DOCSLIB.ORG

Probit Model 1 Probit Model

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Probit Model 1 Probit Model Probit model 1 Probit model In statistics, a probit model is a type of regression where the dependent variable can only take two values, for example married or not married. The name is from probability + unit.[1] A probit model is a popular specification for an ordinal[2] or a binary response model that employs a probit link function. This model is most often estimated using standard maximum likelihood procedure, such an estimation being called a probit regression. Probit models were introduced by Chester Bliss in 1934, and a fast method for computing maximum likelihood estimates for them was proposed by Ronald Fisher in an appendix to Bliss 1935. Introduction Suppose response variable Y is binary, that is it can have only two possible outcomes which we will denote as 1 and 0. For example Y may represent presence/absence of a certain condition, success/failure of some device, answer yes/no on a survey, etc. We also have a vector of regressors X, which are assumed to influence the outcome Y. Specifically, we assume that the model takes form where Pr denotes probability, and Φ is the Cumulative Distribution Function (CDF) of the standard normal distribution. The parameters β are typically estimated by maximum likelihood. It is also possible to motivate the probit model as a latent variable model. Suppose there exists an auxiliary random variable where ε ~ N(0, 1). Then Y can be viewed as an indicator for whether this latent variable is positive: The use of the standard normal distribution causes no loss of generality compared with using an arbitrary mean and standard deviation because adding a fixed amount to the mean can be compensated by subtracting the same amount from the intercept, and multiplying the standard deviation by a fixed amount can be compensated by multiplying the weights by the same amount. To see that the two models are equivalent, note that Probit model 2 Maximum likelihood estimation Suppose data set contains n independent statistical units corresponding to the model above. Then their joint log-likelihood function is The estimator which maximizes this function will be consistent, asymptotically normal and efficient provided that E[XX'] exists and is not singular. It can be shown that this log-likelihood function is globally concave in β, and therefore standard numerical algorithms for optimization will converge rapidly to the unique maximum. Asymptotic distribution for is given by where and φ = Φ' is the Probability Density Function (PDF) of standard normal distribution. Berkson's minimum chi-square method This method can be applied only when there are many observations of response variable having the same value of the vector of regressors (such situation may be referred to as "many observations per cell"). More specifically, the model can be formulated as follows. Suppose among n observations there are only T distinct values of the regressors, which can be denoted as . Let be the number of observations with and the number of such observations with . We assume that there are indeed "many" observations per each "cell": for each . Denote Then Berkson's minimum chi-square estimator is a generalized least squares estimator in a regression of on with weights : It can be shown that this estimator is consistent (as n→∞ and T fixed), asymptotically normal and efficient. Its advantage is the presence of a closed-form formula for the estimator. However, it is only meaningful to carry out this analysis when individual observations are not available, only their aggregated counts , , and (for example in the analysis of voting behavior). Probit model 3 Gibbs sampling Gibbs sampling of a probit model is possible because regression models typically use normal prior distributions over the weights, and this distribution is conjugate with the normal distribution of the errors (and hence of the latent variablesY*). The model can be described as From this, we can determine the full conditional densities needed: The result for β is given in the article on Bayesian linear regression, although specified with different notation. The only trickiness is in the last two equations. The notation is the Iverson bracket, sometimes written or similar. It indicates that the distribution must be truncated within the given range, and rescaled appropriately. In this particular case, a truncated normal distribution arises. Sampling from this distribution depends on how much is truncated. If a large fraction of the original mass remains, sampling can be easily done with rejection sampling — simply sample a number from the non-truncated distribution, and reject it if it falls outside the restriction imposed by the truncation. If sampling from only a small fraction of the original mass, however (e.g. if sampling from one of the tails of the normal distribution — for example if is around 3 or more, and a negative sample is desired), then this will be inefficient and it becomes necessary to fall back on other sampling algorithms. General sampling from the truncated normal can be achieved using approximations to the normal CDF and the probit function, and R has a function rtnorm() for generating truncated-normal samples. References • Bliss, C.I. (1935). "The