Robert M O'Brien
Dados Biográficos
| ID | 4532395 |
|---|---|
| NOME | Robert M O'Brien |
| PRENOMES | Robert M |
| SOBRENOME | O'Brien |
| ASSINATURA | BRIEN R M O |
| AFILIAÇÕES | University of Oregon |
| VERIFICADO | Não |
| TOTAL DE OBRAS | 40 |
| TOTAL DE CITAÇÕES | 446 |
| TOTAL COMO AUTOR | 40 |
| TOTAL COMO EDITOR | 0 |
| PRIMEIRO ANO DE PUBLICAÇÃO | 1977 |
| ANO MAIS RECENTE DE PUBLICAÇÃO | 2017 |
| ÍNDICE H | 12 |
Dropping Highly Collinear Variables from a Model
Objective To change the common practice of eliminating independent variables from models because they produce multicollinearity in an independent variable of special interest. Methods I supplement my presentation, which is based on the purposes of regression analysis, by using Venn diagrams, simple formulas, and two small simulations. Results Independent variables that when removed from a model substantially change the statistics associated with …
Letter from the Co-Editors of Sociological Perspectives
Gendered Arrests or Gendered Sentencing
Since 1970 the percentage of women incarcerated in U.S. prisons has risen from nearly 3 percent to almost 7 percent-more than doubling in less than 40 years. This article examines explanations for this phenomenon-concentrating on two: Changes in the relative rates of arrest for females and males and sentencing reforms that were instituted during this period. The authors examine trends in female to male imprisonment rates from 1970 to 2008 across …
A Mixed Model Estimation of Age, Period, and Cohort Effects
For more than 30 years, sociologists and demographers have struggled to come to terms with the age, period, cohort conundrum: Given the linear dependency between age groups, periods, and cohorts, how can these effects be estimated separately? This article offers a partial solution to this problem. The authors treat cohort effects as random effects and age and period effects as fixed effects in a mixed model. Using this approach, they can (1) asse…
Age Period Cohort Characteristic Models
The Enduring Effects of Cohort Characteristics on Age-Specific Homicide Rates, 1960-1995
In the past decade, young people in the United States have been two to three times more likely than in the two previous decades to commit homicides, while those 25 years and older have been less likely to commit homicides than were members of their age groups in the earlier time period. These changes in youth homicide rates are associated with two cohort characteristics that are theoretically linked to criminality: relative size of cohorts and th…
Correcting Measures of Relationship between Aggregate-Level Variables for Both Unreliability and Correlated Errors
The Determinants of Deadly Force
Political or threat explanations for the state's use of internal violence suggest that killings committed by the police should be greatest in stratified jurisdictions with more minorities. Additional political effects such as race of the city's mayor or reform political arrangements are examined. The level of interpersonal violence the police encounter and other problems in departmental environments should account for these killing rates as well.…
Police Productivity and Crime Rates
According to the Uniform Crime Reports, violent crime rates increased dramatically over the past two decades. National Crime Victimization Survey data, on the other hand, indicate that the rates of violent crime remained relatively stable or dropped during this period. Which series provides a “correct” estimate of crime‐rate trends is of more than academic interest. Highly publicized statistics on crime trends influence the public's concerns abou…
Crime and Its Social Context
Identification of Confirmatory Factor Analysis Models of Arbitrary Complexity
All statistical models must be identified if the estimates are to be meaningful. Determining the identification status of the measurement portion of a structural equation model can be difficult because the resulting system of covariance equations is nonlinear. The recent literature on identification rules for the measurement portion of a structural equation model has concentrated on models of factor complexity 1, that is, models in which each obs…
Identification of Simple Measurement Models with Multiple Latent Variables and Correlated Errors
Although computer programs may estimate values for unidentified parameters, a parameter must be identified in order for there to exist a unique point estimate of its value. We provide a series of rules that can be applied easily to measurement models of complexity one to demonstrate the identifiability of their parameters. These rules can be applied to models that contain one or more latent variables and that contain observed variables with corre…
Correcting Measures of Relationship between Aggregate-Level Variables
Social scientists often use aggregate-level variables. These variables use the weighted sum of the characteristics of single elements to measure the characteristics of cases. For example, a measure of the formalization of different business organizations (cases) may be based on the mean of the responses of a sample of employees (elements) from each business to a question on the extent to which their work is rule governed. Or a measure of the seri…
Detrended UCR and NCS crime rates
The reliability of composites of referee assessments of manuscripts
Estimating the Reliability of Aggregate-Level Variables Based on Individual-Level Characteristics
