Jerry Tamilchelvamaniind*classified·1 day agoUnity as a Testbed for Autonomy DevelopmentThis article was written by Chua Yee Han Dylan as part of his internship at C3 Development, DSTA, under the mentorship of Loke Yu Juan and Jerry Tamilchelvamani Introduction Testing autonomy developments in the field is challenging for various reasons. The test conditions may not be readily available, be opportunistic in…Experimentation7 min readExperimentation7 min read
Sargis·1 day agoRemote Configuration for Node Apps in under a minute.Are you tired of updating your application’s configuration files manually every time you make a change? Do you want an easy and efficient way to manage your remote configurations? Look no further than HappyPath’s Remote Config! HappyPath provides developers with a simple way to create and manage remote configuration files…Experimentation2 min readExperimentation2 min read
Tim Scheifler·Mar 16The Learning Process of Software DevelopmentAs someone who has spent years working in software development, I couldn’t agree more with Alberto Brandolini’s famous quote: Software development is a learning process; working code is a side effect. While many people believe that the primary goal of software development is to produce working code, Brandolini’s quote reminds…Experimentation2 min readExperimentation2 min read
Elizabeth Press·Mar 14Solving the experimentation dilemma and growing The New York Times — an interview with Shane MurrayContextualizing our world with data, Part 4: Journalism. Solving the speed vs. quality dilemma and growing the New York Times, also during the Trump years. Shane Murray, Field Chief Technology Officer at Monte Carlo and former Senior Vice President of data & insights at The New York Times, talks with…Experimentation3 min readExperimentation3 min read
Ayushman Mathur·Mar 12Cross Unit Interference in a Randomized Control Test (An Operations Example)In a typical test, there is a control group and a treatment group. A treatment group experiences an intervention of some kind (design, UX, landing pages, discounts, promotions, etc etc…), and the objective of the experiment is to determine the “effect” (positive, negtive or no effect) of the intervention on…Experimentation6 min readExperimentation6 min read
Ayushman Mathur·Mar 12Power Analysis during Experiment Design → A look under the hoodIn statistics, and more specifically in a two-sample (or more) comparison, a power analysis determines the duration your test should run in order to minimize the Type II error (more on this in this article I wrote on significance testing), by determining the throughput of samples through the primary metric…Experimentation7 min readExperimentation7 min read
Priyanka Murugan·Mar 8Experimentation in the healthcare industryExperimentation is an important step before releasing a product because it allows businesses to gather data and insights that can inform product development and ensure that the product meets business needs. This way, we can test assumptions about the product features, identify any potential issues or challenges, and refine the…Experimentation5 min readExperimentation5 min read
Murat UnalinTowards Data Science·Mar 7Why are Randomized Experiments the Gold Standard in Causal Inference?Understanding the identifying assumptions in experiments — Causal inference without assumptions is impossible. Every available method requires untestable assumptions to establish causality from observed associations in the data. As such, stating the identifying assumptions and defending them is the most critical aspect of causal inference, yet it is also the most neglected one. In my previous article…Experimentation7 min readExperimentation7 min read
Ayushman Mathur·Mar 4Bayesian Analysis: Is it better than an A/B test?Bayesian statistics differs from classical statistics (also known as frequentist) basically in its interpretation of probability. The former sees it as a probability metric of relative certainty over possible hypotheses/models/parameters, whereas the latter sees it as the “relative frequency observed during many trials”. Through this piece, I want to be…Experimentation5 min readExperimentation5 min read
Ayushman Mathur·Mar 4Stat Significance Tests: Deep Dive [Only for Frequentists!]Review significance testing for identifying difference between sample populations in varied situations and leveraging different tests basis merit of each Let’s start with some fundamentals — Data Type(s) Numerical Data: Any data that can be measured on a number scale, can be finite, infinite, discrete or continuous (eg. …Experimentation9 min readExperimentation9 min read
![Stat Significance Tests: Deep Dive [Only for Frequentists!]](https://miro.medium.com/v2/resize:fill:224:224/1*5thW8dg9dJjRNxAby25avg.png)
![Stat Significance Tests: Deep Dive [Only for Frequentists!]](https://miro.medium.com/v2/resize:fill:160:112/1*5thW8dg9dJjRNxAby25avg.png)
