Most recent at the top
- 28 Sep 2024 » Git, peer review, tests and toil
- 21 Sep 2024 » Prime numbers as sums of three squares.
- 14 Sep 2024 » Stepwise selection of variables in regression is Evil.
- 08 Sep 2024 » Gender and sexuality in Australian surveys and census
- 31 Aug 2024 » Sampling without replacement with unequal probabilities
- 30 Aug 2024 » Ratios of indexed line charts
- 24 Aug 2024 » Polar-centred maps
- 20 Aug 2024 » Perturbing a non-symmetrical probability distribution
- 10 Aug 2024 » Snakes and ladders
- 27 Jul 2024 » Population age changes in the Pacific
- 05 May 2024 » Reproducing and adapting the UN Population Projections
- 17 Oct 2023 » The 'V20' group of vulnerable countries and the MVI
- 30 Sep 2023 » The UN's proposed Multidimensional Vulnerability Index
- 23 Sep 2023 » Finding a circle in a chart
- 06 Aug 2023 » Model life tables
- 30 Jul 2023 » Log transforms, geometric means and estimating population totals
- 24 Jun 2023 » Weighted versus unweighted percentiles
- 17 Jun 2023 » Simpler drawing of Pacific choropleth maps
- 04 Jun 2023 » Simulating confounders, colliders and mediators
- 28 May 2023 » Covid-19 vaccination rates in the Pacific
- 26 May 2023 » Showing women proportion of Parliamentarians on a map
- 25 Feb 2023 » Transformations for compositional data
- 13 Oct 2022 » Pacific island choropleth map
- 14 Aug 2022 » Pacific island population pyramids
- 26 Mar 2022 » Smoothing charts of Supreme Court Justice nomination results
- 14 Jun 2021 » Principal components and penguins
- 14 Feb 2021 » Making a database of security prices and volumes
- 05 Feb 2021 » Visualising stock prices and volume
- 21 Dec 2020 » Shiny in production for commercial clients
- 05 Dec 2020 » Animated map of World War I UK ship positions
- 14 Nov 2020 » Reproduce analysis of a political attitudes experiment
- 11 Oct 2020 » Hamlet, data models, interaction graphs and other cool stuff
- 04 Oct 2020 » Facebook survey data for the Covid-19 Symptom Data Challenge
- 26 Sep 2020 » Free text in surveys - important issues in the 2017 New Zealand Election Study
- 13 Sep 2020 » Trying out Processing
- 06 Sep 2020 » Mixture distributions and reporting times for Covid-19 deaths in Florida
- 29 Aug 2020 » Time series cross validation of effective reproduction number nowcasts
- 23 Aug 2020 » Lines of best fit
- 09 Aug 2020 » Essentially random isn't the same as actually random
- 02 Aug 2020 » Visualisation options to show growth in occupations in the Australian health industry
- 18 Jul 2020 » Estimating Covid-19 reproduction number with delays and right-truncation
- 13 Jun 2020 » Fixing scientific publishing and peer review
- 06 Jun 2020 » Forecasts for the 2020 New Zealand elections using R and Stan
- 30 May 2020 » A health data firm making extraordinary claims about its data
- 23 May 2020 » Ordering bars within their clumps in a bar chart
- 17 May 2020 » Incidence of COVID-19 in Texas after adjusting for test positivity
- 09 May 2020 » Test positivity rates and actual incidence and growth of diseases
- 18 Apr 2020 » Pragmatic prediction intervals from a quasi-likelihood GLM
- 06 Apr 2020 » How to make that crazy Fox News y axis chart with ggplot2 and scales
- 21 Mar 2020 » Impact of a country's age breakdown on COVID-19 case fatality rate
- 17 Mar 2020 » COVID-19 cumulative observed case fatality rate over time
- 07 Mar 2020 » New Zealand Election Study webtool
- 01 Mar 2020 » Log transform or log link? And confounding variables.