Social scientists often use the mean of individual-level characteristics to describe aggregates such as organizations, schools, or programs. They seldom, however, attempt to assess the reliability of these measures. This article indicates how the internal consistency reliability of such measures can be estimated for several commonly used research designs. The method is based on generalizability theory and requires only the data that would normall…
Comparing detrended UCR and NCS crime rates over time
Relative Cohort Size and Age‐specific Crime Rates
The compositional effects of relatively large young‐adult cohorts on the total rate of serious crimes is well established. The more subtle effect of relative cohort size on age‐specific crime rates, suggested by Richard Easterlin, is more controversial. The literature contains no adequate test of Easterlin's hypothesis as it relates to crime. To provide an adequate test of Easterlin's theory, this study includes age‐specific rates and measures of…
Relative Cohort Size and Political Alienation
This commentary critiques Kahn and Masons analysis of Easterlins hypothesis. The hypothesis claims that cohort size affects a cohort members well being (e.g. unemployment rates salaries and political alienation) throughout life. Kahn and Mason used a modified Age-Period-Cohort model of Mason Mason Winsborough and Poole. The modified model included not only dummy variables but also interactive terms for each of the youngest 3 age groups by their r…
Exploring the Intersexual Nature of Violent Crimes
Data on criminal homicides (from the Uniform Crime Reports) and aggravated assaults and simple assaults (from the National Crime Surveys) are analyzed to determine the extent to which violent crimes occur within or between sexes. The routine activities approach is used to develop hypotheses, and those hypotheses are tested using models that estimate the proportion of ingroup and outgroup crimes “expected.” With the exception of homicides, in whic…
Prediction in Criminology
The Interracial Nature of Violent Crimes
Several authors have recently challenged the conception that violent crimes in the United States are disproportionately intraracial. They have posited a special propensity for black offenders to seek out white victims because of black rage and have pointed to the desirable characteristics of white victims. In this paper, three models of the race of offender and victim are developed using aggregate national data on homicide (from the Uniform Crime…
Rare events, sample size, and statistical problems in the analysis of the NCS city surveys
The Validity of Occupational Data for Immigrants
The validity of the primary source of data on the occupations of immigrants to the United States (Immigration and Naturalization Service reports) has been severely criticized. In fact, the 'substantive meaningfulness' of results based on this data has been questioned. In this article we empirically investigate the nomological validity of these occupational data using a time series analysis. We find, at least on an aggregate level, that the result…
A Computer Program for Determining the Correlation between Categorized Variables from a Bivariate Normal Distribution with a given Correlation
Data from underlying (unmeasured) continuous variables are often categorized in the process of measurement. The program described in this paper can be used to determine the correlation which results from categorizing two variables which follow a bivariate normal distribution. Different numbers of categories for each variable (e.g., 2 x 4 or 7 x 6) may be used, with different proportions of scores in each category and for different values of the c…
The Determinants of Deadly Force
Political or threat explanations for the state's use of internal violence suggest that killings committed by the police should be greatest in stratified jurisdictions with more minorities. Additional political effects such as race of the city's mayor or reform political arrangements are examined. The level of interpersonal violence the police encounter and other problems in departmental environments should account for these killing rates as well.…
Age Period Cohort Characteristic Models
Police Productivity and Crime Rates
According to the Uniform Crime Reports, violent crime rates increased dramatically over the past two decades. National Crime Victimization Survey data, on the other hand, indicate that the rates of violent crime remained relatively stable or dropped during this period. Which series provides a “correct” estimate of crime‐rate trends is of more than academic interest. Highly publicized statistics on crime trends influence the public's concerns abou…
Estimating the Reliability of Aggregate-Level Variables Based on Individual-Level Characteristics
Social scientists often use the mean of individual-level characteristics to describe aggregates such as organizations, schools, or programs. They seldom, however, attempt to assess the reliability of these measures. This article indicates how the internal consistency reliability of such measures can be estimated for several commonly used research designs. The method is based on generalizability theory and requires only the data that would normall…
The Enduring Effects of Cohort Characteristics on Age-Specific Homicide Rates, 1960-1995
