Sample records for multinomial logit nmnl

  1. Logit Models for Estimating Urban Area Through Travel

    E-Print Network [OSTI]

    Talbot, Eric

    2011-10-21T23:59:59.000Z

    LOGIT MODELS FOR ESTIMATING URBAN AREA THROUGH TRAVEL A Thesis by ERIC TALBOT Submitted to the Office of Graduate Studies of Texas A&M University in partial fulfillment of the requirements for the degree... of MASTER OF SCIENCE August 2010 Major Subject: Civil Engineering LOGIT MODELS FOR ESTIMATING URBAN AREA THROUGH TRAVEL A Thesis by ERIC TALBOT Submitted to the Office of Graduate Studies of Texas A...

  2. Supporting Text Approximation of the Multinomial. Using Stirling's approximation

    E-Print Network [OSTI]

    Peterson, Carsten

    Supporting Text Approximation of the Multinomial. Using Stirling's approximation n! (n/e)n 2n! . [S12] To calculate B L (^n) limN BN L (^n), we apply Stirling's formula to N!, n0!, and n1!, which that r Stirling's formula

  3. Characteristics of rural bank acquisitions: a logit analysis

    E-Print Network [OSTI]

    Applewhite, Jennifer Lynn

    1994-01-01T23:59:59.000Z

    interstate acquisition of their banks, the rate of acquisitions soared. In 1978, Maine enacted legislation permitting interstate banking on a reciprocal basis. Until mid-1982, Maine was the only state with such a law. In 1982, both New York and Alaska... of U. S. banks using comparative performance profiles and logit analysis. Characteristics of acquired and acquiring banks are compared for five years before the acquisitions and found to have significantly different rates of return on assets...

  4. Estimating long-term world coal production with logit and probit transforms David Rutledge

    E-Print Network [OSTI]

    Weinreb, Sander

    from measurements of coal seams. We show that where the estimates based on reserves can be testedEstimating long-term world coal production with logit and probit transforms David Rutledge form 27 October 2010 Accepted 27 October 2010 Available online 4 November 2010 Keywords: Coal reserves

  5. Etude du choix d'acquisition d'automobiles : Application du modle probit multinomial baysien

    E-Print Network [OSTI]

    Paris-Sud XI, Université de

    Etude du choix d'acquisition d'automobiles : Application du modèle probit multinomial bayésien à l comportementale du choix individuel des agents lors d'une nouvelle acquisition automobile. En croisant les trois, Motorisation, Automobile. Classification JEL : C11 ; C25 Correspondance à : Roger Collet, INRETS/DEST, 2

  6. In Proceedings of the International Symposium on Performance Analysis of Systems and Software (ISPASS 2006). Comparing Multinomial and K-Means Clustering for SimPoint

    E-Print Network [OSTI]

    Calder, Bradley

    (ISPASS 2006). Comparing Multinomial and K-Means Clustering for SimPoint Greg Hamerly Erez Perelman Brad represent an accurate picture of the complete execution of the program. SimPoint is based on the k-means of us- ing k-means and multinomial clustering for SimPoint. We show that k-means performs better than

  7. A Plug-in Hybrid Consumer Choice Model with Detailed Market Segmentation

    SciTech Connect (OSTI)

    Lin, Zhenhong [ORNL] [ORNL; Greene, David L [ORNL] [ORNL

    2010-01-01T23:59:59.000Z

    This paper describes a consumer choice model for projecting U.S. demand for plug-in hybrid electric vehicles (PHEV) in competition among 13 light-duty vehicle technologies over the period 2005-2050. New car buyers are disaggregated by region, residential area, attitude toward technology risk, vehicle usage intensity, home parking and work recharging. The nested multinomial logit (NMNL) model of vehicle choice incorporates daily vehicle usage distributions, refueling and recharging availability, technology learning by doing, and diversity of choice among makes and models. Illustrative results are presented for a Base Case, calibrated to the Annual Energy Outlook (AEO) 2009 Reference Updated Case, and an optimistic technology scenario reflecting achievement of U.S. Department of Energy s (DOE s) FreedomCAR goals. PHEV market success is highly dependent on the degree of technological progress assumed. PHEV sales reach one million in 2037 in the Base Case but in 2020 in the FreedomCARGoals Case. In the FreedomCARGoals Case, PHEV cumulative sales reach 1.5 million by 2015. Together with efficiency improvements in other technologies, petroleum use in 2050 is reduced by about 45% from the 2005 level. After technological progress, PHEV s market success appears to be most sensitive to recharging availability, consumers attitudes toward novel echnologies, and vehicle usage intensity. Successful market penetration of PHEVs helps bring down battery costs for electric vehicles (EVs), resulting in a significant EV market share after 2040.