- 23 Feb 2020 » Body Mass Index
- 01 Feb 2020 » Lewis Carroll's proposed rules for tennis tournaments
- 26 Jan 2020 » Analysing the effectiveness of tennis tournament seeding
- 22 Dec 2019 » Analysing large data on your laptop with a database and R
- 24 Nov 2019 » Cost-benefit analysis in R
- 09 Nov 2019 » A small simple random sample will often be better than a huge not-so-random one
- 03 Nov 2019 » Re-creating survey microdata from marginal totals
- 07 Sep 2019 » Poisson point processes, mass shootings and clumping
- 25 Aug 2019 » Inferring a continuous distribution from binned data
- 28 Jul 2019 » Forecasting unemployment
- 20 Jul 2019 » Time series forecast cross-validation
- 28 Jun 2019 » Too important to leave to the data scientists
- 19 May 2019 » Polls v results
- 15 May 2019 » House effects, herding, and the last few days before the election
- 22 Apr 2019 » Familiarisation with the Australian Election Study
- 20 Apr 2019 » Animating the US Treasury yield curve rates
- 07 Apr 2019 » Using svglite with web fonts
- 31 Mar 2019 » Website with Australian federal election forecasts
- 30 Mar 2019 » Better predictions for AFL from adjusted Elo ratings
- 23 Mar 2019 » AFL teams Elo ratings and footy-tipping
- 11 Mar 2019 » Exploring swings in Australian federal elections
- 02 Mar 2019 » Bayesian state space modelling of the Australian 2019 election
- 20 Feb 2019 » Seasonality in NZ voting preference?
- 26 Jan 2019 » What the world agrees with
- 23 Dec 2018 » Simulating Persian Monarchs gameplay
- 01 Dec 2018 » Number of births in the twentieth century
- 24 Nov 2018 » Counting digits
- 18 Nov 2018 » A more systematic look at suppressed data
- 06 Nov 2018 » Suppressed data (left-censored counts)
- 27 Oct 2018 » Simulating simple dice games
- 07 Oct 2018 » Understanding the limitations of group-level inequality data
- 26 Sep 2018 » Sri Lanka visitor arrivals
- 31 Aug 2018 » Rents in Melbourne
- 24 Aug 2018 » Estimating relative risk in a simulated complex survey
- 17 Aug 2018 » Relative risk ratios and odds ratios
- 14 Aug 2018 » Time series intervention analysis with fuel prices
- 10 Aug 2018 » Leading indicators of economic growth
- 01 Aug 2018 » Business confidence and economic growth
- 07 Jul 2018 » Setting up RStudio Server, Shiny Server and PostgreSQL
- 01 Jul 2018 » Spend on petrol by income
- 26 Jun 2018 » Demography simulations
- 15 Jun 2018 » Minor updates for ggseas and Tcomp R packages
- 31 May 2018 » Demystifying life expectancy calculations
- 13 May 2018 » Fifteen New Zealand government Shiny web apps
- 05 May 2018 » Survey books, courses and tools
- 11 Apr 2018 » Weighted survey data with Power BI compared to dplyr, SQL or survey
- 01 Apr 2018 » Deaths per firearm violence event
- 20 Mar 2018 » Truncated Poisson distributions in R and Stan
- 24 Feb 2018 » Do tweeps with more followers follow tweeps with more followers?
