Search

Your search keyword '"PROBIT REGRESSION"' showing total 381 results
Start Over Descriptor "PROBIT REGRESSION"
381 results on '"PROBIT REGRESSION"'

351. Measuring overlap in logistic regression

Author

Christmann, Andreas, Rousseeuw, Peter J., Applied Mathematics, and Vrije Universiteit Brussel

Subjects
Overlap, separation, ddc:519, linear discriminant analysis, regression depth, Linear discriminant analysis, logistic regression, outliers, Logistic regression, Separation, probit regression, Linear discriminant analysis,Logistic regression,Outliers,Overlap,Probit regression,Regression depth,Separation, Probit regression, overlap, Outliers, Regression depth
Abstract

In this paper we show that the recent notion of regression depth can be used as a data-analytic tool to measure the amount of separation between successes and failures in the binary response framework. Extending this algorithm allows us to compute the overlap in data sets which are commonly fitted by logistic regression models. The overlap is the number of observations that would need to be removed to obtain complete or quasicomplete separation, i.e. the situation where the logistic regression parameters are no longer identifiable and the maximum likelihood estimate does not exist. It turns out that the overlap is often quite small.

Published
2001

352. Understanding Population-Specific Age Estimation Using Multivariate Cumulative Probit Regression For Asian Skeletal Samples

Author

Kim, Ji Eun

Subjects
Age-at-death estimation, Bayesian inference, Probit regression, Japanese, Thais, Biological and Physical Anthropology
Abstract

For many years, the field of anthropology has encouraged anthropologists to assume that population variation exists in skeletal aging although interpretations of population specificity in skeletal aging have been inconsistent. This project investigates age progressive changes in modern East and Southeast Asian populations, and attempts to quantify the magnitude of differences or similarities in skeletal aging between different Asian groups as a first step to develop a more inclusive age estimation method for Asian populations. Specifically, this study explores the utility of currently available age estimation methods for Asian populations, asks whether a population-specific aging method should be region-specific (Thai vs. Japan) or continental-specific (Asian), and investigates whether population specificity in age estimation is needed at all. To achieve these goals, data from four skeletal collections representing 20th century Japanese and modern Thais were collected. The four age estimation methods were applied: Transition Analysis (TA) (Boldsen et al. 2002b), plus three ‘conventional’ methods of Suchey and Katz (1998), Lovejoy et al. (1985a), and Meindl and Lovejoy (1985). To develop age estimation models for the Asian samples, while minimizing methodological error a multivariate ordered probit regression model was fitted to the Asian skeletal data under a Bayesian framework. The results of this study show that Japanese-specific age estimation models do not necessarily increase error in age estimates of Thai populations, and vice versa. Thus, multivariate ordered probit models fitted on a pooled sample of Japanese and Thais yielded significantly improved age estimates. Although TA and conventional methods yielded reasonable age estimates for Japanese and Thai populations, the probit models of pooled Asian groups outperformed those methods. The results are even more promising when the scores of TA and conventional methods were combined to fit a multivariate ordered probit model. Broader implications of this research is that, at least for Japanese and Thais, a single age estimation method can be developed. In addition, any error and bias in ages at death estimation may not be due to differences in population-specificity in skeletal aging and age estimation error induced by biased reference samples may be greater than expected.

Published
2016

353. Fast Bayesian Variable Screenings for Binary Response Regressions with Small Sample Size.

Author

Chang SM, Tzeng JY, and Chen RB

Abstract

Screening procedures play an important role in data analysis, especially in high-throughput biological studies where the datasets consist of more covariates than independent subjects. In this article, a Bayesian screening procedure is introduced for the binary response models with logit and probit links. In contrast to many screening rules based on marginal information involving one or a few covariates, the proposed Bayesian procedure simultaneously models all covariates and uses closed-form screening statistics. Specifically, we use the posterior means of the regression coefficients as screening statistics; by imposing a generalized g-prior on the regression coefficients, we derive the analytical form of their posterior means and compute the screening statistics without Markov chain Monte Carlo implementation. We evaluate the utility of the proposed Bayesian screening method using simulations and real data analysis. When the sample size is small, the simulation results suggest improved performance with comparable computational cost.

