Posts by Tags

Hand Coding Instumental Variables

In a previous post we discussed the linear model and how to write a function that performs a linear regression. In this post we will use that linear model fu...

Compiling TensorFlow on Arch Linux

Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA

Ron Graham’s Game

For a job interview at WHO I was asked by build a numeric version of Noughts and Crosses (Tic-Tac-Toe to some), this is called Ron Graham’s Game (repo).

BFV Homomorphic Encryption in R

This is an implementation of the BFV schema in R:

Handcoding a Difference in Differences

In this post we will discuss how to manually implement a Difference-in-Differences (DiD) estimator in R, using simulated data.

PWA of QR code to WhatsApp

Earlier this year I was in China, and in order to communicate with local delegates I installed WeChat. WeChat has a very handy feature that replaces exchangi...

BFV Homomorphic Encryption in R

This is an implementation of the BFV schema in R:

attention package on CRAN

The attention R package, describing how to implement from scratch the attention mechanism - which forms the basis of transformers - in the R language is now ...

Self-Attention from Scratch in R

EDIT 2022-06-24: this code is now available (with helper functions) in the R package attention, which is on CRAN. You can install it simply using: install.pa...

sigmoid package

The sigmoid package makes it easy to become familiar with the way neural networks work by demonstrating the key concepts using straightforward code examples.

Coding a Recurrent Neural Network from Scratch in R

This is an example of how to build a Recurrent Neural Network in R. What we will do is generate two sets of random numbers, a and b, which we will sum up, ...

Handcoding a Logit Model

Below is an example of how to handcode a logit model.

Handcoding a Difference in Differences

In this post we will discuss how to manually implement a Difference-in-Differences (DiD) estimator in R, using simulated data.

Handcoding a Panel Model

The most basic panel estimation is the Pooled OLS model, this model combines all data across indices and performs a regular Ordinary Least Squares Estimation.

Neural Network IV with Simulated Data

Some simulated data, borrowed from this post.

Neural Network Instrumental Variables

A simple example

Hand Coding Instumental Variables

In a previous post we discussed the linear model and how to write a function that performs a linear regression. In this post we will use that linear model fu...

learNN package

The learNN package makes it easy to become familiar with the way neural networks work by demonstrating the key concepts using straightforward code examples....

Linear Model and Neural Network

In this short post I want to quickly demonstrate how the most basic neural network (no hidden layer) gives us the same results as the linear model.

Hand Coding Hilton’s Dropout

Andrew Trask wrote an amazing post at I am Trask called:

Hand Coding Gradient Descent

Andrew Trask wrote an amazing post at I am Trask called:

Coding a Neural Network from Scratch in R

Andrew Trask wrote an amazing post at I am Trask called:

Hand Coding the Power of a Test

We want to test if our population average is different from twenty.

WIOD data sets package

The wiod package is now available on CRAN. The package contains the complete WIOD data sets, in a format compatible with the decompr and gvc package.

Hand Coding Categorical Variables

In last week’s posts we discussed handcoding a linear model and writing a convenient function for this, in today’s post we will take this a step further by i...

Hand Coding a Linear Model function

In yesterday’s post we developed a method for constructing a multivariate linear model with an intercept.

The Linear Model from Scratch in R

When it comes to econometrics, the main take aways from the workshops are primarily in terms of the syntax of yet another computer program.

introducing diagonals

A new R package diagonals is now available on CRAN. The package implements several tools for dealing with fat diagonals on matrices, such as this one:

plot.ly

Quick experiment on embedding plot.ly graphics.

diagonals in a network

A typical example in which diagonals can be helpful is Social Network Analysis. For example, if we use matrices to represent friendship perceptions between i...

gvc package on CRAN

A new R package gvc is now available on CRAN. The package implements several global value chain indicators

decompr on CRAN

I am proud to announce that after a few emails back and forth with Prof. Brian Ripley, which consisted mostly of me appologising for not following the proper...

Data Science Specialisation

Yesterday the Johns Hopkins School of Public Health published a post about their Data Science Specialisation on the online MOOC platform Coursera.

Learning R and Git

In yesterday’s post I discussed some of the principles I use to make my work replicable and - to an extent - reproducible. In this post I want to collect som...

The decompr package

I am proud to announce the beta version of the decompr R package. The package implements Export Decomposition using the Wang-Wei-Zhu (Wang, Wei, and Zhu 2013...

ggvis, shiny, and HTML5 slides

ggvis is wonderful new tool to create interactive graphics, which was build with Shiny apps in mind. In this post I will go over how you can create a Shiny a...