- 17 Feb 2018 » Books I liked in 2017
- 10 Feb 2018 » Visualising an ethnicity statistical classification
- 03 Feb 2018 » Average spend, activities and length of visit in the NZ International Visitor Survey
- 23 Jan 2018 » How to recruit data analysts for the public sector
- 09 Dec 2017 » Some quirks with R and SQL Server
- 19 Nov 2017 » Seasonality of plagues
- 15 Oct 2017 » New Zealand fatal traffic crashes
- 07 Oct 2017 » New Zealand 2017 election results
- 05 Oct 2017 » nzelect 0.4.0 on CRAN with results from 2002 to 2014 and polls up to September 2017
- 16 Sep 2017 » Time-varying house effects in New Zealand political polls
- 09 Sep 2017 » R Markdown for documents with logos, watermarks, and corporate styles
- 09 Sep 2017 » The long view on New Zealand political polls
- 20 Aug 2017 » More things with the New Zealand Election Study
- 19 Aug 2017 » Estimating Gini coefficient when we only have mean income by decile
- 05 Aug 2017 » Sampling distribution of weighted Gini coefficient
- 22 Jul 2017 » Inter-country inequality and the World Development Indicators
- 13 Jul 2017 » Who turned out to vote in the 2014 New Zealand general election?
- 09 Jul 2017 » Improving state-space modelling of the Australian 2007 federal election
- 02 Jul 2017 » Family violence and economic deprivation in New Zealand
- 24 Jun 2017 » State-space modelling of the Australian 2007 federal election
- 17 Jun 2017 » Stats NZ encouraging active sharing for microdata access projects
- 04 Jun 2017 » Global choropleth maps of military expenditure
- 21 May 2017 » Sankey charts for swinging voters
- 14 May 2017 » Web app for individual party vote from the 2014 New Zealand election study
- 06 May 2017 » Modelling individual party vote from the 2014 New Zealand election study
- 30 Apr 2017 » Luke-warm about micromaps
- 25 Apr 2017 » More cartograms of New Zealand census data (district and city level)!
- 23 Apr 2017 » Cartograms of New Zealand census data
- 15 Apr 2017 » Impact of omitted variables on estimating causal effects - simulations
- 09 Apr 2017 » Exploring propensity score matching and weighting
- 26 Mar 2017 » New Zealand election forecasts
- 21 Mar 2017 » House effects in New Zealand voting intention polls
- 12 Mar 2017 » Simulations to explore excessive lagged X variables in time series modelling
- 11 Mar 2017 » New data and functions in nzelect 0.3.0 R package
- 04 Mar 2017 » Visualising relationships between children's books
- 26 Feb 2017 » Success rates of appeals to the Supreme Court by Circuit
- 18 Feb 2017 » Moving largish data from R to H2O - spam detection with Enron emails
- 23 Jan 2017 » US Presidential inauguration speeches
- 22 Jan 2017 » Does seasonally adjusting first help forecasting?
- 14 Jan 2017 » Books I like
- 05 Jan 2017 » Cross-validation of topic modelling
- 31 Dec 2016 » Sparse matrices, k-means clustering, topic modelling with posts on the 2004 US Presidential election
- 26 Dec 2016 » Extracting data on shadow economy from PDF tables
- 24 Dec 2016 » forecastHybrid 0.3.0 on CRAN
- 18 Dec 2016 » Air quality in Indian cities
- 10 Dec 2016 » Extrapolation is tough for trees!
