Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Economics (4)
- Social and Behavioral Sciences (4)
- Econometrics (3)
- Applied Statistics (2)
- Community Health and Preventive Medicine (2)
-
- Medicine and Health Sciences (2)
- Mental and Social Health (2)
- Public Health (2)
- Substance Abuse and Addiction (2)
- American Politics (1)
- Analysis (1)
- Applied Mathematics (1)
- Arts and Humanities (1)
- Bioethics and Medical Ethics (1)
- Categorical Data Analysis (1)
- Civic and Community Engagement (1)
- Civil Law (1)
- Civil Rights and Discrimination (1)
- Community Health (1)
- Conflict of Laws (1)
- Constitutional Law (1)
- Criminal Law (1)
- Criminal Procedure (1)
- Criminology (1)
- Criminology and Criminal Justice (1)
- Data Science (1)
- Design of Experiments and Sample Surveys (1)
- Keyword
-
- Big Data (2)
- Data reduction (2)
- Factor analysis (2)
- PCA (2)
- Principal components regression (2)
-
- Big data (1)
- CRIMINAL justice system -- United States (1)
- CRIMINAL sentencing (1)
- Community research (1)
- Data mining (1)
- Drug use prevention (1)
- Intervention (1)
- LEGAL status of pregnant women (1)
- Methodology (1)
- Prevention science (1)
- SUBSTANCE abuse (1)
- Stepwise regression (1)
- Substance abuse reserarch (1)
- WOMEN criminals (1)
- WOMEN prisoners (1)
- Publication
- Publication Type
Articles 1 - 6 of 6
Full-Text Articles in Multivariate Analysis
Mpt And Capm Mismeasure Risk, Gary N. Smith
Mpt And Capm Mismeasure Risk, Gary N. Smith
Pomona Economics
Mean-variance analysis and the capital asset pricing model provide many useful insights for investors who want to measure and manage risk. However, their focus on short-term returns is of limited use and potentially misleading for investors with long horizons. A value investing approach suggests that risk might be better measured by long-run uncertainty about asset income than by short-run uncertainty about asset prices.
Neither “Post-War” Nor Post-Pregnancy Paranoia: How America’S War On Drugs Continues To Perpetuate Disparate Incarceration Outcomes For Pregnant, Substance-Involved Offenders, Becca S. Zimmerman
Neither “Post-War” Nor Post-Pregnancy Paranoia: How America’S War On Drugs Continues To Perpetuate Disparate Incarceration Outcomes For Pregnant, Substance-Involved Offenders, Becca S. Zimmerman
Pitzer Senior Theses
This thesis investigates the unique interactions between pregnancy, substance involvement, and race as they relate to the War on Drugs and the hyper-incarceration of women. Using ordinary least square regression analyses and data from the Bureau of Justice Statistics’ 2016 Survey of Prison Inmates, I examine if (and how) pregnancy status, drug use, race, and their interactions influence two length of incarceration outcomes: sentence length and amount of time spent in jail between arrest and imprisonment. The results collectively indicate that pregnancy decreases length of incarceration outcomes for those offenders who are not substance-involved but not evenhandedly -- benefitting white …
The Principal Problem With Principal Components Regression, Gary N. Smith, Heidi Margaret Artigue
The Principal Problem With Principal Components Regression, Gary N. Smith, Heidi Margaret Artigue
Pomona Economics
No abstract provided.
Step Away From Stepwise, Gary N. Smith
Step Away From Stepwise, Gary N. Smith
Pomona Economics
Stepwise regression is a popular data-mining tool that uses statistical significance to select the explanatory variables to be used in a multiple-regression model. A fundamental problem with stepwise regression is that some real explanatory variables that have causal effects on the dependent variable may happen to not be statistically significant, while nuisance variables may be coincidentally significant. As a result, the model may fit the data well in-sample, but do poorly out-of-sample. Many Big-Data researchers believe that, the larger the number of possible explanatory variables, the more useful is stepwise regression for selecting explanatory variables. The reality is that stepwise …
The Principal Problem With Principal Components Regression, Heidi Margaret Artigue, Gary Smith
The Principal Problem With Principal Components Regression, Heidi Margaret Artigue, Gary Smith
Pomona Faculty Publications and Research
Principal components regression (PCR) reduces a large number of explanatory variables down to a small number of principal components. PCR is thought to be more useful, the more numerous the potential explanatory variables. The reality is that a large number of candidate explanatory variables does not make PCR more valuable; instead, it magnifies the failings of PCR.
Methodological And Substantive Issues In Substance Abuse Prevention Research, C. Anderson Johnson, John W. Farquhar, Steve Sussman
Methodological And Substantive Issues In Substance Abuse Prevention Research, C. Anderson Johnson, John W. Farquhar, Steve Sussman
CGU Faculty Publications and Research
This article summarizes current issues in drug abuse prevention research through integration of other articles in this journal and by heeding historical trends in prevention science. Recommendations are made for future research directions. For prevention to advance, iterative processes are needed involving both quasi-experimental and experimental designs and involving both small, simple units and large, complex, interactive units. Accuracy of measurement and replication are of paramount importance.