calculation of the dosage-mortality curve". Annals of Applied Biology (22)134–167. doi:10.1111/j.1744-7348.1935.tb07713.x • Bliss, C.I (1938). "The determination of the dosage-mortality curve from small numbers". Quarterly Journal of Pharmacology (11)192–216. • McCullagh, Peter; John Nelder (1989). Generalized Linear Models. London: Chapman and Hall. ISBN 0-412-31760-5. • Albert, J.H., and Chib, S. (1993). "Bayesian Analysis of Binary and Polychotomous Response Data." Journal of the American Statistical Association (88)422: pp. 669-679. http:/ / www. jstor. org/ stable/ 2290350 Notes [1] Oxford English Dictionary, 3rd ed. s.v. probit (article dated June 2007): C. I. Bliss in Science 12 Jan. 1934, 38/1, "These arbitrary probability units have been called ‘probits’." [2] Ordinal probit regression model UCLA Academic Technology Services http:/ / www. ats. ucla. edu/ stat/ stata/ dae/ ologit. htm Article Sources and Contributors 4 Article Sources and Contributors Probit model Source: http://en.wikipedia.org/w/index.php?oldid=500026914 Contributors: Andypar, Baccyak4H, Benwing, Cazort, David Haslam, Den fjättrade ankan, Dfarrar, Doncram, Flavio Guitian, Giganut, Gpeilon, KHirano, Keithh, Kenkleinman, Landroni, Languagehat, Michael Hardy, O18, Owenozier, PAC2, Qwfp, Rjwilmsi, SebastianHelm, Sprunger19, Stpasha, The Anome, Why Not A Duck, ZZeekk, Влад&слав, 18 anonymous edits License Creative Commons Attribution-Share Alike 3.0 Unported //creativecommons.org/licenses/by-sa/3.0/.
Load more

Recommended publications
  • An Instrumental Variables Probit Estimator Using Gretl
    View metadata, citation and similar papers at core.ac.uk brought to you by CORE provided by Research Papers in Economics An Instrumental Variables Probit Estimator using gretl Lee C. Adkins Professor of Economics, Oklahoma State University, Stillwater, OK 74078 [email protected] Abstract. The most widely used commercial software to estimate endogenous probit models offers two choices: a computationally simple generalized least squares estimator and a maximum likelihood estimator. Adkins [1, -. com%ares these estimators to several others in a Monte Carlo study and finds that the 1LS estimator performs reasonably well in some circumstances. In this paper the small sample properties of the various estimators are reviewed and a simple routine us- ing the gretl software is given that yields identical results to those produced by Stata 10.1. The paper includes an example estimated using data on bank holding companies. 1 Introduction 4atchew and Griliches +,5. analyze the effects of various kinds of misspecifi- cation on the probit model. Among the problems explored was that of errors- in-variables. In linear re$ression, a regressor measured with error causes least squares to be inconsistent and 4atchew and Griliches find similar results for probit. Rivers and 7#ong [14] and Smith and 8lundell +,9. suggest two-stage estimators for probit and tobit, respectively. The strategy is to model a con- tinuous endogenous regressor as a linear function of the exogenous regressors and some instruments. Predicted values from this regression are then used in the second stage probit or tobit. These two-step methods are not efficient, &ut are consistent.
    [Show full text]
  • An Empirical Analysis of Factors Affecting Honors Program Completion Rates
    An Empirical Analysis of Factors Affecting Honors Program Completion Rates HALLIE SAVAGE CLARION UNIVERSITY OF PENNSYLVANIA AND T H E NATIONAL COLLEGIATE HONOR COUNCIL ROD D. RAE H SLER CLARION UNIVERSITY OF PENNSYLVANIA JOSE ph FIEDOR INDIANA UNIVERSITY OF PENNSYLVANIA INTRODUCTION ne of the most important issues in any educational environment is iden- tifying factors that promote academic success. A plethora of research on suchO factors exists across most academic fields, involving a wide range of student demographics, and the definition of student success varies across the range of studies published. While much of the research is devoted to looking at student performance in particular courses and concentrates on examina- tion scores and grades, many authors have directed their attention to student success in the context of an entire academic program; student success in this context usually centers on program completion or graduation and student retention. The analysis in this paper follows the emphasis of McKay on the importance of conducting repeated research on student completion of honors programs at different universities for different time periods. This paper uses a probit regression analysis as well as the logit regression analysis employed by McKay in order to determine predictors of student success in the honors pro- gram at a small, public university, thus attempting to answer McKay’s call for a greater understanding of honors students and factors influencing their suc- cess. The use of two empirical models on completion data, employing differ- ent base distributions, provides more robust statistical estimates than observed in similar studies 115 SPRING /SUMMER 2014 AN EMPIRI C AL ANALYSIS OF FA C TORS AFFE C TING COMPLETION RATES PREVIOUS LITEratURE The early years of our research was concurrent with the work of McKay, who studied the 2002–2005 entering honors classes at the University of North Florida and published his work in 2009.
