Replication data for: A Solution to the Ecological Inference Problem: Reconstructing Individual Behavior from Aggregate Data (doi:10.7910/DVN/XXGY0B)

View:

Part 1: Document Description
Part 2: Study Description
Part 3: Data Files Description
Part 4: Variable Description
Part 5: Other Study-Related Materials
Entire Codebook

Replication data for: A Solution to the Ecological Inference Problem: Reconstructing Individual Behavior from Aggregate Data

doi:10.7910/DVN/XXGY0B

Harvard Dataverse

2007-11-28

5

King, Gary, 2007, "Replication data for: A Solution to the Ecological Inference Problem: Reconstructing Individual Behavior from Aggregate Data", https://doi.org/10.7910/DVN/XXGY0B, Harvard Dataverse, V5, UNF:3:DRWozWd89+vNLO7lY2AHbg== [fileUNF]

Replication data for: A Solution to the Ecological Inference Problem: Reconstructing Individual Behavior from Aggregate Data

doi:10.7910/DVN/XXGY0B

King, Gary (Harvard University)

1997

Harvard Dataverse

Harvard Dataverse

2006

1997

https://doi.org/10.7910/DVN/XXGY0B

Social Sciences

<b>Preface from the book:</b> <br /><br />In this book, I present a solution to the ecological inference problem: a method of inferring individual behavior from aggregate data that works in practice. Ecological inference is the process of using aggregate (i.e., "ecological'') data to infer discrete individual-level relationships of interest when individual-level data are not available. Existing methods of ecological inference generate very inaccurate conclusions about the empirical world--which thus gives rise to the ecological inference problem. Most scholars who analyze aggregate data routinely encounter some form of the th is problem. <br /><br />The ecological inference problem has been among the longest standing, hitherto unsolved problems in quantitative social science. It was originally raised over seventy-five years ago as the first statistical problem in the nascent discipline of political science, and it has held back research agendas in most of its empirical subfields. Ecological inferences are required in political science research when individual-level surveys are unavailable (for example, local or compa rative electoral politics), unreliable (racial politics), insufficient (political geography), or infeasible (political history). They are also required in numerous areas of major significance in public policy (for example, for applying the Voting Rights Act) and other academic disciplines, ranging from epidemiology and marketing to sociology and quantitative history. <br /><br />Because the ecological inference problem is caused by the lack of individual-level information, no method of ecological inference, including that introduced in this book, will produce precisely accurate results in every instance. However, potential difficulties are minimized here by models that include more available information, diagnostics to evaluate when assumptions need to be modified, and realistic uncertainty estimates for all quantities of interest. For political methodologis ts, many opportunities remain, and I hope the results reported here lead to continued research into and further improvements in the methods of ecological inference. But most importantly, the solution to the ecological inference problem presented here is designed so that empirical researchers can investigate substantive questions that have heretofore proved intractable. Perhaps it will also lead to new theories and empirical research in areas where analysts have feared to tread due to the lack of reliable ecological methods or individual-level data. <br /><br /> You can order the <a href="http://www.amazon.com/exec/obidos/ISBN=0691012407/9272-6410949-261461" target="_blank">paperback</a> (ISBN 0-691-01240-7) or <a href="http://www.amazon.com/exec/obidos/ISBN=0691012415/9272-6410949-261461/" target="_blank"> hardcover</a> (ISBN 0-691-01241-5) over the web. Here also is a link to the text; the original data used in the book are available for <a href="http://gking.harvard.edu/files/gking/files/eirepl.zip" target="_blank">Unix</a>, and <a href="http://gking.harvard.edu/files/gking/files/eirepl.zip/" target="_blank">Windows NT</a>.<br /><br /> You can also read a <a href="http://www.h-net.org/reviews/showrev.php?id=1792" target="_blank">scholarly review</a> and an <a href="http://gking.harvard.edu/eicamera/nyt.shtml" target="_blank">article</a> from the New York Times, and <a href="http://gking.harvard.edu/eicamera/globe.shtml" target="_blank">another</a> from the <i>Boston Globe</i>, about this book. This book won the <i>Gosnell Prize</i> for the best methodological work in political science in the preceding year, and was listed as one of the <a href="http://web.archive.org/web/20010421212147/http://www.sevenbridgespress.com/lf/Special/books.9905.html" target="_blank"><i>Breakthrough Books in Geography</i></a>; <a href="http://gking.harvard.edu/ei" target="_blank">the accompanying software </a> won the APSA Research Software Award. <br /><br /> See also: <a href="http:// gking.harvard.edu/category/research-interests/methods/ecological-inference" target="_blank">Ecological Inference </a>

This dataset is made available without information on how it can be used. You should communicate with the Contact(s) specified before use.

King, Gary. 1997. A Solution to the Ecological Inference Problem: Reconstructing Individual Behavior from Aggregate Data. Princeton: Princeton University Press. The preface, introduction and first chapter of this book is available online: <a href= "http://j.mp/kpuI5R" target="_blank">book information available here</a>.