In the past decade, young people in the United States have been two to three times more likely than in the two previous decades to commit homicides, while those 25 years and older have been less likely to commit homicides than were members of their age groups in the earlier time period. These changes in youth homicide rates are associated with two cohort characteristics that are theoretically linked to criminality: relative size of cohorts and th…
The Use of Pearson's with Ordinal Data
Through the use of computer simulations, Labovitz's (1970) examination of the effects of randomly stretching measurement scales on the correlation between these stretched scales and an equal distance scoring system are reformulated and extended. Specifically, we examine the effects of the number of rank categories (C) for rank-order variables on the product moment correlation (r) between stretched scales and an equal distance scoring system. The …
The Interracial Nature of Violent Crimes
Several authors have recently challenged the conception that violent crimes in the United States are disproportionately intraracial. They have posited a special propensity for black offenders to seek out white victims because of black rage and have pointed to the desirable characteristics of white victims. In this paper, three models of the race of offender and victim are developed using aggregate national data on homicide (from the Uniform Crime…
Prestige of Journals in Criminology and Criminal Justice
The prestige of professional journals is an important element in the academic world because of the relationship of journal prestige to the careers of individuals and to the reputations of academic institutions. This study investigates the system of journal prestige in the field of criminology and criminal justice, using the ratings of professional journals obtained from a sample of respondents who are members of professional associations in crimi…
Relative Cohort Size and Age‐specific Crime Rates
The compositional effects of relatively large young‐adult cohorts on the total rate of serious crimes is well established. The more subtle effect of relative cohort size on age‐specific crime rates, suggested by Richard Easterlin, is more controversial. The literature contains no adequate test of Easterlin's hypothesis as it relates to crime. To provide an adequate test of Easterlin's theory, this study includes age‐specific rates and measures of…
Metropolitan Structure and Violent Crime
Population Density and Criminal Victimization Some Unexpected Findings in Central Cities
Criminal behavior and criminal victimization have been associated with population density in the criminological literature. and this has led re‐ searchers to argue that there is a positive zero‐order relationship between population density and crime rates. However, using National Crime Survey victimization data we found that there is no simple relationship between population density and crime rates in 26 large American cities. Property crimes nit…
A Mixed Model Estimation of Age, Period, and Cohort Effects
For more than 30 years, sociologists and demographers have struggled to come to terms with the age, period, cohort conundrum: Given the linear dependency between age groups, periods, and cohorts, how can these effects be estimated separately? This article offers a partial solution to this problem. The authors treat cohort effects as random effects and age and period effects as fixed effects in a mixed model. Using this approach, they can (1) asse…
Comparing detrended UCR and NCS crime rates over time
Relative Cohort Size and Political Alienation
This commentary critiques Kahn and Masons analysis of Easterlins hypothesis. The hypothesis claims that cohort size affects a cohort members well being (e.g. unemployment rates salaries and political alienation) throughout life. Kahn and Mason used a modified Age-Period-Cohort model of Mason Mason Winsborough and Poole. The modified model included not only dummy variables but also interactive terms for each of the youngest 3 age groups by their r…
An Empirical Comparison of the Validity of UCR and NCS Crime Rates
A large volume of criminological research uses either the Uniform Crime Reports (UCR) or the National Crime Surveys (NCS) as a source for data on crime rates. The validity of both these measures, however, has been criticized. In this paper we assess the validity of these two indicators of the crime rate for six different types of crimes by examining their “convergent” and “nomological” validity. We find a moderate to high degree of convergent val…
Exploring the Intersexual Nature of Violent Crimes
Data on criminal homicides (from the Uniform Crime Reports) and aggravated assaults and simple assaults (from the National Crime Surveys) are analyzed to determine the extent to which violent crimes occur within or between sexes. The routine activities approach is used to develop hypotheses, and those hypotheses are tested using models that estimate the proportion of ingroup and outgroup crimes “expected.” With the exception of homicides, in whic…
Dropping Highly Collinear Variables from a Model
Objective To change the common practice of eliminating independent variables from models because they produce multicollinearity in an independent variable of special interest. Methods I supplement my presentation, which is based on the purposes of regression analysis, by using Venn diagrams, simple formulas, and two small simulations. Results Independent variables that when removed from a model substantially change the statistics associated with …