  8. Technical Report Documentation Page 1. Report No.

    E-Print Network [OSTI]

    can be used to control, manage, and shape individual traveler behavior and aggregate travel demand multinomial logit-ordered response structure that (a) accommodates differential sensitivity to the built The contents of this report reflect the views of the authors, who are responsible for the facts

  9. 1 October 17, 2001 Department of Agricultural and Resource Economics ARE 213, Fall 2001

    E-Print Network [OSTI]

    Sadoulet, Elisabeth

    , GA. "Estimating the demand for a new technology: Bt cotton and insecticide policies." American Review, Vol. 16, No. 2, June 1975. (Multinomial logit) Vandeveer, M.L. and E.T. Loehman. "Farmer Response of Wisconsin Milk Producers - An Aggregate Analysis." American Journal of Agricultural Economics, 1995 Nov, V77

  10. Tracking Land Cover Change in a Mixed Logit Model: Recognizing Temporal and Spatial Effects

    E-Print Network [OSTI]

    Kockelman, Kara M.

    , but high residential densities can impede future development. Model application produces graphic in order to demonstrate compliance with air quality- related planning standards. Moreover, with further

  11. Residential mobility and location choice: a nested logit model with sampling of alternatives

    E-Print Network [OSTI]

    Lee, Brian H.; Waddell, Paul

    2010-01-01T23:59:59.000Z

    empirical results from the Puget Sound region. Environ.residences from the central Puget Sound region. It usesapplication in the Central Puget Sound region The NL model

  12. Numerical Experiments with AMLET, a New Monte Carlo Algorithm for Estimating Mixed Logit Models

    E-Print Network [OSTI]

    Toint, Philippe

    th International Conference on Travel Behaviour Research Lucerne, 1015. August 2003 #12 at the 10 th International Conference on Travel Behaviour Research, Lucerne, August 2003. 1 Research Fellow

  13. Residential mobility and location choice: a nested logit model with sampling of alternatives

    E-Print Network [OSTI]

    Lee, Brian H.; Waddell, Paul

    2010-01-01T23:59:59.000Z

    Waddell, P. : Modeling residential location in UrbanSim. In:D. (eds. ) Modelling Residential Location Choice. Springer,based model system and a residential location model. Urban

  14. Z .Social Networks 21 1999 3766 primer: logit models for social networks

    E-Print Network [OSTI]

    Fienberg, Stephen E.

    a,b,) , Stanley Wasserman b,c,d,1 , Bradley Crouch b,2 a Department of Educational Psychology, Uni: Jossey-Bass, pp. 156192; Fienberg, S.E., Meyer, M.M., Wasserman, S., 1985. Statistical analysis

  15. Bounds on the expected entropy and KL-divergence of sampled multinomial distributions

    E-Print Network [OSTI]

    Roy, Deb

    the samples are iid p, then the expected number of samples in bin i can be calculated as = n k=0 n k pk i (1 i (1 - pi)n-k k log k n Note that in this equation, pi is the true probability of bin i in p rather C. Roy bcroy@media.mit.edu Original: May 18, 2011 Revised: June 6, 2011 Abstract Information

  16. Co-relation of Variables Involved in the Occurrence of Crane Accidents in U.S. through Logit Modeling.

    E-Print Network [OSTI]

    Bains, Amrit Anoop Singh

    2010-10-12T23:59:59.000Z

    One of the primary reasons of the escalating rates of injuries and fatalities in the construction industry is the ever so complex, dynamic and continually changing nature of construction work. Use of cranes has become imperative to overcome...

  17. Econometric Analysis of Discrete-Valued Irregularly-Spaced Financial Transactions Data Using a New Autoregressive Conditional Multinomial Model

    E-Print Network [OSTI]

    Russell, Jeffrey; Engle, Robert F

    1998-01-01T23:59:59.000Z

    Lancaster, T. , 1990, The Econometric Analysis of TransitionDEPARTMENT OF ECONOMICS ECONOMETRIC ANALYSIS OF DISCRETE-PAPER 98-10 APRIL 1998 Econometric analysis of discrete-

  18. OAK RIDGE NATIONAL LABORATORY U. S. DEPARTMENT OF ENERGY

    E-Print Network [OSTI]

    . S. DEPARTMENT OF ENERGY Drawing from several other DOE models, HyTrans integrates supply and demand/ASCM) Consumer demand: NMNL/representative consumer 3 geographic, 3 fuel demand density regions Key dynamic and model choice. Light-duty Vehicles Sales Fuel Cell Vehicles Hydrogen ICE CH2 FCV ICEs Gasoline Diesel

  19. The Belief Bias Effect Is Aptly Named: A Reply to Klauer and Kellen (2011)

    E-Print Network [OSTI]

    Wixted, John T.