    [Show full text]
  • Application of Random-Effects Probit Regression Models
    Journal of Consulting and Clinical Psychology Copyright 1994 by the American Psychological Association, Inc. 1994, Vol. 62, No. 2, 285-296 0022-006X/94/S3.00 Application of Random-Effects Probit Regression Models Robert D. Gibbons and Donald Hedeker A random-effects probit model is developed for the case in which the outcome of interest is a series of correlated binary responses. These responses can be obtained as the product of a longitudinal response process where an individual is repeatedly classified on a binary outcome variable (e.g., sick or well on occasion t), or in "multilevel" or "clustered" problems in which individuals within groups (e.g., firms, classes, families, or clinics) are considered to share characteristics that produce similar responses. Both examples produce potentially correlated binary responses and modeling these per- son- or cluster-specific effects is required. The general model permits analysis at both the level of the individual and cluster and at the level at which experimental manipulations are applied (e.g., treat- ment group). The model provides maximum likelihood estimates for time-varying and time-invari- ant covariates in the longitudinal case and covariates which vary at the level of the individual and at the cluster level for multilevel problems. A similar number of individuals within clusters or number of measurement occasions within individuals is not required. Empirical Bayesian estimates of per- son-specific trends or cluster-specific effects are provided. Models are illustrated with data from
    [Show full text]
  • Logit and Ordered Logit Regression (Ver
    Getting Started in Logit and Ordered Logit Regression (ver. 3.1 beta) Oscar Torres-Reyna Data Consultant [email protected] http://dss.princeton.edu/training/ PU/DSS/OTR Logit model • Use logit models whenever your dependent variable is binary (also called dummy) which takes values 0 or 1. • Logit regression is a nonlinear regression model that forces the output (predicted values) to be either 0 or 1. • Logit models estimate the probability of your dependent variable to be 1 (Y=1). This is the probability that some event happens. PU/DSS/OTR Logit odelm From Stock & Watson, key concept 9.3. The logit model is: Pr(YXXXFXX 1 | 1= , 2 ,...=k β ) +0 β ( 1 +2 β 1 +βKKX 2 + ... ) 1 Pr(YXXX 1= | 1 , 2k = ,... ) 1−+(eβ0 + βXX 1 1 + β 2 2 + ...βKKX + ) 1 Pr(YXXX 1= | 1 , 2= ,... ) k ⎛ 1 ⎞ 1+ ⎜ ⎟ (⎝ eβ+0 βXX 1 1 + β 2 2 + ...βKK +X ⎠ ) Logit nd probita models are basically the same, the difference is in the distribution: • Logit – Cumulative standard logistic distribution (F) • Probit – Cumulative standard normal distribution (Φ) Both models provide similar results. PU/DSS/OTR It tests whether the combined effect, of all the variables in the model, is different from zero. If, for example, < 0.05 then the model have some relevant explanatory power, which does not mean it is well specified or at all correct. Logit: predicted probabilities After running the model: logit y_bin x1 x2 x3 x4 x5 x6 x7 Type predict y_bin_hat /*These are the predicted probabilities of Y=1 */ Here are the estimations for the first five cases, type: 1 x2 x3 x4 x5 x6 x7 y_bin_hatbrowse y_bin x Predicted probabilities To estimate the probability of Y=1 for the first row, replace the values of X into the logit regression equation.