Gendered Arrests or Gendered Sentencing
Since 1970 the percentage of women incarcerated in U.S. prisons has risen from nearly 3 percent to almost 7 percent-more than doubling in less than 40 years. This article examines explanations for this phenomenon-concentrating on two: Changes in the relative rates of arrest for females and males and sentencing reforms that were instituted during this period. The authors examine trends in female to male imprisonment rates from 1970 to 2008 across …
Rare events, sample size, and statistical problems in the analysis of the NCS city surveys
The relationship of criminal victimization, police per capita and population density in twenty-six cities
Identification of Simple Measurement Models with Multiple Latent Variables and Correlated Errors
Although computer programs may estimate values for unidentified parameters, a parameter must be identified in order for there to exist a unique point estimate of its value. We provide a series of rules that can be applied easily to measurement models of complexity one to demonstrate the identifiability of their parameters. These rules can be applied to models that contain one or more latent variables and that contain observed variables with corre…
Detrended UCR and NCS crime rates
Periodical Prestige in Criminology and Criminal Justice
Journals in criminology and criminal justice have been ranked using subjective techniques to assess journal presitige as well as objective measures intended to assess journal eminence. Two recent studies have resulted in somewhat similar rankings of professional journals although each used distinct methods of data analysis and asked different research questions. This finding suggests that there is a consensus among professionals in the field conc…
Reducing Grouping Distortion in Rank Category Variables
Social scientists often measure variables that are best thought of as having continuous underlying distributions by using crude rank-category techniques (i.e., measures which have few rank categories). The result is a large amount of grouping error. This workshop uses computer simulations to investigate the effects of four factors which contribute to grouping error: (1) the underlying distribution of scores, (2) the marginal proportion of cases i…
Correcting Measures of Relationship between Aggregate-Level Variables for Both Unreliability and Correlated Errors
A Solution To the Problem of 'Differences in Units of Measure
It has been suggested that researchers comparing causal models across populations employ path regression coefficients corrected for unreliability. This procedure, however, does not eliminate the problem of differences in the units of measure across populations. This paper outlines a technique designed to eliminate this problem by comparing 'effect ratios,' rather than effect coefficients, across populations. Both hypothetical and real data are us…
Partial Regression Coefficients
Population Density and Criminal Victimization Some Unexpected Findings in Central Cities
Criminal behavior and criminal victimization have been associated with population density in the criminological literature. and this has led re‐ searchers to argue that there is a positive zero‐order relationship between population density and crime rates. However, using National Crime Survey victimization data we found that there is no simple relationship between population density and crime rates in 26 large American cities. Property crimes nit…
"On Kim's "Multivariate Analysis of Ordinal Variables
The Use of Pearson's with Ordinal Data
Through the use of computer simulations, Labovitz's (1970) examination of the effects of randomly stretching measurement scales on the correlation between these stretched scales and an equal distance scoring system are reformulated and extended. Specifically, we examine the effects of the number of rank categories (C) for rank-order variables on the product moment correlation (r) between stretched scales and an equal distance scoring system. The …
The relationship of criminal victimization, police per capita and population density in twenty-six cities
Social Structure and Games
Silver (1978), in this journal, reports several interesting relationships between structural characteristics of societies and their “game complexity.” This note questions these findings on the grounds that his sample size is inadequate for the analyses which he undertakes
An exploratory study of social class and energy issues
An Empirical Comparison of the Validity of UCR and NCS Crime Rates
A large volume of criminological research uses either the Uniform Crime Reports (UCR) or the National Crime Surveys (NCS) as a source for data on crime rates. The validity of both these measures, however, has been criticized. In this paper we assess the validity of these two indicators of the crime rate for six different types of crimes by examining their “convergent” and “nomological” validity. We find a moderate to high degree of convergent val…
Prestige of Journals in Criminology and Criminal Justice
The prestige of professional journals is an important element in the academic world because of the relationship of journal prestige to the careers of individuals and to the reputations of academic institutions. This study investigates the system of journal prestige in the field of criminology and criminal justice, using the ratings of professional journals obtained from a sample of respondents who are members of professional associations in crimi…