    2011-01-01T23:59:59.000Z

    ) multinomial processing tree (MPT) model to confidence ratings (henceforth, MPTC) describes the data better

  20. The results of a world-wide study on yield improvement are presented. Die yields col-lected from 21 fabs are transformed via a logit formula and compared. The die yields and

    E-Print Network [OSTI]

    California at Berkeley, University of

    -aided manufacturing practices and statistical process control practices in addition to commonly cited practices improvement rates of the fabs are compared, and manufacturing yield improve- ment practices are evaluated such as particle control and advanced manufacturing technology. #12;Introduction The results of a world-wide study

  1. Future Potential of Hybrid and Diesel Powertrains in the U.S. Light-duty Vehicle Market

    SciTech Connect (OSTI)

    Greene, D.L.

    2004-08-23T23:59:59.000Z

    Diesel and hybrid technologies each have the potential to increase light-duty vehicle fuel economy by a third or more without loss of performance, yet these technologies have typically been excluded from technical assessments of fuel economy potential on the grounds that hybrids are too expensive and diesels cannot meet Tier 2 emissions standards. Recently, hybrid costs have come down and the few hybrid makes available are selling well. Diesels have made great strides in reducing particulate and nitrogen oxide emissions, and are likely though not certain to meet future standards. In light of these developments, this study takes a detailed look at the market potential of these two powertrain technologies and their possible impacts on light-duty vehicle fuel economy. A nested multinomial logit model of vehicle choice was calibrated to 2002 model year sales of 930 makes, models and engine-transmission configurations. Based on an assessment of the status and outlook for the two technologies, market shares were predicted for 2008, 2012 and beyond, assuming no additional increase in fuel economy standards or other new policy initiatives. Current tax incentives for hybrids are assumed to be phased out by 2008. Given announced and likely introductions by 2008, hybrids could capture 4-7% and diesels 2-4% of the light-duty market. Based on our best guesses for further introductions, these shares could increase to 10-15% for hybrids and 4-7% for diesels by 2012. The resulting impacts on fleet average fuel economy would be about +2% in 2008 and +4% in 2012. If diesels and hybrids were widely available across vehicle classes, makes, and models, they could capture 40% or more of the light-duty vehicle market.

  2. A Quantitative Analysis of Previously Launched Adults

    E-Print Network [OSTI]

    Farris, Demetrea Nicole

    2012-02-14T23:59:59.000Z

    " of either previously launched or failure to launch. I undertake two multinomial logistic regression models with the dependent variable "launching status." I then proceed to a replication of the original analysis with two other multinomial logistic regression...

  3. Bernoulli 19(1), 2013, 295307 DOI: 10.3150/11-BEJ393

    E-Print Network [OSTI]

    McKeague, Ian

    ], Franck [7] and Mau [12]. For more than two populations, Wang [21] discussed the LRT in the multinomial

  4. A REVIEW OF ASSUMPTIONS AND ANALYSIS IN EPRI EA-3409, "HOUSEHOLD APPLIANCE CHOICE: REVISION OF REEPS BEHAVIORAL MODELS"

    E-Print Network [OSTI]

    Wood, D.J.

    2010-01-01T23:59:59.000Z

    only logit estimate variable name normalized capital costcost estimates by using construction handbooks (for capitalcapital cost coefficient to operating cost coefficient gives an estimate

  5. Sensitivity analysis of the optimal solutions to Huff-type competitive ...

    E-Print Network [OSTI]

    2008-11-26T23:59:59.000Z

    facilities and the distances to them, through a gravitational or logit type model. Both the ..... This generalizes the 'law of retail gravitation' of Reilly [33], who.

  6. Factors Affecting Cotton Producers' Choice of Marketing Outlet

    E-Print Network [OSTI]

    Pace, Jason 1979-

    2012-08-16T23:59:59.000Z

    Studies 4 Adoption Studies Employing Multinomial Logistic Regression ?.. 5 Hedging Studies ?????????????????????.. 8 Marketing Studies ????????????????????... 12 Non-cotton and General Commodity Marketing Studies ????. 12 Cotton Marketing Studies... Employing Multinomial Logistic Regression This paper will model the factors that influence several qualitative choices (cash marketing outlets) among cotton producers. The objective of qualitative choice modeling is to determine each explanatory...