    [Show full text]
  • Diagnostic Plots — Distributional Diagnostic Plots
    Title stata.com diagnostic plots — Distributional diagnostic plots Syntax Menu Description Options for symplot, quantile, and qqplot Options for qnorm and pnorm Options for qchi and pchi Remarks and examples Methods and formulas Acknowledgments References Also see Syntax Symmetry plot symplot varname if in , options1 Ordered values of varname against quantiles of uniform distribution quantile varname if in , options1 Quantiles of varname1 against quantiles of varname2 qqplot varname1 varname2 if in , options1 Quantiles of varname against quantiles of normal distribution qnorm varname if in , options2 Standardized normal probability plot pnorm varname if in , options2 Quantiles of varname against quantiles of χ2 distribution qchi varname if in , options3 χ2 probability plot pchi varname if in , options3 1 2 diagnostic plots — Distributional diagnostic plots options1 Description Plot marker options change look of markers (color, size, etc.) marker label options add marker labels; change look or position Reference line rlopts(cline options) affect rendition of the reference line Add plots addplot(plot) add other plots to the generated graph Y axis, X axis, Titles, Legend, Overall twoway options any options other than by() documented in[ G-3] twoway options options2 Description Main grid add grid lines Plot marker options change look of markers (color, size, etc.) marker label options add marker labels; change look or position Reference line rlopts(cline options) affect rendition of the reference line
    [Show full text]
  • A User's Guide to Multiple Probit Or Logit Analysis. Gen
    United States Department of Agriculture Forest Service Pacific Southwest Forest and Range Experiment Station General Technical Report PSW- 55 a user's guide to multiple Probit Or LOgit analysis Robert M. Russell, N. E. Savin, Jacqueline L. Robertson Authors: ROBERT M. RUSSELL has been a computer programmer at the Station since 1965. He was graduated from Graceland College in 1953, and holds a B.S. degree (1956) in mathematics from the University of Michigan. N. E. SAVIN earned a B.A. degree (1956) in economics and M.A. (1960) and Ph.D. (1969) degrees in economic statistics at the University of California, Berkeley. Since 1976, he has been a fellow and lecturer with the Faculty of Economics and Politics at Trinity College, Cambridge University, England. JACQUELINE L. ROBERTSON is a research entomologist assigned to the Station's insecticide evaluation research unit, at Berkeley, California. She earned a B.A. degree (1969) in zoology, and a Ph.D. degree (1973) in entomology at the University of California, Berkeley. She has been a member of the Station's research staff since 1966. Acknowledgments: We thank Benjamin Spada and Dr. Michael I. Haverty, Pacific Southwest Forest and Range Experiment Station, U.S. Department of Agriculture, Berkeley, California, for their support of the development of POL02. Publisher: Pacific Southwest Forest and Range Experiment Station P.O. Box 245, Berkeley, California 94701 September 1981 POLO2: a user's guide to multiple Probit Or LOgit analysis Robert M. Russell, N. E. Savin, Jacqueline L. Robertson CONTENTS
    [Show full text]
  • Lecture 9: Logit/Probit Prof
    Lecture 9: Logit/Probit Prof. Sharyn O’Halloran Sustainable Development U9611 Econometrics II Review of Linear Estimation So far, we know how to handle linear estimation models of the type: Y = β0 + β1*X1 + β2*X2 + … + ε ≡ Xβ+ ε Sometimes we had to transform or add variables to get the equation to be linear: Taking logs of Y and/or the X’s Adding squared terms Adding interactions Then we can run our estimation, do model checking, visualize results, etc. Nonlinear Estimation In all these models Y, the dependent variable, was continuous. Independent variables could be dichotomous (dummy variables), but not the dependent var. This week we’ll start our exploration of non- linear estimation with dichotomous Y vars. These arise in many social science problems Legislator Votes: Aye/Nay Regime Type: Autocratic/Democratic Involved in an Armed Conflict: Yes/No Link Functions Before plunging in, let’s introduce the concept of a link function This is a function linking the actual Y to the estimated Y in an econometric model We have one example of this already: logs Start with Y = Xβ+ ε Then change to log(Y) ≡ Y′ = Xβ+ ε Run this like a regular OLS equation Then you have to “back out” the results Link Functions Before plunging in, let’s introduce the concept of a link function This is a function linking the actual Y to the estimated Y in an econometric model We have one example of this already: logs Start with Y = Xβ+ ε Different β’s here Then change to log(Y) ≡ Y′ = Xβ + ε Run this like a regular OLS equation Then you have to “back out” the results Link Functions If the coefficient on some particular X is β, then a 1 unit ∆X Æ β⋅∆(Y′) = β⋅∆[log(Y))] = eβ ⋅∆(Y) Since for small values of β, eβ ≈ 1+β , this is almost the same as saying a β% increase in Y (This is why you should use natural log transformations rather than base-10 logs) In general, a link function is some F(⋅) s.t.