- 07 Dec 2016 » Why time series forecasts prediction intervals aren't as good as we'd hope
- 27 Nov 2016 » Error, trend, seasonality - ets and its forecast model friends
- 24 Nov 2016 » Declining sea ice in the Arctic
- 19 Nov 2016 » Earthquake energy over time
- 15 Nov 2016 » Extreme pie chart polishing
- 06 Nov 2016 » Timeseries forecasting using extreme gradient boosting
- 29 Oct 2016 » FiveThirtyEight's polling data for the US Presidential election
- 19 Oct 2016 » Tourism forecasting competition data in the Tcomp R package
- 15 Oct 2016 » Statistics New Zealand experimental API initiative
- 12 Oct 2016 » Update of `ggseas` for seasonal decomposition on the fly
- 18 Sep 2016 » New Zealand Election Study individual level data
- 16 Sep 2016 » Why you need version control
- 13 Sep 2016 » Analysing the Modelled Territorial Authority GDP estimates for New Zealand
- 28 Aug 2016 » Dual axes time series plots with various more awkward data
- 18 Aug 2016 » Dual axes time series plots may be ok sometimes after all
- 13 Aug 2016 » Elastic net regularization of a model of burned calories
- 04 Aug 2016 » nzcensus on GitHub
- 14 Jul 2016 » nzelect 0.2.0 on CRAN
- 02 Jul 2016 » Animated world inequality map
- 30 Jun 2016 » International Household Income Inequality data
- 16 Jun 2016 » Monthly Regional Tourism Estimates
- 14 Jun 2016 » Presentation slides on using graphics
- 05 Jun 2016 » Bootstrap and cross-validation for evaluating modelling strategies
- 29 May 2016 » Actual coverage of confidence intervals for standard deviation
- 22 May 2016 » Visual contrast of two robust regression methods
- 14 May 2016 » Minimalist Tufte-inspired axis text with Scottish-New Zealand historical material
- 07 May 2016 » Announcing new forecastHybrid package
- 16 Apr 2016 » Election analysis contest entry part 4 - drivers of preference for Green over Labour party
- 09 Apr 2016 » Election analysis contest entry part 3 - interactive exploration of voting locations with leaflet and Shiny
- 04 Apr 2016 » Election analysis contest entry part 2 - building the nzelect R package
- 03 Apr 2016 » Election analysis contest entry part 1 - introducing the nzelect R package
- 28 Mar 2016 » Seasonal decomposition in the ggplot2 universe with ggseas
- 19 Mar 2016 » Skill v luck in determining backgammon winners
- 06 Mar 2016 » Explore with Shiny the impact of sample size on "p-charts"
- 24 Feb 2016 » New Zealand Tourism Dashboard pushes Shiny to the max
- 20 Feb 2016 » Dynamic Stochastic General Equilibrium models made (relatively) easy with R
- 08 Feb 2016 » ggseas package for seasonal adjustment on the fly with ggplot2
- 06 Feb 2016 » Data from the World Health Organization API
- 30 Jan 2016 » Better prediction intervals for time series forecasts
- 23 Jan 2016 » Filling in the gaps - highly granular estimates of income and population for New Zealand from survey data
- 29 Dec 2015 » A (not too talkative) twitterbot is born
- 26 Dec 2015 » Network charts of commuting in New Zealand with R and D3
- 21 Dec 2015 » X13-SEATS-ARIMA as an automated forecasting tool
- 12 Dec 2015 » Importance of exports and economic growth, cross-country time series
- 05 Dec 2015 » Inequality measures in the World Development Indicators
- 26 Nov 2015 » Deaths from assault over time in 40 relatively rich countries
- 21 Nov 2015 » Create ARIMA time series from bottom up
- 15 Nov 2015 » Linear model with time series random component
- 30 Oct 2015 » Modelled Territorial Authority GDP for New Zealand
- 25 Oct 2015 » Silver flows in the seventeenth and eighteenth centuries
- 10 Oct 2015 » Seasonal adjusment on the fly with X-13ARIMA-SEATS, seasonal and ggplot2
- 04 Oct 2015 » Recruiting Analysts for dynamic cutting edge public sector team
- 30 Sep 2015 » Success rates of automated ARIMA fitting
- 20 Sep 2015 » How to compare two blackbox timeseries generators?
- 19 Sep 2015 » Autocorrelation functions of materially different time series
- 12 Sep 2015 » Sampling distribution of Gini coefficient
- 07 Sep 2015 » Transforming the breaks to match a scale
- 05 Sep 2015 » Creating a scale transformation
- 30 Aug 2015 » Getting started in applied statistics / datascience
- 21 Aug 2015 » A better way of visualising income distributions with zeroes and negatives
- 15 Aug 2015 » Importing the New Zealand Income Survey SURF
- 07 Aug 2015 » Simulating backgammon players' Elo ratings
- 01 Aug 2015 » New Zealand Data & APIs on GitHub
- 26 Jul 2015 » Hello world!