Published
2017
Full Text
View/download PDF

354. Variable selection in semi-parametric models.

Author

Zhang H, Maity A, Arshad H, Holloway J, and Karmaus W

Subjects
Cotinine analysis, CpG Islands, Creatinine metabolism, Cytochrome P-450 CYP1A1 genetics, Datasets as Topic, Female, Humans, Mothers, Pregnancy, Bayes Theorem, DNA Methylation, Epistasis, Genetic, Linear Models, Normal Distribution, Smoking genetics
Abstract

We propose Bayesian variable selection methods in semi-parametric models in the framework of partially linear Gaussian and problit regressions. Reproducing kernels are utilized to evaluate possibly non-linear joint effect of a set of variables. Indicator variables are introduced into the reproducing kernels for the inclusion or exclusion of a variable. Different scenarios based on posterior probabilities of including a variable are proposed to select important variables. Simulations are used to demonstrate and evaluate the methods. It was found that the proposed methods can efficiently select the correct variables regardless of the feature of the effects, linear or non-linear in an unknown form. The proposed methods are applied to two real data sets to identify cytosine phosphate guanine methylation sites associated with maternal smoking and cytosine phosphate guanine sites associated with cotinine levels with creatinine levels adjusted. The selected methylation sites have the potential to advance our understanding of the underlying mechanism for the impact of smoking exposure on health outcomes, and consequently benefit medical research in disease intervention., Competing Interests: The authors declare that there is no conflict of interest., (© The Author(s) 2013.)

Published
2016
Full Text
View/download PDF

355. Advantages of Joint Modeling of Component HIV Risk Behaviors and Non-Response: Application to Randomized Trials in Cocaine-Dependent and Methamphetamine-Dependent Populations.

Author

Holmes TH, Anderson AL, Li SH, and Elkashef AM

Abstract

The HIV risk-taking behavior scale (HRBS) is an 11-item instrument designed to assess the risks of HIV infection due to self-reported injection-drug use and sexual behavior. A retrospective analysis was performed on HRBS data collected from approximately 1,000 participants pooled across seven clinical trials of pharmacotherapies for either the treatment of cocaine dependence or methamphetamine dependence. Analysis faced three important challenges. The sample contained a high proportion of missing assessments after randomization. Also, the HRBS scale consists of two distinct behavioral components which may or may not coincide in response patterns. In addition, distributions of responses on the subscales were highly concentrated at just a few values (e.g., 0, 6). To address these challenges, a single probit regression model was fit to three outcomes variables simultaneously - the two subscale totals plus an indicator variable for assessments not obtained (non-response). This joint-outcome regression model was able to identify that those who left assessment early had higher self-reported risk of injection-drug use and lower self-reported risky sexual behavior because the model was able to draw on information on associations among the three outcomes collectively. These findings were not identified in analyses performed on each outcome separately. No evidence for an effect of pharmacotherapies was observed, except to reduce missing assessments. Univariate-outcome modeling is not recommended for the HRBS.

Published
2011
Full Text
View/download PDF

356. Economic policy uncertainty, financial markets and probability of US recessions

Author

Lilia Karnizova and Jiaxiong (Chris) Li

Subjects
Economics and Econometrics, Policy uncertainty, Stock market volatility, Economic policy, Financial economics, media_common.quotation_subject, Financial market, education, Term spread, Probit, social sciences, Recession, Interest rate, Recession forecast, Probit model, Probit regression, Economics, Stock (geology), Finance, health care economics and organizations, media_common
Abstract

We use probit recession forecasting models to assess the ability of economic policy uncertainty indexes developed by Baker et al. (2013) to predict future US recessions. The model specifications include policy indexes on their own, and in combination with financial variables, such as interest rate spreads, stock returns and stock market volatility. Both in-sample and out-of-sample analysis suggests that the policy uncertainty indexes are statistically and economically significant in forecasting recessions at the horizons beyond five quarters. The index based on newspaper reports emerges as the best predictor, outperforming the term spread at the longer forecast horizons.

Full Text
View/download PDF

358. Utilization of graduate education in the United States Marine Corps

Author

Hatch, William D. II, Tick, Simona, McCarthy, Mitchell, Graduate School of Business and Public Policy (GSBPP), Ealy, Daniel A., Hatch, William D. II, Tick, Simona, McCarthy, Mitchell, Graduate School of Business and Public Policy (GSBPP), and Ealy, Daniel A.

