scholarly journals Bayesian Crime Investigations: Integrating Actuarial And Expert Models

2021 ◽  
Author(s):  
Jared C. Allen
Keyword(s):  
Regression Analysis ◽  
Prediction Accuracy ◽  
Linear Trend ◽  
Regression Equations ◽  
Criminal Offender ◽  
Offender Characteristics ◽  
Subjective Input ◽  
Expert Ratings ◽  
Analysis Models ◽  
Expert Models

In response to concerns that some of the most methodologically rigorous predictive studies of criminal offender characteristics may yet be less generalizable and applicable than advertised or assumed, this research first tests how well seven regression analysis models (represented by 28 equations) predict characteristics across three conditions: familiar cases (used to create the regressions), less familiar cases (native to the sample used to create the regressions) and foreign cases (from a similar but novel sample). Here a linear trend shows overfitting of the models to their own sample: a drop-off in prediction accuracy relative to simple mean-based prediction as cases become more foreign (ηp 2 = .646). In response to hopes that subjective input from expert police investigators could be integrated into the models to correct for this overfitting bias, this research also tests an algorithm combining expert ratings with the regression equations. Here moderate and significant improvement in novel-case prediction is observed overall (p = .036, r = .44) and equations for all twelve expert participants are shown to improve prediction to varying degrees. These results suggest that current best methods would perform poorly in the field, but can be improved by expert insight.

scholarly journals Bayesian Crime Investigations: Integrating Actuarial And Expert Models

2021 ◽  
Author(s):  
Jared C. Allen
Keyword(s):  
Regression Analysis ◽  
Prediction Accuracy ◽  
Linear Trend ◽  
Regression Equations ◽  
Criminal Offender ◽  
Offender Characteristics ◽  
Subjective Input ◽  
Expert Ratings ◽  
Analysis Models ◽  
Expert Models

In response to concerns that some of the most methodologically rigorous predictive studies of criminal offender characteristics may yet be less generalizable and applicable than advertised or assumed, this research first tests how well seven regression analysis models (represented by 28 equations) predict characteristics across three conditions: familiar cases (used to create the regressions), less familiar cases (native to the sample used to create the regressions) and foreign cases (from a similar but novel sample). Here a linear trend shows overfitting of the models to their own sample: a drop-off in prediction accuracy relative to simple mean-based prediction as cases become more foreign (ηp 2 = .646). In response to hopes that subjective input from expert police investigators could be integrated into the models to correct for this overfitting bias, this research also tests an algorithm combining expert ratings with the regression equations. Here moderate and significant improvement in novel-case prediction is observed overall (p = .036, r = .44) and equations for all twelve expert participants are shown to improve prediction to varying degrees. These results suggest that current best methods would perform poorly in the field, but can be improved by expert insight.

Studying the factors of regional insurance market development using the correlation and regression analysis

2020 ◽  
Vol 26 (7) ◽  
pp. 1610-1630
Author(s):  
E.L. Prokop'eva
Keyword(s):  
Regression Analysis ◽  
Federal District ◽  
Insurance Market ◽  
Market Development ◽  
Insurance Markets ◽  
Regression Equations ◽  
Factors Affecting ◽  
Correlation And Regression Analysis ◽  
Country Level ◽  
Inverse Effect

Subject. The article investigates and quantifies factors of insurance markets functioning in Russian regions, and reveals possibilities to manage them. Objectives. The purpose of the study is to substantiate regional factors that determine the specifics of regional insurance market development; to quantify them to increase the efficiency of regional insurance. Methods. The study draws on statistical methods, functional analysis, algorithm development, correlation and regression analysis. Results. I calculated coefficients of pair and multiple correlation with the indicators of insurance markets in the context of the subjects of the Russian Federation, and composed regression equations. Based on the analysis, I determined the algorithm for inverse effect of the insurance market on the economic, social, fiscal and environmental performance of the region, offered appropriate measures aimed at developing the economic potential of the region and its social sphere. Conclusions. The paper considers the case of the Republic of Khakassia, one of depressed subjects in the Siberian Federal District. The developed models can be used for other regions of Russia, given the geographical and economic features of development. The findings may help generate regional strategies for socio-economic development at the country level. The scientific contribution and the novelty of the work consist of systematizing and quantifying the factors affecting the insurance mechanisms of regional markets, and assessing the inverse effect of insurance mechanisms on integrated development of the region.