  7. Journal of Machine Learning Research 7 (2006) 21892213 Submitted 01/2006; Published 10/2006 Noisy-OR Component Analysis

    E-Print Network [OSTI]

    Hauskrecht, Milos

    2006-01-01T23:59:59.000Z

    ), multinomial PCA (or aspect) models (Buntine, 2002; Hofmann, 1999a; Blei et al., 2003), the multiple cause, such as to identify the document topics in the aspect model (Hofmann, 1999a; Blei et al., 2003) or regulatory signals- dimensional continuous-valued data. More recently, multinomial mixture models (Hofmann, 1999a; Blei et al

  8. The Effect of Branding and Firm Size on the Recurrence of Food Recall Events Associated with Pathogenic Contamination in the United States

    E-Print Network [OSTI]

    Kapilakanchana, Montalee

    2012-07-16T23:59:59.000Z

    an econometric model with discrete choice modeling approaches: logit and probit. There are two main hypotheses. Firstly, it is hypothesized that branding decreases the likelihood of the occurrence of the repeated recall event. Secondly, size of the firm...

  9. Landowner perception, awareness, and adoption of wildfire programs in the Southern United States

    E-Print Network [OSTI]

    Jarrett, Adam R.

    2009-05-15T23:59:59.000Z

    . Specifically, it was hypothesized that landowner program awareness, interest in biomass utilization, and wildfire mitigation strategies would be influenced by the type of information they received, management activities, and other factors. Seven logit models...

  10. Patterns of Identification: The Children of Latino/Non-Latino White Families

    E-Print Network [OSTI]

    Fox, Amber

    2012-02-14T23:59:59.000Z

    and ethnically identify their children. Specifically, I use both multinomial logistic regression and multilevel binomial logistic regression to predict the outcome of the child either being identified as Latino (white or other) or non-Latino (white or other...

  11. Von Mises-Fisher Clustering Models Siddharth Gopal SGOPAL1@CS.CMU.EDU

    E-Print Network [OSTI]

    Shamos, Michael I.

    Dirichlet allocation (Blei et al., 2003) have emerged as the defacto standard for discovering the latent., 2004) or Multinomial (Blei et al., 2003; 2004; Blei & Lafferty, 2006a;b) are not appropriate. On one

  12. Categorical missing data imputation for software cost estimation by

    E-Print Network [OSTI]

    Bae, Doo-Hwan

    the cost usually begins by building estimation model Apply estimation method to historical data setsCategorical missing data imputation for software cost estimation by multinomial logistic regression Organization type Banking, Construction, Gas, Defense, Engergy, ... bartype Business area type Accounting

  13. Poisson loglinear modeling with linear constraints on the expected cell frequencies

    E-Print Network [OSTI]

    Martin, Nirian

    2010-01-01T23:59:59.000Z

    In this paper we consider Poisson loglinear models with linear constraints (LMLC) on the expected table counts. Multinomial and product multinomial loglinear models can be obtained by considering that some marginal totals (linear constraints on the expected table counts) have been prefixed in a Poisson loglinear model. Therefore with the theory developed in this paper, multinomial and product multinomial loglinear models can be considered as a particular case. To carry out inferences on the parameters in the LMLC an information-theoretic approach is followed from which the classical maximum likelihood estimators and Pearson chi-square statistics for goodness-of fit are obtained. In addition, nested hypotheses are proposed as a general procedure for hypothesis testing. Through a simulation study the appropriateness of proposed inference tools is illustrated.

  14. An alternative proof of a PTAS for fixed-degree polynomial ...

    E-Print Network [OSTI]

    2014-09-25T23:59:59.000Z

    multinomial distribution in terms of the Stirling numbers of the second kind. 1.5 Notation. Throughout we use the notation [n] = {1, 2,...,n} and Nn is the set of all...

  15. Mixing finishing swine: physiological effects and measurement of aggression

    E-Print Network [OSTI]

    Glover, Jamie Dea

    1984-01-01T23:59:59.000Z

    rerun if differences in counts between duplicates exceeded 10X. The concentration of cortisol was determined by using a logit-log transformation. Sensitivity of the assay was 2 ng/ml of plasma. Cross reactivity was . 1X for all steriods except 21...

  16. Optimized Cascade of Classifiers for People Detection Using Covariance Malik SOUDED1,2

    E-Print Network [OSTI]

    Paris-Sud XI, Université de

    for many applications like people track- ing especially in crowded scenes has motivated many researchesOptimized Cascade of Classifiers for People Detection Using Covariance Features Malik SOUDED1.Souded@digitalbarriers.com Keywords: People detection, Covariance descriptor, LogitBoost. Abstract: People detection on static images

  17. ANNUAL REPORT RESEARCH PROGRAM

    E-Print Network [OSTI]

    Rock, Chris

    Winter Safflower as a New Biomass Energy Crop for the Lower Great Plains ofNorth America...................................16 Cotton Price Risk Management across Different Countries......................... 17 Brand-Supermarket Price Competition with Nested Logit Demand.................18 Supermarket Price Competition: The Case of