Abstract

This research was conducted at the request of Marine CorpsUniversity and examined the utilization of 344 graduate education billets within the Marine Corps. The research findings make two recommendations: 1) DC CD&I should charter a working group and use this research as a basis to review the reallocation of under-utilized BEEC BMOSs. 2) DC CD&I should also review BEEC BMOS structure and consider a new distribution plan that includes a new graduate education requirements assessment. These billets are highly desired by units due to their excepted manning precedence level. This thesis used survey methods to collect utilization data on Marine CorpsOfficers that graduated from the Special Education Program and the Advanced Degree Program between the years of 2009 and 2013. The survey is approved through the Naval Postgraduate School Institutional Review Board (NPS IRB), sponsored through Training and Education Command (TECOM) and supported by Headquarters Marine Corps(HQMC). The data collected from the survey was analyzed to identify significant factors that are highly correlated with low and high utilization in order to improve efficiencies. Findings include initial placement rate from school to billet of 93 percent and the utilization rate reflecting self-reported usage while in billet of 75 percent, identified throughout individual tours. This difference between placement utilization reflects the disparity between top-down and bottom-up planning. Collective review and reorganization of these billets is recommended to reduce further disparity between placement and utilization rates. Objective evaluation and fair reorganization based upon high utilization will ensure Marine Corpshuman resource assets remain a constant force multiplier and act as a model for high retention strategy., http://archive.org/details/utilizationofgra1094545182, Captain, United States Marine Corps, Approved for public release; distribution is unlimited.

359. United States Marine Corps Reserve First Term Attrition Characteristics

Author

Mehay, Stephen L., Arkes, Jeremy A., Management, Herschelman, Philip R., Mehay, Stephen L., Arkes, Jeremy A., Management, and Herschelman, Philip R.

Abstract

This thesis examines the effect of attrition on USMCR NPS marines who enlisted with a 6X2 contract in FY 19942005. Three cohorts were established to determine if the events of September 11, 2001 had any impact on attrition rates with this population. The Pre-9/11 cohort enlisted in FY 19941995 and was used as a control group. The Overlap-9/11 cohort enlisted in FY 19962001, had no expectation of deployment but many did deploy in support of the Global War on Terrorism. The Post-9/11 cohort enlisted in FY 20022005 after 9/11 with full expectation to deploy. The analysis included previous attrition studies, descriptive statistics, and two different probit regression models to determine the effects of various characteristics on attrition. The variables analyzed included deployment variables, demographics, education and aptitude variables, and regional areas. The thesis found a decrease in attrition from the Pre-9/11 cohort to the Post-9/11 cohort. This was most likely caused by an increasing unemployment rate and deployments overseas. Deployments to combat areas decreased the probability of attrition. The other variables remained constant throughout the cohorts with predicted results. Overall, attrition is lower after 9/11 but as the economy improves and deployments decrease, attrition could return to Pre-9/11 levels., http://archive.org/details/unitedstatesmari109456807, Major, United States Marine Corps

360. The Effects of Combat Exposure on the Military Divorce Rate

Author

Shen, Yu-Chu, Pema, Elda, Management, DeBaun, Matthew B., Shen, Yu-Chu, Pema, Elda, Management, and DeBaun, Matthew B.

Abstract

This research investigates the effect that combat exposure has on the divorce rate for military personnel. The thesis uses demographic data from the Defense Manpower Data Center (DMDC) coupled with responses from the post-deployment health assessment (PDHA). The sample contains enlisted personnel from all four services who were married and deployed between 2001 and 2007. The probability of divorce after deployment was predicted using a probit model. Combat exposure is divided into two distinct categories, casualty experience and weapon usage. Casualty experience and weapon usage were used to create interaction terms with occupational specialties (combat arms, medical service, combat service, service support) and gender. Results indicate that in most cases, combat exposure will increase the likelihood of divorce. Additionally, a casualty experience tends to have a greater impact on divorce than does weapon usage. Specifically, weapon usage was found to increase the likelihood of divorce for personnel in the medical service (Navy) and service support (Army). A casualty experience increased the likelihood of divorce for personnel in combat arms (Marines, Army) and service support (Marines). Aside from combat exposure, the results indicate that divorce rates vary across occupational specialties and the likelihood of divorce is substantially higher for women., http://archive.org/details/theeffectsofcomb109456785, Lieutenant, United States Navy

361. A study of promotion and attrition of mid-grade officers in the U.S. Marine Corps: are assignments a key factor?

Author

Pema, Elda, Dooley, Susan, Naval Postgraduate School (U.S.), Graduate School of Business and Public Policy, Morgan, Jerry R., Pema, Elda, Dooley, Susan, Naval Postgraduate School (U.S.), Graduate School of Business and Public Policy, and Morgan, Jerry R.