PSVI-8 Meta-regression Analysis to Determine the Relationship Between Growing Pig Body Weight and Variation

2021 ◽  
Vol 99 (Supplement_1) ◽  
pp. 218-219
Author(s):  
Andres Fernando T Russi ◽  
Mike D Tokach ◽  
Jason C Woodworth ◽  
Joel M DeRouchey ◽  
Robert D Goodband ◽  
...  
Keyword(s):  
Body Weight ◽  
Regression Analysis ◽  
Sample Size ◽  
Polynomial Regression ◽  
Data Sets ◽  
Regression Equations ◽  
Prediction Equations ◽  
Data Set ◽  
Rate Of Increase ◽  
The Relationship

Abstract The swine industry has been constantly evolving to select animals with improved performance traits and to minimize variation in body weight (BW) in order to meet packer specifications. Therefore, understanding variation presents an opportunity for producers to find strategies that could help reduce, manage, or deal with variation of pigs in a barn. A systematic review and meta-analysis was conducted by collecting data from multiple studies and available data sets in order to develop prediction equations for coefficient of variation (CV) and standard deviation (SD) as a function of BW. Information regarding BW variation from 16 papers was recorded to provide approximately 204 data points. Together, these data included 117,268 individually weighed pigs with a sample size that ranged from 104 to 4,108 pigs. A random-effects model with study used as a random effect was developed. Observations were weighted using sample size as an estimate for precision on the analysis, where larger data sets accounted for increased accuracy in the model. Regression equations were developed using the nlme package of R to determine the relationship between BW and its variation. Polynomial regression analysis was conducted separately for each variation measurement. When CV was reported in the data set, SD was calculated and vice versa. The resulting prediction equations were: CV (%) = 20.04 – 0.135 × (BW) + 0.00043 × (BW)2, R2=0.79; SD = 0.41 + 0.150 × (BW) - 0.00041 × (BW)2, R2 = 0.95. These equations suggest that there is evidence for a decreasing quadratic relationship between mean CV of a population and BW of pigs whereby the rate of decrease is smaller as mean pig BW increases from birth to market. Conversely, the rate of increase of SD of a population of pigs is smaller as mean pig BW increases from birth to market.

scholarly journals Determination of individual teleroentgenographic characteristics of the face profile in ukrainian young men and girls with orthognathic bite

2018 ◽  
pp. 28-34
Author(s):  
М. О. Dmitriev
Keyword(s):  
Regression Analysis ◽  
Soft Tissue ◽  
Young Women ◽  
Stepwise Regression ◽  
Young Men ◽  
Stepwise Regression Analysis ◽  
Regression Equations ◽  
Determination Coefficient ◽  
Normal Occlusion

Modern dentistry requires the definition of individualized values of teleroentgenographic indicators. To solve such problems, methods of regression and correlation analysis are increasingly used, which help to establish not only the existence of various relationships between the anatomical structures of the head and the parameters of the dento-jaw system, but also allow more accurately predict the change in the contour of soft facial tissue in response to orthodontic treatment. The purpose of the study is to develop mathematical models for the determination of individual teleroentgenographic characteristics of the facial soft tissues by studying the cephalometric indices of young men and women of Ukraine with normal occlusion and balanced faces and conducting a direct stepwise regression analysis. With the use of Veraviewepocs 3D device, Morita (Japan) from 38 young men (17 to 21 years of age) and 55 young women (aged from 16 to 20 years) with occlusal close to the orthognathic bite and balanced faces received side teleroentgenograms. The cephalometric analysis was performed using OnyxCeph³™ licensed software. Cephalometric points and measurements were made according to the recommendations of Downs W. B., Holdway R. A., McNamara J., Schwarz A. M., Schmuth G. P. F., Steiner C. C. and Tweed C. H. With the help of direct stepwise regression analysis, in the licensed package “Statistica 6.0”, regression models of individual teleroentgenographic characteristics of the profile of soft facial tissues were constructed. In young men with normal occlusion close to the orthognathic bite of 19 possible models, 11 were constructed with a determination coefficient from 0.638 to 0.930, and in young women – 12 models with a determination coefficient from 0.541 to 0.927. The conducted analysis of models showed that in young men most often the regression equations included – angle N_POG, parameters of which indicate a linear interjaw relation in the anterior-posterior direction (14.0%); angle GL_SNPOG, or index of convexity of the soft tissue profile (8.8%); MAX maxillary length (7.0%), and GL_SN_S index, which defines vertical correlations in the facial profile (5.3%). The young women most often models included – the angle N_POG (12.5%); angle GL_SNPOG (7.5%); soft tissue front angle P_OR_N (6.25%); the reference angle ML_NL and the profile angle T (by 5.0%); the angle AB_NPOG, the angle NBA_PTGN, which defines the direction of development of the mandible and the distance PN_A (3.75%). Thus, in the work with the help of the method of stepwise regression with inclusion, among Ukrainians of adolescence age, based on the characteristics of teleroentgenographic indicators, reliable models of individual teleroentgenographic characteristics of the profile of soft facial tissues were developed and analyzed.

