J. Eduardo Vera-Valdés

@eduardoveravaldes.bsky.social

Associate Professor in Mathematics-Economics at the Department of Mathematical Sciences in Aalborg University. Research Interests: Econometrics, time series, long memory, statistical learning, and climate econometrics. Website: everval.github.io

Doing a phoenix - i.e. buying back the assets of your own failed, liquidated business to start up a new identical venture, is a gross misuse of Ltd company protections and should be illegal.

All error messages should be copyable. I'm so bored of having to transcribe some arcane error code just because some gobshite developer couldn't be arsed to find the setting to make their error messages appear as copyable text.

Our paper “The Effect of CEO Public Behaviour on the Company’s Valuation: The Case of Tesla and Elon Musk” is now out in Applied Economics Letters. It began as a fun “weekend” experiment, took much longer than expected to publish, but we are very happy with the final results.

I’m happy to share the latest update to LongMemory.jl, the Julia package for generating, estimating, and forecasting long memory time series models. This release adds support for harmonic weighted processes, expanding the set of tools available for modelling long memory in practice.

GitHub - everval/LongMemory.jl: Julia package to generate, estimate, and forecast long memory processes

Julia package to generate, estimate, and forecast long memory processes - everval/LongMemory.jl

github.com

The deadline for submissions to the 10th Conference on Econometric Models of Climate Change (EMCC-X) at Aalborg, Denmark on 20–21 August, is next week on 26 March. We invite contributions on statistical and econometric methods for climate data. More info: www.math.aau.dk/2026-econome...

2026 Econometric Models of Climate Change Conference

The conference brings together economists, econometricians, climate scientists, statisticians, and policy researchers to improve our understanding of climate change, its impacts, and effective policy ...

math.aau.dk

📊 Data update: The Penn World Table is an extensive database that helps us understand long-run, global trends in economic growth, working hours, productivity, and living standards. We’ve updated 17 of our charts using the latest release.

A line chart showing productivity, defined as gross domestic product (GDP) per hour of work, for a selection of 10 countries from 1950 to 2023. The data is adjusted for inflation and differences in living costs between countries. At the top of the chart is Denmark, with a productivity of 88.7 $ per hour. At the bottom is Ethiopia, at 4.5 $ per hour. The data source is the Penn World Table (2025). The chart is licensed CC BY to Our World in Data.

Amusing how 99% of people using LLMs forget how these things work: They are advanced probability machines. They generate the next most likely token (word) based in the input and their training. Under the hood, it’s a giant matrix multiplication that has eerily good output.