Journal of the Royal Statistical Society: Series A (Statistics in Society)

Cover image for Vol. 180 Issue 1

Edited By: H. Goldstein and L. Sharples

Impact Factor: 1.702

ISI Journal Citation Reports © Ranking: 2015: 13/49 (Social Sciences Mathematical Methods); 24/123 (Statistics & Probability)

Online ISSN: 1467-985X

Associated Title(s): Journal of the Royal Statistical Society: Series B (Statistical Methodology), Journal of the Royal Statistical Society: Series C (Applied Statistics), Significance


Surviving slavery: mortality at Mesopotamia, a Jamaican sugar estate, 1762–1832, by M. Forster and S. D. Smith, Journal of the Royal Statistical Society, Series A, Statistics in Society, Volume 174, (2011), part 4, pages 907–929

Contents of folder
1. The data set in ASCII, tab-delimited, format: “2011_03_17_surviving_slavery_FOR_RELEASE.txt”
2. Extract of Stata do file for descriptive statistics and inferential analysis (females only: results for males uses similar code): “”
3. Extract of Stata do file for g-estimation: “”

1. The data set contains only the variables arising directly from the Bodleian Library sources. Users will need to define their own variables (for example, denoting slaves imported from Africa or slaves transferred from within Jamaica). The do files provide some guidance on the categorisations used in the published article.
2. Users will need to make modifications to the do files if they wish to run them on their own computers.
3. The files are made available in good faith in the hope that they will encourage researchers to replicate our results and pursue other interesting lines of research. Every effort has been made to avoid errors, but to guarantee that they have been eliminated would be unrealistic. Users therefore use the data and associated code at their own risk.
4. We welcome feedback on the data set and files and would be grateful to know if errors are identified.
5. Please check carefully the information available in all available sources relevant to the paper - the journal article itself, the supporting information ( and the Working Paper version of the article ( - before contacting us with queries. We regret we shall be unable to respond to requests for information if that information is already in the public domain.

Martin Forster
Department of Economics and Related Studies
University of York
York YO10 5DD

S. D. Smith
The Wilberforce Institute for the Study of Slavery and Emancipation
University of Hull
Hull HU1 1NE

Dataset (135kb)

Combining the intensity and sequencing of the poverty experience: a class of longitudinal poverty indices, by D. Mendola, A. Busetta and A. M. Milito, Journal of the Royal Statistical Society, Series A, Statistics in Society, Volume 174, (2011), part 4, pages 953–973

The software for the paper runs under Windows.
It requires .net framework 3.5.sp1, and is provided without any expressed or implied warranties.
The file contains, embedded, 'readme' instructions.

Daria Mendola
Dipartimento di Metodi Quantitativi per le Scienze Umane
Università di Palermo
Viale delle Scienze
90128 Palermo


Dataset (10.3MB)

The effect of survey design on household reporting of financial difficulty, by R. Breunig and R. McKibbin, Journal of the Royal Statistical Society, Series A, Statistics in Society, Volume 174, (2011), part 4, pages 991–1005

This read-me file details, step-by-step, the various do files (programs/code) used to run the regressions and data work referred to in the paper.

We use two data sources: HILDA (General Release) Release 6.0 and HES 2003-04 ** The HILDA and HES data are not provided - they are both unit record data and can only be used by approved researchers. **HILDA data: For information on obtaining a user licence contact the Melbourne Institute for Applied Economic and Social Research (e-mail:, phone: (03) 8344 2108) ** HES data, visit for details on obtaining a user licence.

**HES data setup

1. The HES data is available at three levels (household, income unit, person). This file merges them into a dataset called hes0304.dta It also creates a subsample containing only couples called couple.dta. Called by

2. Creates the household types and explanatory variables. You can restrict the HES sample to observations collected over the same period as HILDA in this file. Must be run manually. This file only needs to be executed once; the data will be saved as nuclear_v2.dta

**HILDA set up

1. Creates explanatory variables and identifies household types. Some data cleaning is required to identify households according to our criteria (matching HES). This is run manually.It only needs to be run once and produces a data file called bob_nuclear_v2.dta

**Results included in the paper 1. Joins the two data sets, Creates all tables in the paper.

Other exercises.

1. (Not included in the paper) runs probit models for each financial stress indicator by family type. Also runs regression combining family types to assess differences in responses.

Must be run manually.

2. (Not included in the paper) runs probit models for each financial stress indicator by family type. Must be run manually.

Both of these execute automatically as part of the data set up process.

Robert Breunig
Economics Program
Research School of Economics
Australian National University
Canberra ACT 0200


Dataset (16kb)

New Orleans business recovery in the aftermath of Hurricane Katrina, by J. P. LeSage, R. K. Pace, N. Lam, R. Campanella and X. Liu, Journal of the Royal Statistical Society, Series A, Statistics in Society, Volume 174, (2011), part 4, pages 1007–1027

MATLAB program files and data files to produce MCMC spatial probit estimates for binary probit store operating status on 3 streets in New Orleans.

NOTE: Use of these programs requires that you download the freely available spatial econometrics toolbox functions from: since the toolbox contains support/utility functions used by these programs

data files (with data for stores located on 3 streets):
magazine_data.txt (see katrina_job.m file for variable definitions)

data files containing latitude-longitude coordinates of stores:

katrina_job.m, a program file that reads data files and calls function
sarpx_g.m to carry out MCMC estimation and calls
prt.m - a function to print out estimation results
cr_interval.m - a support function for calculating confidence intervals

plot_effects.m - a program to plot store-level effects for all three streets, which uses results stored in a MATLAB file named period1.mat created by the program katrina_job.m, which must be executed first

James P. LeSage
McCoy School of Business Administration
Department of Finance and Economics
Texas State University--San Marcos
San Marcos
TX 78666


Dataset (57kb)