Home – φ philip's curve

Misdirected confusion: what are ESG ratings even

On ESG ratings, Berg et al., the welfare function nobody specified, and why unstable inter-rater correlation is not a scandal.

There is no S2 without S1. Even under transition relief.

Transition relief narrows the scope of IFRS S1 to climate, but it does not replace it. You cannot faithfully apply IFRS S2 without S1 concepts.

Some People Want It All. Good Sustainability Disclosure Doesn’t Pretend You Can.

Sustainability-related management commentary that does not communicate tradeoffs is not decision-useful. IFRS S1 is entirely comfortable letting boards confess their own…

Immunity Is Real. Harm Is Ambient.

Why I refuse PPE abandonment—and why the logic of reprieve, though biologically sound, collapses under asymptomatic spread.

Fair Pay: Getting it Right for ESG Success

We compare how FTSE Russell and S&P Global assess various aspects of fair pay within their ESG ratings methodologies. By highlighting the key differences in their approaches…

Anti-Corruption Governance and ESG Ratings

Prepared for SustenyX; first published on LinkedIn

Waste Management and ESG

Prepared for SustenyX; first published on LinkedIn

Navigating the ESG Ratings Maze: A Guide for Malaysian PLCs

Prepared for SustenyX; first published on LinkedIn

Penang’s Semiconductor Crossroads

Navigating global trends and industrial upgrading

US-China Tensions and the Transformation of Penang’s Tech Industry

First published in Penang Monthly (October 2024).

Pay for progress: do head of state governments’ pay respond to performance?

Malaysiakini’s data journalism team just published this fascinating analysis about the salaries of states’ heads of government:

Penang’s Evolving Schooling Preferences

Penang’s education scene is changing rapidly. While Malaysia’s private school enrollment remains modest compared to the region, it is seeing a concerning shift.

EPF Account 3: Flexibility or Erosion of Retirement Savings?

First published in Penang Monthly (June 2024).

Brain drain: not as big a problem as you think

First published on LinkedIn.

Temperatures 🌡️

Panasnya

Hello Julia

Not sure how I landed up browsing through Julia for Data Science and Julia Data Science this Saturday evening. Julia is a fascinating language, but I think the learning…

The Limited Local Benefits of Swiftonomics

This article was first published in the April 2024 issue of Penang Monthly.

My approach to Covid-19 in 2024

Four years into the pandemic, my refusal to align myself with the rest of society sleepwalking into a replay of 2019 norms of work and life has set me back for years…

When Less Is More Expensive: The Trend of Shrinkflation

First published in Penang Monthly (September 2023).

Seasonality in decarbonisation

or, perhaps, the carbon costs of returning to the office?

(Individual) tax rebates suck

One of my pet peeves is to see people advocate for tax rebates when they should know better.

Gradient boosting?

There’s no shortage of machine learning hot takes on how the XGBoost gradient boosting framework continues to defy the no-free-lunch theorem by being perhaps the most…

Nested cross-validation

In Why do cross-validation, I described cross-validation as a way of evaluating your modeling workflow from start to end to help you pick the appropriate model and avoid…

Why do cross-validation?

In short, we do cross-validation to pick the right model. But what does that mean for our ‘final model’?

WSL2 and R

Windows Subsystem for Linux (WSL) is a great way to run Linux software on your computer without dual-booting or starting over. For certain reasons, you may want to run R in…

Charts can lie

Data visualization is something we use to understand our data. Sure, it has some aesthetic function, but its primary purpose is to communicate what’s in the data.

Learning to sell data science

Half of your job, regardless of what that job is, is being able to sell your work. (source)

Link functions matter

There’s a bit of a conversation on Twitter whether to use linear models or logistic models for estimating effect sizes in the case of binary response variables. I wondered…

Reflections on the tidyverse

At my previous gig as a junior data scientist trainer, my team was given some time to revamp our base R-based syllabus to be more tidy-friendly while retaining significant…

File paths and data science projects

Large data science projects can be a pain to manage. Cookiecutter Data Science recommends the following project folder structure, and I think it’s a good picture of how a…

The Australian gender wage gap: interactive viz

I wrote a piece at The Ambitious Economist on Australia’s gender wage gap with some good ol’ ggplot2 dataviz. However, there was a chart showing the gender wage gap by…

PSA: Python, OLS and perfectly collinear variables

Unlike most implementations of linear models (e.g. Stata, R), Python packages don’t usually drop perfectly collinear variables.

My first package: bnmr

bnmr is a wrapper for httr to access BNM (Malaysia’s central bank)’s recently released API. I wrote this to practice writing R packages, with lots of help from the R Packages…

Exploring GE14 results with Python (part 2)

See here for part 1.

Exploring GE14 results with Python (part 1)

There’s an interesting blog post up on DataTarik about using random forests to model the outcomes of Malaysia’s 14th general election (GE14). While I have my reservations…

Visualising government expenditure data with ggplot2

I thought I’d practice my rusty R skills when I came across a post by Khairil Yusof on the Sinar Project Facebook group that Malaysian Administrative Modernisation and…