Abstract

This study analyzes the relationship between selection to major in the Marine Corps, and the survival of midgrade officers to the promotion point of major, by investigating the effects of billet assignments. Specifically, this study looks at the influence of the percentage of time spent in the Fleet Marine Forces (FMF), the percentage of time spent in primary military occupation (PMOS) billet assignments, and the effect of having served in combat, recruiting, security forces, joint, and drill field duties. Models were formulated using groundwork established in previous promotion, retention, and attrition studies. Assignment variables were then introduced to the models. To account for officers' choice for continued service vice forced attrition, the sample was restricted to officers who had attained five years of service. Probit regression was used to find the influence of career assignments on the probability of selection; Heckman's correction was used to control for self-selection bias; and, Cox proportionalhazard regression was used, utilizing the same assignment factors, to find the influence of assignments on the likelihood of attrition. The findings indicated that FMF and PMOS ratios above 60 percent had a negative effect on promotion and retention. Also indicated was that time spent outside the PMOS, in "B" billets, had a positive effect on retention. In a time of budgetary constraints, this information may provide assistance to personnel planners as an alternative to pecuniary measures used to maintain and shape the force., http://archive.org/details/astudyofpromotio109452214, Major, United States Marine Corps, Approved for public release; distribution is unlimited.

362. Determinants of innovation activities in small and open economies: the Lebanese business sector

Author

Hadhri, Walid, Arvanitis, Rigas, M’Henni, Hatem, Hadhri, Walid, Arvanitis, Rigas, and M’Henni, Hatem

Abstract

The question of the determinants of innovation activities in the business sector is one of the issues that take the most attention in the theoretical and empirical researches in the economics of innovation field. This paper is probably the first study that develops an econometric approach to analyze firms’ decisions to innovate in Lebanon. More precisely, we analyze the impact of firm characteristics, competition environment, human capital, R&D activities, partnership and technological transfer on good, process, organizational or marketing innovation. We use a survey of 478 industrial enterprises conducted by the local National Council for Scientific Research (CNRS) with support of the World Bank during 2011-2012. Using a probit model, the results confirm the Schumpeterian hypothesis stipulating that larger firms present a greater capability to innovate. At the same time, the market share has a positive but not significant effect on innovation. We also find significant statistical relationship between R&D activities, partnerships and technological transfers with innovation decision of Lebanese firms. In terms of policy recommendations, these results confirm the necessity to give incentives to rather large firms in order to boost innovation in the country and at the same time to implement new incentives to SMEs for the promotion of partnerships with universities, research centers and other firms, including firms in the same sector. Finally, our results confirm the point of view that the Schumpeterian hypothesis seems to suite better for small and open developing countries than developed ones.JEL Codes: O12, O3, C25

364. Prediction of unwanted pregnancies using logistic regression, probit regression and discriminant analysis

Author

Ebrahimzadeh, F., Hajizadeh, E., Vahabi, N., Mohammad Almasian, and Bakhteyar, K.

Subjects
Khorramabad, Unwanted Pregnancy, Logistic regression, Discriminant Analysis, Probit Regression, Original Article
Abstract

Background: Unwanted pregnancy not intended by at least one of the parents has undesirable consequences for the family and the society. In the present study, three classification models were used and compared to predict unwanted pregnancies in an urban population. Methods: In this cross-sectional study, 887 pregnant mothers referring to health centers in Khorramabad, Iran, in 2012 were selected by the stratified and cluster sampling; relevant variables were measured and for prediction of unwanted pregnancy, logistic regression, discriminant analysis, and probit regression models and SPSS software version 21 were used. To compare these models, indicators such as sensitivity, specificity, the area under the ROC curve, and the percentage of correct predictions were used. Results: The prevalence of unwanted pregnancies was 25.3%. The logistic and probit regression models indicated that parity and pregnancy spacing, contraceptive methods, household income and number of living male children were related to unwanted pregnancy. The performance of the models based on the area under the ROC curve was 0.735, 0.733, and 0.680 for logistic regression, probit regression, and linear discriminant analysis, respectively. Conclusion: Given the relatively high prevalence of unwanted pregnancies in Khorramabad, it seems necessary to revise family planning programs. Despite the similar accuracy of the models, if the researcher is interested in the interpretability of the results, the use of the logistic regression model is recommended.

Catalog

Books, media, physical & digital resources
See catalog results