    [Show full text]
  • Generalized Linear Models
    CHAPTER 6 Generalized linear models 6.1 Introduction Generalized linear modeling is a framework for statistical analysis that includes linear and logistic regression as special cases. Linear regression directly predicts continuous data y from a linear predictor Xβ = β0 + X1β1 + + Xkβk.Logistic regression predicts Pr(y =1)forbinarydatafromalinearpredictorwithaninverse-··· logit transformation. A generalized linear model involves: 1. A data vector y =(y1,...,yn) 2. Predictors X and coefficients β,formingalinearpredictorXβ 1 3. A link function g,yieldingavectoroftransformeddataˆy = g− (Xβ)thatare used to model the data 4. A data distribution, p(y yˆ) | 5. Possibly other parameters, such as variances, overdispersions, and cutpoints, involved in the predictors, link function, and data distribution. The options in a generalized linear model are the transformation g and the data distribution p. In linear regression,thetransformationistheidentity(thatis,g(u) u)and • the data distribution is normal, with standard deviation σ estimated from≡ data. 1 1 In logistic regression,thetransformationistheinverse-logit,g− (u)=logit− (u) • (see Figure 5.2a on page 80) and the data distribution is defined by the proba- bility for binary data: Pr(y =1)=y ˆ. This chapter discusses several other classes of generalized linear model, which we list here for convenience: The Poisson model (Section 6.2) is used for count data; that is, where each • data point yi can equal 0, 1, 2, ....Theusualtransformationg used here is the logarithmic, so that g(u)=exp(u)transformsacontinuouslinearpredictorXiβ to a positivey ˆi.ThedatadistributionisPoisson. It is usually a good idea to add a parameter to this model to capture overdis- persion,thatis,variationinthedatabeyondwhatwouldbepredictedfromthe Poisson distribution alone.
    [Show full text]
  • Bayesian Inference: Probit and Linear Probability Models
    Utah State University DigitalCommons@USU All Graduate Plan B and other Reports Graduate Studies 5-2014 Bayesian Inference: Probit and Linear Probability Models Nate Rex Reasch Utah State University Follow this and additional works at: https://digitalcommons.usu.edu/gradreports Part of the Finance and Financial Management Commons Recommended Citation Reasch, Nate Rex, "Bayesian Inference: Probit and Linear Probability Models" (2014). All Graduate Plan B and other Reports. 391. https://digitalcommons.usu.edu/gradreports/391 This Report is brought to you for free and open access by the Graduate Studies at DigitalCommons@USU. It has been accepted for inclusion in All Graduate Plan B and other Reports by an authorized administrator of DigitalCommons@USU. For more information, please contact [email protected]. Utah State University DigitalCommons@USU All Graduate Plan B and other Reports Graduate Studies, School of 5-1-2014 Bayesian Inference: Probit and Linear Probability Models Nate Rex Reasch Utah State University Recommended Citation Reasch, Nate Rex, "Bayesian Inference: Probit and Linear Probability Models" (2014). All Graduate Plan B and other Reports. Paper 391. http://digitalcommons.usu.edu/gradreports/391 This Report is brought to you for free and open access by the Graduate Studies, School of at DigitalCommons@USU. It has been accepted for inclusion in All Graduate Plan B and other Reports by an authorized administrator of DigitalCommons@USU. For more information, please contact [email protected]. BAYESIAN INFERENCE: PROBIT AND LINEAR PROBABILITY MODELS by Nate Rex Reasch A report submitted in partial fulfillment of the requirements for the degree of MASTER OF SCIENCE in Financial Economics Approved: Tyler Brough Jason Smith Major Professor Committee Member Alan Stephens Committee Member UTAH STATE UNIVERSITY Logan, Utah 2014 ABSTRACT Bayesian Model Comparison Probit Vs.