  18. A FOREWARNING INDICATOR SYSTEM FOR FINANCIAL CRISES : THE CASE OF SIX CENTRAL AND EASTERN EUROPEAN

    E-Print Network [OSTI]

    Boyer, Edmond

    system for each one. JEL classification : F31; F47. Keywords : Currency Crisis, Early Warning System analysis, logit/probit regressions, Early Warning Systems, and Markovian models (see, among many others in that each country is also analyzed separately, permitting the creation of a more "custom-made" early warning

  19. A Blockwise Descent Algorithm for Group-penalized Multiresponse and

    E-Print Network [OSTI]

    Hastie, Trevor

    ). This approach gives a solution with few non-zero groups. Now, instead of usual linear regression, one might. 1 Introduction Consider the usual linear regressions framework with y an n-vector of re- sponses as the "multiresponse lasso". Multinomial regression (via a generalized linear model) is also initimately related

  20. Example learned topics and document model Train on 160K documents, subset of TREC AP corpus; use variational EM,

    E-Print Network [OSTI]

    Hinton, Geoffrey E.

    of individuals #12;Discovering role similarity reflects jobs: Blair ('gas pipeline logistics') Watson ('pipeline email words wrt topic distributions #12;Inference in Author-Recipient-Topic model models message content-specific multinomial z Aim: calculate posterior distribution of topic and recipient assignments given words P(z, r

  1. Journal of Transportation Engineering Modelling Automobile Driver's Toll-Lane Choice Behaviour at a Toll Plaza

    E-Print Network [OSTI]

    Kundu, Debasis

    Journal of Transportation Engineering Modelling Automobile Driver's Toll-Lane Choice Behaviour at a Toll Plaza --Manuscript Draft-- Manuscript Number: TEENG-1181R3 Full Title: Modelling Automobile Driver to develop a random utility based discrete multinomial choice model for the behaviour of automobile drivers

  2. Essays on A Rational Expectations Model of Dividend Policy and Stock Returns

    E-Print Network [OSTI]

    Nam, Changwoo

    2011-10-21T23:59:59.000Z

    : : : : : : : : : : : : : : : 77 III Size and Value Factors and the Size-BE=ME Portfolios : : : : : : : 78 IV Logit Regressions of Propensities of Payouts: Dividend Payment and Stock Repurchase, 1962 to 2009 : : : : : : : : : : : : : : : : : : 79 V Statistics for Measures... : : : : : : : : : : : : : 94 11 Time-Varying VMG and Value Spread in Quarterly Frequency : : : : 95 12 Expected Returns on 10 Portfolios Formed on BE=ME and Mar- ket Size : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 96 13 Solow Residual and Dividend...

  3. {beta}-delayed neutron decay of {sup 14}Be

    SciTech Connect (OSTI)

    Belbot, M.D.; Kolata, J.J.; Lamkin, K.; Tighe, R.J.; Zahar, M. [Physics Department, University of Notre Dame, Notre Dame, Indiana 46556 (United States)] [Physics Department, University of Notre Dame, Notre Dame, Indiana 46556 (United States); Harkewicz, R.; Morrissey, D.J.; Orr, N.A.; Ronningen, R.M.; Sherrill, B.M.; Winger, J.A. [Cyclotron Laboratory, Michigan State University, East Lansing, Michigan 48824 (United States)] [Cyclotron Laboratory, Michigan State University, East Lansing, Michigan 48824 (United States); Carpenter, M. [Physics Division, Argonne National Laboratory, Argonne, Illinois 60439 (United States)] [Physics Division, Argonne National Laboratory, Argonne, Illinois 60439 (United States)

    1995-05-01T23:59:59.000Z

    The neutron spectroscopy of the {beta}-delayed neutron decay of {sup 14}Be has been investigated. Two neutron groups were observed, and energy limits are given for a third (unobserved) group that receives most of the {beta}-decay strength. Branching ratios and log{ital ft} values deduced for all three groups are compared with the results of a shell-model calculation.

  4. Crop acreage estimators based on satellite imagery

    E-Print Network [OSTI]

    Vidart, Stephane

    1983-01-01T23:59:59.000Z

    acreages have been pooled during the creation of the two data sets. Each data set refers to a particular part of the state of Texas. The two regions are shown in Figure 1. The partitioning is made according to crop reporting districts (CRD), which... studies are reported: (1) a comparison of sample behavior with theoretical asymptotic behavior, (2) an evaluation using CAMS data and fixed size sampling units of the improvement of the estimators under the new decision process over the old multinomial...