Coding a Recurrent Neural Network from Scratch in R

This is an example of how to build a Recurrent Neural Network in R. What we will do is generate two sets of random numbers, a and b, which we will sum up, ...

Online Office Hours

With over a year working from home and an end not immediately in sight, I felt it was time to think a bit structurally about how to work remotely as effectiv...

Tech Learn Talks

Today I gave a presentation at the UN Innovation Network’s TechLearnTalks (archived, backup):

Compiling TensorFlow on Arch Linux

Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA

Tech Learn Talks

Today I gave a presentation at the UN Innovation Network’s TechLearnTalks (archived, backup):

PWA of QR code to WhatsApp

Earlier this year I was in China, and in order to communicate with local delegates I installed WeChat. WeChat has a very handy feature that replaces exchangi...

Promoting Content in Africa

In the keynote at African Peering Forum (AfPIF) 2016 I presented the Promoting Content in Africa report written together with Michael Kende, these are the sl...

attention package on CRAN

The attention R package, describing how to implement from scratch the attention mechanism - which forms the basis of transformers - in the R language is now ...

Self-Attention from Scratch in R

EDIT 2022-06-24: this code is now available (with helper functions) in the R package attention, which is on CRAN. You can install it simply using: install.pa...

Male/Female Bargaining Power and Child Growth

Increased male bargaining power in households causes greater expenditure on food, an improvement in Weight-for-Age Z-scores in young children, and a deterior...

Hand Coding Categorical Variables

In last week’s posts we discussed handcoding a linear model and writing a convenient function for this, in today’s post we will take this a step further by i...

Male/Female Bargaining Power and Child Growth

Increased male bargaining power in households causes greater expenditure on food, an improvement in Weight-for-Age Z-scores in young children, and a deterior...

gvc package on CRAN

A new R package gvc is now available on CRAN. The package implements several global value chain indicators

decompr on CRAN

I am proud to announce that after a few emails back and forth with Prof. Brian Ripley, which consisted mostly of me appologising for not following the proper...

Data Science Specialisation

Yesterday the Johns Hopkins School of Public Health published a post about their Data Science Specialisation on the online MOOC platform Coursera.

WIOD data sets package

The wiod package is now available on CRAN. The package contains the complete WIOD data sets, in a format compatible with the decompr and gvc package.

gvc package on CRAN

A new R package gvc is now available on CRAN. The package implements several global value chain indicators

decompr on CRAN

I am proud to announce that after a few emails back and forth with Prof. Brian Ripley, which consisted mostly of me appologising for not following the proper...

The decompr package

I am proud to announce the beta version of the decompr R package. The package implements Export Decomposition using the Wang-Wei-Zhu (Wang, Wei, and Zhu 2013...

Compiling TensorFlow on Arch Linux

Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA

Hand Coding Gradient Descent

Andrew Trask wrote an amazing post at I am Trask called:

introducing diagonals

A new R package diagonals is now available on CRAN. The package implements several tools for dealing with fat diagonals on matrices, such as this one:

diagonals in a network

A typical example in which diagonals can be helpful is Social Network Analysis. For example, if we use matrices to represent friendship perceptions between i...

learNN package

The learNN package makes it easy to become familiar with the way neural networks work by demonstrating the key concepts using straightforward code examples....

Hand Coding Hilton’s Dropout

Andrew Trask wrote an amazing post at I am Trask called:

Hand Coding Categorical Variables

In last week’s posts we discussed handcoding a linear model and writing a convenient function for this, in today’s post we will take this a step further by i...

Learning R and Git

In yesterday’s post I discussed some of the principles I use to make my work replicable and - to an extent - reproducible. In this post I want to collect som...

Hand Coding a Linear Model function

In yesterday’s post we developed a method for constructing a multivariate linear model with an intercept.

ggvis, shiny, and HTML5 slides

ggvis is wonderful new tool to create interactive graphics, which was build with Shiny apps in mind. In this post I will go over how you can create a Shiny a...

Handcoding a Logit Model

Below is an example of how to handcode a logit model.

Hand Coding Gradient Descent

Andrew Trask wrote an amazing post at I am Trask called:

WIOD data sets package

The wiod package is now available on CRAN. The package contains the complete WIOD data sets, in a format compatible with the decompr and gvc package.

gvc package on CRAN

A new R package gvc is now available on CRAN. The package implements several global value chain indicators

decompr on CRAN

I am proud to announce that after a few emails back and forth with Prof. Brian Ripley, which consisted mostly of me appologising for not following the proper...

