Search results

Showing 1 – 7 of 7 results.
Curated
Simple Crosstabs

Crime Hot Spot Forecasting with Data from the Pittsburgh [Pennsylvania] Bureau of Police, 1990-1998 (ICPSR 3469)

Released/updated on: 2015-08-07
Geographic coverage: United States, Pennsylvania, Pittsburgh
Time period: 1990-01-01--1998-01-01

This study used crime count data from the Pittsburgh, Pennsylvania, Bureau of Police offense reports and 911 computer-aided dispatch (CAD) calls to determine the best univariate forecast method for crime and to evaluate the value of leading indicator crime forecast models.

The researchers used the rolling-horizon experimental design, a design that maximizes the number of forecasts for a given time series at different times and under different conditions. Under this design, several forecast models are used to make alternative forecasts in parallel. For each forecast model included in an experiment, the researchers estimated models on training data, forecasted one month ahead to new data not previously seen by the model, and calculated and saved the forecast error. Then they added the observed value of the previously forecasted data point to the next month's training data, dropped the oldest historical data point, and forecasted the following month's data point. This process continued over a number of months.

A total of 15 statistical datasets and 3 geographic information systems (GIS) shapefiles resulted from this study.

The statistical datasets consist of

  • Univariate Forecast Data by Police Precinct (Dataset 1) with 3,240 cases
  • Output Data from the Univariate Forecasting Program: Sectors and Forecast Errors (Dataset 2) with 17,892 cases
  • Multivariate, Leading Indicator Forecast Data by Grid Cell (Dataset 3) with 5,940 cases
  • Output Data from the 911 Drug Calls Forecast Program (Dataset 4) with 5,112 cases
  • Output Data from the Part One Property Crimes Forecast Program (Dataset 5) with 5,112 cases
  • Output Data from the Part One Violent Crimes Forecast Program (Dataset 6) with 5,112 cases
  • Input Data for the Regression Forecast Program for 911 Drug Calls (Dataset 7) with 10,011 cases
  • Input Data for the Regression Forecast Program for Part One Property Crimes (Dataset 8) with 10,011 cases
  • Input Data for the Regression Forecast Program for Part One Violent Crimes (Dataset 9) with 10,011 cases
  • Output Data from Regression Forecast Program for 911 Drug Calls: Estimated Coefficients for Leading Indicator Models (Dataset 10) with 36 cases
  • Output Data from Regression Forecast Program for Part One Property Crimes: Estimated Coefficients for Leading Indicator Models (Dataset 11) with 36 cases
  • Output Data from Regression Forecast Program for Part One Violent Crimes: Estimated Coefficients for Leading Indicator Models (Dataset 12) with 36 cases
  • Output Data from Regression Forecast Program for 911 Drug Calls: Forecast Errors (Dataset 13) with 4,936 cases
  • Output Data from Regression Forecast Program for Part One Property Crimes: Forecast Errors (Dataset 14) with 4,936 cases
  • Output Data from Regression Forecast Program for Part One Violent Crimes: Forecast Errors (Dataset 15) with 4,936 cases.
  • The GIS Shapefiles (Dataset 16) are provided with the study in a single zip file: Included are polygon data for the 4,000 foot, square, uniform grid system used for much of the Pittsburgh crime data (grid400); polygon data for the 6 police precincts, alternatively called districts or zones, of Pittsburgh(policedist); and polygon data for the 3 major rivers in Pittsburgh the Allegheny, Monongahela, and Ohio (rivers).
Curated

Determinants of Case Growth in Federal District Courts in the United States, 1904-2002 (ICPSR 3987)

Released/updated on: 2006-03-30
Geographic coverage: United States
Time period: 1904-01-01--2002-01-01
This study analyzed the determinants of the explosion in the caseload of the United States federal district courts that commenced in 1960. First, the study sought to provide forecasts of future demands on the federal courts while reducing forecasting errors by taking account of the time series properties of the case data. The researchers constructed a comprehensive dataset based on annual aggregated civil and criminal case volumes of individual federal district courts spanning the period 1904-1998, for a total of 95 yearly observations. Secondly, the study specified and estimated multivariate econometric models of the determinants of civil case filings over time and across geographic space using panel data techniques. These empirical models were run on three alternative datasets consisting of observations on statewide, districtwide, and circuitwide United States civil, private civil, and total civil cases per capita, over the period 1960 to 1998. The empirical models included standard socioeconomic variables, such as income, population density, and race, along with variables that controlled for fixed effects associated with the courts' geographic location. The study also addressed the pressing issue of allocating judgeships across circuits and districts. Variables include total civil and criminal cases, percentage of minority population, unemployment rate, percentage of drug and immigration cases, annual unweighted and weighted total case filings per judge, and annual civil and criminal case filings per judge.
Self-published