  5. CATDAT : A Program for Parametric and Nonparametric Categorical Data Analysis : User's Manual Version 1.0, 1998-1999 Progress Report.

    SciTech Connect (OSTI)

    Peterson, James T.

    1999-12-01T23:59:59.000Z

    Natural resource professionals are increasingly required to develop rigorous statistical models that relate environmental data to categorical responses data. Recent advances in the statistical and computing sciences have led to the development of sophisticated methods for parametric and nonparametric analysis of data with categorical responses. The statistical software package CATDAT was designed to make some of these relatively new and powerful techniques available to scientists. The CATDAT statistical package includes 4 analytical techniques: generalized logit modeling; binary classification tree; extended K-nearest neighbor classification; and modular neural network.

  6. Finding a Minimally Informative Dirichlet Prior Distribution Using Least Squares

    SciTech Connect (OSTI)

    Dana Kelly; Corwin Atwood

    2011-03-01T23:59:59.000Z

    In a Bayesian framework, the Dirichlet distribution is the conjugate distribution to the multinomial likelihood function, and so the analyst is required to develop a Dirichlet prior that incorporates available information. However, as it is a multiparameter distribution, choosing the Dirichlet parameters is less straight-forward than choosing a prior distribution for a single parameter, such as p in the binomial distribution. In particular, one may wish to incorporate limited information into the prior, resulting in a minimally informative prior distribution that is responsive to updates with sparse data. In the case of binomial p or Poisson, the principle of maximum entropy can be employed to obtain a so-called constrained noninformative prior. However, even in the case of p, such a distribution cannot be written down in closed form, and so an approximate beta distribution is used in the case of p. In the case of the multinomial model with parametric constraints, the approach of maximum entropy does not appear tractable. This paper presents an alternative approach, based on constrained minimization of a least-squares objective function, which leads to a minimally informative Dirichlet prior distribution. The alpha-factor model for common-cause failure, which is widely used in the United States, is the motivation for this approach, and is used to illustrate the method. In this approach to modeling common-cause failure, the alpha-factors, which are the parameters in the underlying multinomial aleatory model for common-cause failure, must be estimated from data that is often quite sparse, because common-cause failures tend to be rare, especially failures of more than two or three components, and so a prior distribution that is responsive to updates with sparse data is needed.

  7. Finding A Minimally Informative Dirichlet Prior Using Least Squares

    SciTech Connect (OSTI)

    Dana Kelly

    2011-03-01T23:59:59.000Z

    In a Bayesian framework, the Dirichlet distribution is the conjugate distribution to the multinomial likelihood function, and so the analyst is required to develop a Dirichlet prior that incorporates available information. However, as it is a multiparameter distribution, choosing the Dirichlet parameters is less straightforward than choosing a prior distribution for a single parameter, such as p in the binomial distribution. In particular, one may wish to incorporate limited information into the prior, resulting in a minimally informative prior distribution that is responsive to updates with sparse data. In the case of binomial p or Poisson \\lambda, the principle of maximum entropy can be employed to obtain a so-called constrained noninformative prior. However, even in the case of p, such a distribution cannot be written down in the form of a standard distribution (e.g., beta, gamma), and so a beta distribution is used as an approximation in the case of p. In the case of the multinomial model with parametric constraints, the approach of maximum entropy does not appear tractable. This paper presents an alternative approach, based on constrained minimization of a least-squares objective function, which leads to a minimally informative Dirichlet prior distribution. The alpha-factor model for common-cause failure, which is widely used in the United States, is the motivation for this approach, and is used to illustrate the method. In this approach to modeling common-cause failure, the alpha-factors, which are the parameters in the underlying multinomial model for common-cause failure, must be estimated from data that are often quite sparse, because common-cause failures tend to be rare, especially failures of more than two or three components, and so a prior distribution that is responsive to updates with sparse data is needed.

  8. User's manual for geophysical well-logging software programs

    SciTech Connect (OSTI)

    Petrie, G.M.; Gibson, D.; Blair, S.C.

    1983-02-01T23:59:59.000Z

    Since 1958 the Ground-Water Surveillance Program for the Hanford Site has made geophysical logging measurements in most of the 800 wells and deep boreholes that have been drilled on the Hanford Site. In 1980 the Pacific Northwest Laboratory (PNL), which conducts the Ground-Water Surveillance Program, began forming a computerized data base for storing and retrieving geophysical well log data and developing software for quantitative analysis of the well log data. This report, designed to serve as a user's guide, documents the data base system that handles the well log data. Two programs, DIGLOG1 and LOGIT, are used to manipulate the data. The program DIGLOG1 translates analog paper strip charts into digital format; the program LOGIT is a general utility program that edits, displays, checks, stores, writes, and deletes sets of well log data. These two programs do not provide sophisticated display and analytical capabilities; rather, they provide programs that give the user easy access to powerful standard analytical software.