The decompr package

I am proud to announce the beta version of the decompr R package. The package implements Export Decomposition using the Wang-Wei-Zhu (Wang, Wei, and Zhu 2013...

Hand Coding Instumental Variables

In a previous post we discussed the linear model and how to write a function that performs a linear regression. In this post we will use that linear model fu...

Hand Coding the Power of a Test

We want to test if our population average is different from twenty.

Slides International Actors Digital Health

The slides from my briefing on the ITU-WHO Focus Group on Artificial Intelligence for Health at the Roundtable on International Actors in Digital Health (arc...

ITU-D SG2 Briefing on FG-AI4H

The slides from my briefing on the ITU-WHO Focus Group on Artificial Intelligence for Health to Study Group 2 of the ITU Development Sector at their Workshop...

learNN package

The learNN package makes it easy to become familiar with the way neural networks work by demonstrating the key concepts using straightforward code examples....

Hand Coding Hilton’s Dropout

Andrew Trask wrote an amazing post at I am Trask called:

BFV Homomorphic Encryption in R

This is an implementation of the BFV schema in R:

Slides 2nd Homomorphic Encryption Standardization Presentation

The slides from my presentation at the Homomorphic Encryption Standardization Consortium meeting on 6 February 2020 at Microsoft Research in Seattle (archive...

homomorphic encryption in R

Homomorphic encryption is allows computations to be performed on encrypted data. This has enormous potential in areas of machine learning that deal with priv...

Slides Homomorphic Encryption Standardization

The slides from my presentation at the Homomorphic Encryption Standardization Consortium meeting on 17 August 2019 at Intel HQ in Santa Clara:

ggvis, shiny, and HTML5 slides

ggvis is wonderful new tool to create interactive graphics, which was build with Shiny apps in mind. In this post I will go over how you can create a Shiny a...

Hand Coding the Power of a Test

We want to test if our population average is different from twenty.

Hand Coding Instumental Variables

In a previous post we discussed the linear model and how to write a function that performs a linear regression. In this post we will use that linear model fu...

Promoting Content in Africa

In the keynote at African Peering Forum (AfPIF) 2016 I presented the Promoting Content in Africa report written together with Michael Kende, these are the sl...

Making the Next Billion Demand Access

The Local-Content Effect of google.co.za in Setswana

Making the Next Billion Demand Access

The Local-Content Effect of google.co.za in Setswana

Hand Coding Instumental Variables

In a previous post we discussed the linear model and how to write a function that performs a linear regression. In this post we will use that linear model fu...

Learning R and Git

In yesterday’s post I discussed some of the principles I use to make my work replicable and - to an extent - reproducible. In this post I want to collect som...

Handcoding a Difference in Differences

In this post we will discuss how to manually implement a Difference-in-Differences (DiD) estimator in R, using simulated data.

Handcoding a Panel Model

The most basic panel estimation is the Pooled OLS model, this model combines all data across indices and performs a regular Ordinary Least Squares Estimation.

Neural Network IV with Simulated Data

Some simulated data, borrowed from this post.

Neural Network Instrumental Variables

A simple example

Hand Coding Instumental Variables

In a previous post we discussed the linear model and how to write a function that performs a linear regression. In this post we will use that linear model fu...

Linear Model and Neural Network

In this short post I want to quickly demonstrate how the most basic neural network (no hidden layer) gives us the same results as the linear model.

Hand Coding the Power of a Test

We want to test if our population average is different from twenty.

Hand Coding Categorical Variables

In last week’s posts we discussed handcoding a linear model and writing a convenient function for this, in today’s post we will take this a step further by i...

Hand Coding a Linear Model function

In yesterday’s post we developed a method for constructing a multivariate linear model with an intercept.

The Linear Model from Scratch in R

When it comes to econometrics, the main take aways from the workshops are primarily in terms of the syntax of yet another computer program.

Hand Coding Instumental Variables

In a previous post we discussed the linear model and how to write a function that performs a linear regression. In this post we will use that linear model fu...

Hand Coding Categorical Variables

In last week’s posts we discussed handcoding a linear model and writing a convenient function for this, in today’s post we will take this a step further by i...

Hand Coding a Linear Model function

In yesterday’s post we developed a method for constructing a multivariate linear model with an intercept.

The Linear Model from Scratch in R

When it comes to econometrics, the main take aways from the workshops are primarily in terms of the syntax of yet another computer program.

Promoting Content in Africa

In the keynote at African Peering Forum (AfPIF) 2016 I presented the Promoting Content in Africa report written together with Michael Kende, these are the sl...