    [Show full text]
  • Week 12: Linear Probability Models, Logistic and Probit
    Week 12: Linear Probability Models, Logistic and Probit Marcelo Coca Perraillon University of Colorado Anschutz Medical Campus Health Services Research Methods I HSMP 7607 2019 These slides are part of a forthcoming book to be published by Cambridge University Press. For more information, go to perraillon.com/PLH. c This material is copyrighted. Please see the entire copyright notice on the book's website. Updated notes are here: https://clas.ucdenver.edu/marcelo-perraillon/ teaching/health-services-research-methods-i-hsmp-7607 1 Outline Modeling 1/0 outcomes The \wrong" but super useful model: Linear Probability Model Deriving logistic regression Probit regression as an alternative 2 Binary outcomes Binary outcomes are everywhere: whether a person died or not, broke a hip, has hypertension or diabetes, etc We typically want to understand what is the probability of the binary outcome given explanatory variables It's exactly the same type of models we have seen during the semester, the difference is that we have been modeling the conditional expectation given covariates: E[Y jX ] = β0 + β1X1 + ··· + βpXp Now, we want to model the probability given covariates: P(Y = 1jX ) = f (β0 + β1X1 + ··· + βpXp) Note the function f() in there 3 Linear Probability Models We could actually use our vanilla linear model to do so If Y is an indicator or dummy variable, then E[Y jX ] is the proportion of 1s given X , which we interpret as the probability of Y given X The parameters are changes/effects/differences in the probability of Y by a unit change in X or for a small change in X If an indicator variable, then change from 0 to 1 For example, if we model diedi = β0 + β1agei + i , we could interpret β1 as the change in the probability of death for an additional year of age 4 Linear Probability Models The problem is that we know that this model is not entirely correct.
    [Show full text]
  • 9. Logit and Probit Models for Dichotomous Data
    Sociology 740 John Fox Lecture Notes 9. Logit and Probit Models For Dichotomous Data Copyright © 2014 by John Fox Logit and Probit Models for Dichotomous Responses 1 1. Goals: I To show how models similar to linear models can be developed for qualitative response variables. I To introduce logit and probit models for dichotomous response variables. c 2014 by John Fox Sociology 740 ° Logit and Probit Models for Dichotomous Responses 2 2. An Example of Dichotomous Data I To understand why logit and probit models for qualitative data are required, let us begin by examining a representative problem, attempting to apply linear regression to it: In September of 1988, 15 years after the coup of 1973, the people • of Chile voted in a plebiscite to decide the future of the military government. A ‘yes’ vote would represent eight more years of military rule; a ‘no’ vote would return the country to civilian government. The no side won the plebiscite, by a clear if not overwhelming margin. Six months before the plebiscite, FLACSO/Chile conducted a national • survey of 2,700 randomly selected Chilean voters. – Of these individuals, 868 said that they were planning to vote yes, and 889 said that they were planning to vote no. – Of the remainder, 558 said that they were undecided, 187 said that they planned to abstain, and 168 did not answer the question. c 2014 by John Fox Sociology 740 ° Logit and Probit Models for Dichotomous Responses 3 – I will look only at those who expressed a preference. Figure 1 plots voting intention against a measure of support for the • status quo.
    [Show full text]
  • A Probit Regression Approach
    2016 Annual Evaluation Review, Linked Document D 1 Analyzing the Determinants of Project Success: A Probit Regression Approach 1. This regression analysis aims to ascertain the factors that determine development project outcome. It is intended to complement the trend analysis in the performance of ADB-financed operations from IED’s project evaluations and validations. Given the binary nature of the project outcome (i.e., successful/unsuccessful), a discrete choice probit model is appropriate to empirically test the relationship between project outcome and a set of project and country-level characteristics. 2. In the probit model, a project rated (Y) successful is given a value 1 while a project rated unsuccessful is given a value of 0. Successful projects are those rated successful or highly successful. 1 The probability 푝푖 of having a successful rating over an unsuccessful rating can be expressed as: 푥 ′훽 2 푝 = 푃푟표푏 (푌 = 1|푿) = 푖 (2휋)−1/2exp (−푡 ) 푑푡 = Φ(풙 ′훽) 푖 푖 ∫−∞ 2 푖 where Φ is the cumulative distribution function of a standard normal variable which ensures 0≤ 푝푖 ≤ 1, 풙 is a vector of factors that determine or explain the variation in project outcome and 훽 is a vector of parameters or coefficients that reflects the effect of changes in 풙 on the probability of success. The relationship between a specific factor and the outcome of the probability is interpreted by the means of the marginal effect which accounts for the partial change in the probability.2 The marginal effects provide insights into how the explanatory variables change the predicted probability of project success.
    [Show full text]