Inequity in Intergenerational Mobility in Transitional China and Its Dynamics: The Effects of Schooling

2012 ◽  
Vol 1 (1) ◽  
pp. 54-71 ◽  
Author(s):  
Zhou Jinyan ◽  
Chung Yue-ping
Keyword(s):  
Regression Analysis ◽  
Intergenerational Mobility ◽  
Increasing Returns ◽  
Access To Education ◽  
Economic Equality ◽  
Equity In Access ◽  
Unequal Access ◽  
Analysis Models ◽  
Transitional China ◽  
The Relationship

Abstract In this study, the relationship between schooling and intergenerational mobility was examined by applying regression analysis and path analysis models to the CHNS dataset. It was found that schooling has only small effects on status and economic equality. It was found that stronger, intermediate effects resulted from parents’ transforming advantages attached to their economic, educational and household registration status into advantages for their children. These trends, now growing stronger in transitional China, have resulted from increasing returns to education and increasingly unequal access to education. In order to prevent schooling from contributing to the solidification of economic inequality, equity in access to education must be pursued.

scholarly journals Study of the Risk and Preventive Factors for Progress of Mild Cognitive Impairment to Dementia

2020 ◽  
Vol 35 ◽  
pp. 153331752092532
Author(s):  
Chengping Hu ◽  
Ling Wang ◽  
Yi Guo ◽  
Zhicheng Cao ◽  
Ying Lu ◽  
...  
Keyword(s):  
Regression Analysis ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Cognitive Function ◽  
Epidemiological Survey ◽  
Ordinal Regression ◽  
Clinical Dementia Rating ◽  
The Status ◽  
Mini Mental Status Examination ◽  
Analysis Models

Objective: To evaluate the risk factors for progress of mild cognitive impairment to dementia. Methods: This study was based on the epidemiological survey in 2011 (No. PKJ2010-Y26) and contained 441 MCI individuals. Cognitive function was measured by the Mini-Mental Status Examination, clinical dementia rating, and montreal cognitive assessment. The association between demographic characteristics and MCI outcomes were evaluated using single-and multifactor ordered logistic regression analysis models. Results: Of the 441 MCI, 77 progressed to dementia (MCIp: 17.5%, 95% CI: 14.4%-21.6%), 356 remained stable (MCIs: 80.7%, 95% CI: 77.0%-88.4%), and 8 reverted to normal cognition (MCIr: 1.8%, 95% CI: 0.6%-3.0%) at follow-up in 2017. Univariate ordinal regression analysis showed that diabetes ( P = .052), marriage ( P = .028), worker ( P = .069), and manager ( P = .075) may be the risk factor for the status of MCI. Multiple ordinal regression results showed that diabetes ( P = .049) and marriage ( P = .04) significantly affected the cognitive function changes in the MCI patients. Conclusion: Nondiabetics and being married may prevent the progression from MCI to dementia.

Enhancing project performance by developing multiple regression analysis and risk analysis models for interface

2014 ◽  
Vol 41 (11) ◽  
pp. 929-944 ◽  
Author(s):  
Nesreen Weshah ◽  
Wael El-Ghandour ◽  
Lynne Cowe Falls ◽  
George Jergeas
Keyword(s):  
Regression Analysis ◽  
Risk Analysis ◽  
Multiple Regression Analysis ◽  
Multiple Regression ◽  
Performance Indicators ◽  
Project Performance ◽  
Interface Problems ◽  
Interface Problem ◽  
Second Phase ◽  
Analysis Models

Interface management (IM) is a main factor in the success of construction projects. The failure to correctly manage interfaces impacts a project’s performance measurements, such as scope control and schedule. Using Alberta’s data, collected using a web questionnaire from a large group of experienced industry experts, three phases are conducted in this research. The first identifies the top ten interface problems that affect IM. The second phase includes enhancing project performance by developing and applying multiple regression analysis models between the underlying interface problem factors and the project performance indicators. The last phase includes measuring the severity of the impact of each IM problem to develop an IM risk analysis model. The results of the multiple regression models indicate that the interface problems caused by the “technical engineering and site issues factor”, the “bidding and contracting factor”, and the “information factor” were the strongest influences on the schedule and cost project performance indicators. The results will assist engineers, architects, and others in analyzing and predicting the project performance. This will in turn serve to minimize project delay and cost and reduce conflict among project participants.

Review of Regression Analysis Models

2017 ◽  
Vol V6 (08) ◽  
Author(s):  
Aviral Gupta ◽  
Akshay Sharma ◽  
Dr. Amita Goel ◽  
Keyword(s):  
Regression Analysis ◽  
Analysis Models
Sign in / Sign up

Export Citation Format

Share Document