ECIN Replication Package for "Macroeconomic Forecasting During Recessions and Expansions in the US and the Euro Area" (ICPSR 238922)

Released/updated on: 2026-01-29
Geographic coverage: United States
Time period: 1980-01-01--2023-06-01
This study systematically evaluates forecasting performance of 11 DSGE and 2 BVAR models during recessions and expansions in the US and the euro area. Results show that no single model dominates: parsimonious models perform well in stable periods and at short horizons, while richer DSGE specifications with financial frictions, flexible inflation targeting, or labor market dynamics improve forecasts during recessions. BVARs excel in interest rate forecasting, especially in expansions. Crisis-specific extensions, such as Covid-related shocks, yield temporary gains. Forecast accuracy depends on the economic state, variable, horizon, and evaluation metric, underscoring the need for a diversified, context-dependent modeling toolkit.
Curated

Firm Volatility and Credit: A Macroeconomic Analysis (ICPSR 25062)

Released/updated on: 2009-03-11
Geographic coverage: United States
This paper examines a tractable real business cycle model with idiosyncratic productivity shocks and binding credit constraints on entrepreneurs. The model shows how firm volatility increases in combination with credit market development. It further generates the observed co-movement of credit and firm volatility with output at business cycle frequencies in response to aggregate productivity shocks.
Curated

Linking Theory to Practice: Examining Geospatial Predictive Policing, Denver, Colorado, 2013-2015 (ICPSR 37299)

Released/updated on: 2020-02-26
Geographic coverage: United States, Colorado, Denver
Time period: 2013-01-01--2015-12-31

This research sought to examine and evaluate geospatial predictive policing models across the United States. The purpose of this applied research is three-fold: (1) to link theory and appropriate data/measures to the practice of predictive policing; (2) to determine the accuracy of various predictive policing algorithms to include traditional hotspot analyses, regression-based analyses, and data-mining algorithms; and (3) to determine how algorithms perform in a predictive policing process.

Specifically, the research project sought to answer questions such as:

  • What are the underlying criminological theories that guide the development of the algorithms and subsequent strategies?
  • What data are needed in what capacity and when?
  • What types of software and hardware are useful and necessary?
  • How does predictive policing "work" in the field? What is the practical utility of it?
  • How do we measure the impacts of predictive policing?

The project's primary phases included: (1) employing report card strategies to analyze, review and evaluate available data sources, software and analytic methods; (2) reviewing the literature on predictive tools and predictive strategies; and (3) evaluating how police agencies and researchers tested predictive algorithms and predictive policing processes.

Curated
Restricted

Policing by Place: A Proposed Multi-level Analysis of the Effectiveness of Risk Terrain Modeling for Allocating Police Resources, 2014-2015 [New York City] (ICPSR 36899)

Released/updated on: 2018-07-26
Geographic coverage: New York City, New York, United States
Time period: 2014-01-01--2015-12-01

These data are part of NACJD's Fast Track Release and are distributed as they were received from the data depositor. The files have been zipped by NACJD for release, but not checked or processed except for the removal of direct identifiers. Users should refer to the accompanying readme file for a brief description of the files available with this collection and consult the investigator(s) if further information is needed.

This study contains data from a project by the New York City Police Department (NYPD) involving GIS data on environmental risk factors that correlate with criminal behavior. The general goal of this project was to test whether risk terrain modeling (RTM) could accurately and effectively predict different crime types occurring across New York City. The ultimate aim was to build an enforcement prediction model to test strategies for effectiveness before deploying resources. Three separate phases were completed to assess the effectiveness and applicability of RTM to New York City and the NYPD. A total of four boroughs (Manhattan, Brooklyn, the Bronx, Queens), four patrol boroughs (Brooklyn North, Brooklyn South, Queens North, Queens South), and four precincts (24th, 44th, 73rd, 110th) were examined in 6-month time periods between 2014 and 2015. Across each time period, a total of three different crime types were analyzed: street robberies, felony assaults, and shootings.

The study includes three shapefiles relating to New York City Boundaries, four shapefiles relating to criminal offenses, and 40 shapefiles relating to risk factors.

Curated

What Are the Odds? Option-Based Forecasts of FOMC Target Changes (ICPSR 1332)

Released/updated on: 2006-11-29
This article uses the probability forecasts derived from options to assess evolving market uncertainty about Federal Reserve monetary policy actions in a variety of recent events and episodes. Options on federal funds futures contracts reveal a complete probability density function over possible Federal Reserve target rates, thus augmenting the expectations provided by federal funds futures contracts. Option-based forecasts are most useful when more than two federal funds target outcomes are plausible at an upcoming policy meeting.