King, Gary. 1997. A Solution to the Ecological Inference Problem: Reconstructing Individual Behavior from Aggregate Data. Princeton: Princeton University Press. The preface, introduction and first chapter of this book is available online: <a href= "http://j.mp/kpuI5R" target="_blank">book information available here</a>.

• Number of cases: 250

• No. of variables per record: 2

• Type of File: text/tab-separated-values

UNF:3:sT6ZeeZFxN0ss62qwQuCjA==

Hispanic Voters Data. Figures 5.1 and 5.5.

• Number of cases: 660

• No. of variables per record: 5

• Type of File: text/tab-separated-values

UNF:3:rZPEBVDyq4yPJu39GYIIww==

Indiana data. Figures 4.1 and 4.1.

• Number of cases: 1677

• No. of variables per record: 5

• Type of File: text/tab-separated-values

UNF:3:Khiv0wp35w9IKSjT3EZlFA==

Pennsylvania Data . Figure 4.3.

• X_I
• T_I
• X_I
• V_I
• T_I
• V4
• V5
• X_I
• V_I
• T_I
• V4
• V5

f100918 Location:

Variable Format: numeric

Notes: UNF:3:gp4vXPSPpHqP5YuNc9uukQ==

f100918 Location:

Variable Format: numeric

Notes: UNF:3:CDUlklJk9R2oxHaD3TtF2A==

f100927 Location:

Variable Format: numeric

Notes: UNF:3:Dcg2pSz/JTRP+TQ4eRaTzQ==

f100927 Location:

Variable Format: numeric

Notes: UNF:3:bamxtpwJlDXwEi1iGA90rw==

f100927 Location:

Variable Format: numeric

Notes: UNF:3:Tqy+JBwmBUDP4crwiXj73w==

f100927 Location:

Variable Format: numeric

Notes: UNF:3:BJzp/qQshjRVgAbF9XWOXg==

f100927 Location:

Variable Format: numeric

Notes: UNF:3:y+CPVxT2I595MYrdIejOmw==

f100930 Location:

Variable Format: numeric

Notes: UNF:3:YqeBn9O0rMogWwhoIOLdHw==

f100930 Location:

Variable Format: numeric

Notes: UNF:3:tPk2qI3IpaCAWoS3yC+aDA==

f100930 Location:

Variable Format: numeric

Notes: UNF:3:eJQFL5782GpsJBT8o0iwkg==

f100930 Location:

Variable Format: numeric

Notes: UNF:3:5oSjkP7BAQlDkJX1QzpK1w==

f100930 Location:

Variable Format: numeric

Notes: UNF:3:f0RUdcuvUwp/Tmz+3+RG5A==

Label:

cens1910.fmt

Text:

1910 Census Data. Section 13.1, Black literacy in 1910(Output data buffers in standard EI format for an HPUX machine).

application/octet-stream

Label:

ei.zip

Text:

EI 1.0 Source Code (in Gauss source format, zipped). This is the version of the program used to run the analyses in the book. The program requires Gauss (version 3.2.18, Dec 5, 1995), and CML (version 1.0.15). We recommend you use the new version for subsequent analysis; see http://gking.harvard.edu/stats.shtml#ei

application/zip

Label:

fultongen.fmt

Text:

Fulton County Data. Section 13.1, voter transitions. (Output data buffers in standard EI format for an HPUX machine).

application/octet-stream

Label:

hisp.asc

Text:

Hispanic Voters Data. Figures 5.1 and 5.5., ASCII Format

text/plain; charset=US-ASCII

Label:

in90.asc

Text:

Indiana data, Figures 4.1 and 4.1., ASCII Format

text/plain; charset=US-ASCII

Label:

kyck88.fmt

Text:

Kentuck Data. Chapter 12. Black registration in Kentucky (Output data buffers in standard EI format for an HPUX machine).

application/octet-stream

Label:

lavoteall.fmt

Text:

Louisiana Data. Figure 1.1, turnout by race in Lousiana (Output data buffers in standard EI format for an HPUX machine)

application/octet-stream

Label:

matproii.fmt

Text:

Marion County Data. Chapter 10. Voter registration by race (Output data buffers in standard EI format for an HPUX machine)

application/octet-stream

Label:

nj.fmt

Text:

New Jersey Data. Figure 1.2, nonminority turnout in New Jersey MCDs (Output data buffers in standard EI format for an HPUX machine).

application/octet-stream

Label:

pa90.asc

Text:

Pennasylvania Data. Figure 4.3. , ASCII Format

text/plain; charset=US-ASCII

Label:

README

Text:

Detailed information about replication data files

text/plain; charset=US-ASCII

Label:

Readme_nt.txt

Text:

Additional information for Windows NT data files

text/plain; charset=US-ASCII

Label:

scsp.fmt

Text:

South Carolina Data. Chapter 11. Poverty status by sex(Output data buffers in standard EI format for an HPUX machine).

application/octet-stream

Label:

ZIPforWindows NT.Zip

Text:

Versions of the files made available for replication of A Solution to the Problem of Ecological Inference. Princeton Univeristy Press, 1997. The files are converted from Gauss's unix matrix format (v92) to Gauss's universal matrix format (v96). The files are configured to be read using Gauss for NT by Jeff Lewis.

application/octet-stream