Reducing Grouping Distortion in Rank Category Variables
Social scientists often measure variables that are best thought of as having continuous underlying distributions by using crude rank-category techniques (i.e., measures which have few rank categories). The result is a large amount of grouping error. This workshop uses computer simulations to investigate the effects of four factors which contribute to grouping error: (1) the underlying distribution of scores, (2) the marginal proportion of cases i…
Periodical Prestige in Criminology and Criminal Justice
Journals in criminology and criminal justice have been ranked using subjective techniques to assess journal presitige as well as objective measures intended to assess journal eminence. Two recent studies have resulted in somewhat similar rankings of professional journals although each used distinct methods of data analysis and asked different research questions. This finding suggests that there is a consensus among professionals in the field conc…
Rank Order Versus Rank Category Measures of Continuous Variables
Metropolitan Structure and Violent Crime
A Computer Program for Determining the Correlation between Categorized Variables from a Bivariate Normal Distribution with a given Correlation
Data from underlying (unmeasured) continuous variables are often categorized in the process of measurement. The program described in this paper can be used to determine the correlation which results from categorizing two variables which follow a bivariate normal distribution. Different numbers of categories for each variable (e.g., 2 x 4 or 7 x 6) may be used, with different proportions of scores in each category and for different values of the c…
Urban Structure and Victimization
The Validity of Occupational Data for Immigrants
The validity of the primary source of data on the occupations of immigrants to the United States (Immigration and Naturalization Service reports) has been severely criticized. In fact, the 'substantive meaningfulness' of results based on this data has been questioned. In this article we empirically investigate the nomological validity of these occupational data using a time series analysis. We find, at least on an aggregate level, that the result…
Rare events, sample size, and statistical problems in the analysis of the NCS city surveys
Prediction in Criminology
The Interracial Nature of Violent Crimes
Several authors have recently challenged the conception that violent crimes in the United States are disproportionately intraracial. They have posited a special propensity for black offenders to seek out white victims because of black rage and have pointed to the desirable characteristics of white victims. In this paper, three models of the race of offender and victim are developed using aggregate national data on homicide (from the Uniform Crime…
Exploring the Intersexual Nature of Violent Crimes
Data on criminal homicides (from the Uniform Crime Reports) and aggravated assaults and simple assaults (from the National Crime Surveys) are analyzed to determine the extent to which violent crimes occur within or between sexes. The routine activities approach is used to develop hypotheses, and those hypotheses are tested using models that estimate the proportion of ingroup and outgroup crimes “expected.” With the exception of homicides, in whic…
Relative Cohort Size and Age‐specific Crime Rates
The compositional effects of relatively large young‐adult cohorts on the total rate of serious crimes is well established. The more subtle effect of relative cohort size on age‐specific crime rates, suggested by Richard Easterlin, is more controversial. The literature contains no adequate test of Easterlin's hypothesis as it relates to crime. To provide an adequate test of Easterlin's theory, this study includes age‐specific rates and measures of…
Relative Cohort Size and Political Alienation
This commentary critiques Kahn and Masons analysis of Easterlins hypothesis. The hypothesis claims that cohort size affects a cohort members well being (e.g. unemployment rates salaries and political alienation) throughout life. Kahn and Mason used a modified Age-Period-Cohort model of Mason Mason Winsborough and Poole. The modified model included not only dummy variables but also interactive terms for each of the youngest 3 age groups by their r…
Estimating the Reliability of Aggregate-Level Variables Based on Individual-Level Characteristics
Social scientists often use the mean of individual-level characteristics to describe aggregates such as organizations, schools, or programs. They seldom, however, attempt to assess the reliability of these measures. This article indicates how the internal consistency reliability of such measures can be estimated for several commonly used research designs. The method is based on generalizability theory and requires only the data that would normall…
Comparing detrended UCR and NCS crime rates over time
Psychology (26 obras) · Mathematics (23 obras) · Statistics (22 obras) · Sociology (18 obras) · Crime Patterns and Interventions (17 obras) · Criminology (15 obras) · Econometrics (14 obras) · Computer Science (11 obras) · Economics (10 obras) · Social Psychology (9 obras)