intriguing from a data perspective. Makes me want to dive more deeply into the quantitative data we collect for support.

Read more (and geek out on the charts): 2014 was a good year for Basecamp support

h/t Andrew Spittle

Playing with Data

A virtual cult of the spreadsheet has formed, complete with gurus and initiates, detailed lore, arcane rituals – and an unshakable belief that the way the world works can be embodied in rows and columns of numbers and formulas.

I heard this quote from “A Spreadsheet Way of Knowledge,” written in 1984 by Steven Levy after the introduction of spreadsheet software, in a recent episode of Planet Money titled “Spreadsheets.”

As I learn more about quantitative data analysis, I’m excited about all of the things I can do with it. I enjoy thinking about the data and trying to understand how to use it. But I’m cautious. If I learned anything from studying anthropology, it was a certain amount of skepticism about data — and quantitative data in particular. Although I’m aware that even qualitative data can be heavily manipulated, and I’m grateful for what I’m learning to do with quantitative data, I remain constantly concerned about how numbers can oversimplify, obscure, and deceive. As Levy wrote:

Yet all these benefits will be meaningless if the spreadsheet metaphor is taken too much to heart. After all, it is only a metaphor. Fortunately, few would argue that all relations between people can be quantified and manipulated by formulas. Of human behavior, no faultless assumptions – and so no perfect model — can be made.

Image by Jon Newman (CC BY-NC-ND 2.0)

Diving into Data Analysis

The Automattic Creed starts with this:

I will never stop learning.

I don’t generally need much encouragement to start learning new things, but it’s awesome that learning is part of my job, every single day. Lately, I’ve focused most of my learning on data analysis.

Back in April, I worked with a group of colleagues on doing some basic data analysis related to our team’s work. I didn’t do the number crunching myself (hat tip to Kevin for doing that) but I was involved in framing our questions and coming up with hypotheses, along with helping brainstorm what to do with our findings. It sparked my interest in delving into the data more.

Last month, at our company meetup, I participated in a workshop (taught by a brilliant colleague and data engineer) on doing data analysis with Python and R. Most of my previous work was with qualitative data, so beyond basic statistics things tend to get fuzzy for me. But this workshop helped me find my legs and realize just where I needed to learn more.

So what am I up to now? I started reading Naked Statistics: Stripping the Dread from the Data, on the recommendation of some members of our data team. I’m also committing myself to a couple online classes. This week I started the course Measuring Causal Effects in the Social Sciences, and next month I’ll start Foundations of Data Analysis. We’ll see how I do with those, and I’ll do my best to share some of what I learn here. 🙂