Handcoding a Logit Model

Below is an example of how to handcode a logit model.

attention package on CRAN

The attention R package, describing how to implement from scratch the attention mechanism - which forms the basis of transformers - in the R language is now ...

Self-Attention from Scratch in R

EDIT 2022-06-24: this code is now available (with helper functions) in the R package attention, which is on CRAN. You can install it simply using: install.pa...

Backpropagation: the simplest form

doing backpropagation using pen and paper

Neural Network Instrumental Variables

A simple example

learNN package

The learNN package makes it easy to become familiar with the way neural networks work by demonstrating the key concepts using straightforward code examples....

Linear Model and Neural Network

In this short post I want to quickly demonstrate how the most basic neural network (no hidden layer) gives us the same results as the linear model.

Hand Coding Hilton’s Dropout

Andrew Trask wrote an amazing post at I am Trask called:

Hand Coding Gradient Descent

Andrew Trask wrote an amazing post at I am Trask called:

Coding a Neural Network from Scratch in R

Andrew Trask wrote an amazing post at I am Trask called:

introducing diagonals

A new R package diagonals is now available on CRAN. The package implements several tools for dealing with fat diagonals on matrices, such as this one:

Data Science Specialisation

Yesterday the Johns Hopkins School of Public Health published a post about their Data Science Specialisation on the online MOOC platform Coursera.

diagonals in a network

A typical example in which diagonals can be helpful is Social Network Analysis. For example, if we use matrices to represent friendship perceptions between i...

Backpropagation: the simplest form

doing backpropagation using pen and paper

rnn: a Recurrent Neural Network in R - on CRAN

The rnn R package, describing how to implement from scratch the Recurrent Neural Network algorithm) in the R language is now available on CRAN.

sigmoid package

The sigmoid package makes it easy to become familiar with the way neural networks work by demonstrating the key concepts using straightforward code examples.

Neural Network IV with Simulated Data

Some simulated data, borrowed from this post.

Neural Network Instrumental Variables

A simple example

learNN package

The learNN package makes it easy to become familiar with the way neural networks work by demonstrating the key concepts using straightforward code examples....

Linear Model and Neural Network

In this short post I want to quickly demonstrate how the most basic neural network (no hidden layer) gives us the same results as the linear model.

Hand Coding Hilton’s Dropout

Andrew Trask wrote an amazing post at I am Trask called:

Hand Coding Gradient Descent

Andrew Trask wrote an amazing post at I am Trask called:

Coding a Neural Network from Scratch in R

Andrew Trask wrote an amazing post at I am Trask called:

Hand Coding Categorical Variables

In last week’s posts we discussed handcoding a linear model and writing a convenient function for this, in today’s post we will take this a step further by i...

Hand Coding a Linear Model function

In yesterday’s post we developed a method for constructing a multivariate linear model with an intercept.

The Linear Model from Scratch in R

When it comes to econometrics, the main take aways from the workshops are primarily in terms of the syntax of yet another computer program.

introducing diagonals

A new R package diagonals is now available on CRAN. The package implements several tools for dealing with fat diagonals on matrices, such as this one:

gvc package on CRAN

A new R package gvc is now available on CRAN. The package implements several global value chain indicators

decompr on CRAN

I am proud to announce that after a few emails back and forth with Prof. Brian Ripley, which consisted mostly of me appologising for not following the proper...

The decompr package

I am proud to announce the beta version of the decompr R package. The package implements Export Decomposition using the Wang-Wei-Zhu (Wang, Wei, and Zhu 2013...

Handcoding a Difference in Differences

In this post we will discuss how to manually implement a Difference-in-Differences (DiD) estimator in R, using simulated data.

Handcoding a Panel Model

The most basic panel estimation is the Pooled OLS model, this model combines all data across indices and performs a regular Ordinary Least Squares Estimation.

Handcoding a Difference in Differences

In this post we will discuss how to manually implement a Difference-in-Differences (DiD) estimator in R, using simulated data.

Handcoding a Panel Model

The most basic panel estimation is the Pooled OLS model, this model combines all data across indices and performs a regular Ordinary Least Squares Estimation.

plot.ly

Quick experiment on embedding plot.ly graphics.

Hand Coding the Power of a Test

We want to test if our population average is different from twenty.

Tech Learn Talks

Today I gave a presentation at the UN Innovation Network’s TechLearnTalks (archived, backup):

Slides 2nd Homomorphic Encryption Standardization Presentation

The slides from my presentation at the Homomorphic Encryption Standardization Consortium meeting on 6 February 2020 at Microsoft Research in Seattle (archive...