  9. MODELING THE DEMAND FOR E85 IN THE UNITED STATES

    SciTech Connect (OSTI)

    Liu, Changzheng [ORNL; Greene, David L [ORNL

    2013-10-01T23:59:59.000Z

    How demand for E85 might evolve in the future in response to changing economics and policies is an important subject to include in the National Energy Modeling System (NEMS). This report summarizes a study to develop an E85 choice model for NEMS. Using the most recent data from the states of Minnesota, North Dakota, and Iowa, this study estimates a logit model that represents E85 choice as a function of prices of E10 and E85, as well as fuel availability of E85 relative to gasoline. Using more recent data than previous studies allows a better estimation of non-fleet demand and indicates that the price elasticity of E85 choice appears to be higher than previously estimated. Based on the results of the econometric analysis, a model for projecting E85 demand at the regional level is specified. In testing, the model produced plausible predictions of US E85 demand to 2040.

  10. Assessment Of Carbon Leakage In Multiple Carbon-Sink Projects: ACase Study In Jambi Province, Indonesia

    SciTech Connect (OSTI)

    Boer, Rizaldi; Wasrin, Upik R.; Hendri, Perdinan; Dasanto,Bambang D.; Makundi, Willy; Hero, Julius; Ridwan, M.; Masripatin, Nur

    2007-06-01T23:59:59.000Z

    Rehabilitation of degraded forest land throughimplementation of carbon sink projects can increase terrestrial carbonstock. However, carbon emissions outside the project boundary, which iscommonly referred to as leakage, may reduce or negate the sequestrationbenefits. This study assessed leakage from carbon sink projects thatcould potentially be implemented in the study area comprised of elevensub-districts in the Batanghari District, Jambi Province, Sumatra,Indonesia. The study estimates the probability of a given land use/coverbeing converted into other uses/cover, by applying a logit model. Thepredictor variables were: proximity to the center of the land use area,distance to transportation channel (road or river), area of agriculturalland, unemployment (number of job seekers), job opportunities, populationdensity and income. Leakage was estimated by analyzing with and withoutcarbon sink projects scenarios. Most of the predictors were estimated asbeing significant in their contribution to land use cover change. Theresults of the analysis show that leakage in the study area can be largeenough to more than offset the project's carbon sequestration benefitsduring the period 2002-2012. However, leakage results are very sensitiveto changes of carbon density of the land uses in the study area. Byreducing C-density of lowland and hill forest by about 10 percent for thebaseline scenario, the leakage becomes positive. Further data collectionand refinement is therefore required. Nevertheless, this study hasdemonstrated that regional analysis is a useful approach to assessleakage.

  11. Electric and hybrid electric vehicles: A technology assessment based on a two-stage Delphi study

    SciTech Connect (OSTI)

    Vyas, A.D.; Ng, H.K.; Santini, D.J.; Anderson, J.L.

    1997-12-01T23:59:59.000Z

    To address the uncertainty regarding future costs and operating attributes of electric and hybrid electric vehicles, a two stage, worldwide Delphi study was conducted. Expert opinions on vehicle attributes, current state of the technology, possible advancements, costs, and market penetration potential were sought for the years 2000, 2010, and 2020. Opinions related to such critical components as batteries, electric drive systems, and hybrid vehicle engines, as well as their respective technical and economic viabilities, were also obtained. This report contains descriptions of the survey methodology, analytical approach, and results of the analysis of survey data, together with a summary of other factors that will influence the degree of market success of electric and hybrid electric vehicle technologies. Responses by industry participants, the largest fraction among all the participating groups, are compared with the overall responses. An evaluation of changes between the two Delphi stages is also summarized. An analysis of battery replacement costs for various types is summarized, and variable operating costs for electric and hybrid vehicles are compared with those of conventional vehicles. A market penetration analysis is summarized, in which projected market shares from the survey are compared with predictions of shares on the basis of two market share projection models that use the cost and physical attributes provided by the survey. Finally, projections of market shares beyond the year 2020 are developed by use of constrained logit models of market shares, statistically fitted to the survey data.