Slides International Actors Digital Health

The slides from my briefing on the ITU-WHO Focus Group on Artificial Intelligence for Health at the Roundtable on International Actors in Digital Health (arc...

ITU-D SG2 Briefing on FG-AI4H

The slides from my briefing on the ITU-WHO Focus Group on Artificial Intelligence for Health to Study Group 2 of the ITU Development Sector at their Workshop...

Slides Homomorphic Encryption Standardization

The slides from my presentation at the Homomorphic Encryption Standardization Consortium meeting on 17 August 2019 at Intel HQ in Santa Clara:

Promoting Content in Africa

In the keynote at African Peering Forum (AfPIF) 2016 I presented the Promoting Content in Africa report written together with Michael Kende, these are the sl...

Hand Coding a Linear Model function

In yesterday’s post we developed a method for constructing a multivariate linear model with an intercept.

Promoting Content in Africa

In the keynote at African Peering Forum (AfPIF) 2016 I presented the Promoting Content in Africa report written together with Michael Kende, these are the sl...

PWA of QR code to WhatsApp

Earlier this year I was in China, and in order to communicate with local delegates I installed WeChat. WeChat has a very handy feature that replaces exchangi...

Coding a Recurrent Neural Network from Scratch in R

This is an example of how to build a Recurrent Neural Network in R. What we will do is generate two sets of random numbers, a and b, which we will sum up, ...

Coding a Recurrent Neural Network from Scratch in R

This is an example of how to build a Recurrent Neural Network in R. What we will do is generate two sets of random numbers, a and b, which we will sum up, ...

The Linear Model from Scratch in R

When it comes to econometrics, the main take aways from the workshops are primarily in terms of the syntax of yet another computer program.

attention package on CRAN

The attention R package, describing how to implement from scratch the attention mechanism - which forms the basis of transformers - in the R language is now ...

Self-Attention from Scratch in R

EDIT 2022-06-24: this code is now available (with helper functions) in the R package attention, which is on CRAN. You can install it simply using: install.pa...

ggvis, shiny, and HTML5 slides

ggvis is wonderful new tool to create interactive graphics, which was build with Shiny apps in mind. In this post I will go over how you can create a Shiny a...

sigmoid package

The sigmoid package makes it easy to become familiar with the way neural networks work by demonstrating the key concepts using straightforward code examples.

ggvis, shiny, and HTML5 slides

ggvis is wonderful new tool to create interactive graphics, which was build with Shiny apps in mind. In this post I will go over how you can create a Shiny a...

diagonals in a network

A typical example in which diagonals can be helpful is Social Network Analysis. For example, if we use matrices to represent friendship perceptions between i...

Slides 2nd Homomorphic Encryption Standardization Presentation

The slides from my presentation at the Homomorphic Encryption Standardization Consortium meeting on 6 February 2020 at Microsoft Research in Seattle (archive...

Slides International Actors Digital Health

The slides from my briefing on the ITU-WHO Focus Group on Artificial Intelligence for Health at the Roundtable on International Actors in Digital Health (arc...

ITU-D SG2 Briefing on FG-AI4H

The slides from my briefing on the ITU-WHO Focus Group on Artificial Intelligence for Health to Study Group 2 of the ITU Development Sector at their Workshop...

Slides Homomorphic Encryption Standardization

The slides from my presentation at the Homomorphic Encryption Standardization Consortium meeting on 17 August 2019 at Intel HQ in Santa Clara:

Hand Coding the Power of a Test

We want to test if our population average is different from twenty.

attention package on CRAN

The attention R package, describing how to implement from scratch the attention mechanism - which forms the basis of transformers - in the R language is now ...

Self-Attention from Scratch in R

EDIT 2022-06-24: this code is now available (with helper functions) in the R package attention, which is on CRAN. You can install it simply using: install.pa...

Hand Coding Instumental Variables

In a previous post we discussed the linear model and how to write a function that performs a linear regression. In this post we will use that linear model fu...

WIOD data sets package

The wiod package is now available on CRAN. The package contains the complete WIOD data sets, in a format compatible with the decompr and gvc package.

Posts by Tags

2sls

Arch Linux

Artificial Intelligence

BFV

DiD

PWA

R

RNN

Remote Working

Tech Learn Talks

TensorFlow

UN Innovation Network

WhatsApp

africa

attention

bargaining power

categorical variable

child growth

cran

data science

decompr

deep learning

descent

diagonals

dropout

dummy variable

education

function

ggvis

glm model

gradient

gvc

hand coding

health

hilton

homomorphic encryption

html5

hypthesis

instumental variables

internet

internet access

internet demand

iv

learning

linear model

lm