  12. Maximum entropy principal for transportation

    SciTech Connect (OSTI)

    Bilich, F. [University of Brasilia (Brazil); Da Silva, R. [National Research Council (Brazil)

    2008-11-06T23:59:59.000Z

    In this work we deal with modeling of the transportation phenomenon for use in the transportation planning process and policy-impact studies. The model developed is based on the dependence concept, i.e., the notion that the probability of a trip starting at origin i is dependent on the probability of a trip ending at destination j given that the factors (such as travel time, cost, etc.) which affect travel between origin i and destination j assume some specific values. The derivation of the solution of the model employs the maximum entropy principle combining a priori multinomial distribution with a trip utility concept. This model is utilized to forecast trip distributions under a variety of policy changes and scenarios. The dependence coefficients are obtained from a regression equation where the functional form is derived based on conditional probability and perception of factors from experimental psychology. The dependence coefficients encode all the information that was previously encoded in the form of constraints. In addition, the dependence coefficients encode information that cannot be expressed in the form of constraints for practical reasons, namely, computational tractability. The equivalence between the standard formulation (i.e., objective function with constraints) and the dependence formulation (i.e., without constraints) is demonstrated. The parameters of the dependence-based trip-distribution model are estimated, and the model is also validated using commercial air travel data in the U.S. In addition, policy impact analyses (such as allowance of supersonic flights inside the U.S. and user surcharge at noise-impacted airports) on air travel are performed.

  13. Normal Tissue Complication Probability Modeling of Radiation-Induced Hypothyroidism After Head-and-Neck Radiation Therapy

    SciTech Connect (OSTI)

    Bakhshandeh, Mohsen [Department of Medical Physics, Faculty of Medical Sciences, Tarbiat Modares University, Tehran (Iran, Islamic Republic of)] [Department of Medical Physics, Faculty of Medical Sciences, Tarbiat Modares University, Tehran (Iran, Islamic Republic of); Hashemi, Bijan, E-mail: bhashemi@modares.ac.ir [Department of Medical Physics, Faculty of Medical Sciences, Tarbiat Modares University, Tehran (Iran, Islamic Republic of)] [Department of Medical Physics, Faculty of Medical Sciences, Tarbiat Modares University, Tehran (Iran, Islamic Republic of); Mahdavi, Seied Rabi Mehdi [Department of Medical Physics, Faculty of Medical Sciences, Tehran University of Medical Sciences, Tehran (Iran, Islamic Republic of)] [Department of Medical Physics, Faculty of Medical Sciences, Tehran University of Medical Sciences, Tehran (Iran, Islamic Republic of); Nikoofar, Alireza; Vasheghani, Maryam [Department of Radiation Oncology, Hafte-Tir Hospital, Tehran University of Medical Sciences, Tehran (Iran, Islamic Republic of)] [Department of Radiation Oncology, Hafte-Tir Hospital, Tehran University of Medical Sciences, Tehran (Iran, Islamic Republic of); Kazemnejad, Anoshirvan [Department of Biostatistics, Faculty of Medical Sciences, Tarbiat Modares University, Tehran (Iran, Islamic Republic of)] [Department of Biostatistics, Faculty of Medical Sciences, Tarbiat Modares University, Tehran (Iran, Islamic Republic of)

    2013-02-01T23:59:59.000Z

    Purpose: To determine the dose-response relationship of the thyroid for radiation-induced hypothyroidism in head-and-neck radiation therapy, according to 6 normal tissue complication probability models, and to find the best-fit parameters of the models. Methods and Materials: Sixty-five patients treated with primary or postoperative radiation therapy for various cancers in the head-and-neck region were prospectively evaluated. Patient serum samples (tri-iodothyronine, thyroxine, thyroid-stimulating hormone [TSH], free tri-iodothyronine, and free thyroxine) were measured before and at regular time intervals until 1 year after the completion of radiation therapy. Dose-volume histograms (DVHs) of the patients' thyroid gland were derived from their computed tomography (CT)-based treatment planning data. Hypothyroidism was defined as increased TSH (subclinical hypothyroidism) or increased TSH in combination with decreased free thyroxine and thyroxine (clinical hypothyroidism). Thyroid DVHs were converted to 2 Gy/fraction equivalent doses using the linear-quadratic formula with {alpha}/{beta} = 3 Gy. The evaluated models included the following: Lyman with the DVH reduced to the equivalent uniform dose (EUD), known as LEUD; Logit-EUD; mean dose; relative seriality; individual critical volume; and population critical volume models. The parameters of the models were obtained by fitting the patients' data using a maximum likelihood analysis method. The goodness of fit of the models was determined by the 2-sample Kolmogorov-Smirnov test. Ranking of the models was made according to Akaike's information criterion. Results: Twenty-nine patients (44.6%) experienced hypothyroidism. None of the models was rejected according to the evaluation of the goodness of fit. The mean dose model was ranked as the best model on the basis of its Akaike's information criterion value. The D{sub 50} estimated from the models was approximately 44 Gy. Conclusions: The implemented normal tissue complication probability models showed a parallel architecture for the thyroid. The mean dose model can be used as the best model to describe the dose-response relationship for hypothyroidism complication.