Search results

Multiple linear regression (MLR) is a commonly used statistical technique to predict future values. In this paper, we examine the situation in which a given time series dataset contains numerous observations of important predictor variables that can effectively be classified into groups based on their values. In such situations, cluster analysis is often employed to improve the MLR models predictive accuracy, usually by creating separate regressions for each cluster. We introduce a novel approach in which we use the clusters and cluster centroids as input data for the predictor variables to improve the predictive accuracy of the MLR model. We illustrate and test this approach with a real dataset on fleet maintenance.

In elite professional firms, minorities are actively recruited but struggle to move upward. The authors argue that initiatives aimed at general skill development can have unintended consequences for firm diversity. Specifically, the authors contend that approaches that win partner support through motivational significance and interpretive clarity provide a more effective avenue to skill development for minorities, who have less access than White peers to informal developmental opportunities. The authors also argue that a longer “partnership track,” which imposes a time limit on skill development, will benefit minority professionals. Using data on 601 offices of large US law firms in 1996 and 2005, the authors investigate the effects of five developmental initiatives and partnership track length on the representation of African-Americans, Latinxs, and Asian-Americans among partners. Observed effects are consistent with expectations, but patterns vary across racial-ethnic groups.

In a previous chapter (Klimberg, Ratick, & Smith, 2018), we introduced a novel approach in which cluster centroids were used as input data for the predictor variables of a multiple linear regression (MLR) used to forecast fleet maintenance costs. We applied this approach to a real data set and significantly improved the predictive accuracy of the MLR model. In this chapter, we develop a methodology for adjusting moving average forecasts of the future values of fleet service occurrences by interpolating those forecast values using their relative distances from cluster centroids. We illustrate and evaluate the efficacy of this approach with our previously used data set on fleet maintenance.

This paper presents a numerical study of inverse parameter identification problems in fracture mechanics. Inverse methodology is applied to the detection of subsurface cracks and to the study of propagating cracks. The procedure for detecting subsurface cracks combines the finite element method with a sequential quadratic programming algorithm to solve for the unknown geometric parameters associated with the internal flaw. The procedure utilizes finite element substructuring capabilities in order to minimize the processing and solution time for practical problems. The finite element method and non‐linear optimization are also used in determining the direction a crack will propagate in a heterogeneous planar domain. This procedure involves determining the direction that produces the maximum strain energy release for a given increment of crack growth. The procedure is applied to several numerical examples. The results of these numerical studies coincide with theoretical predictions and experimentally observed crack behavior.

The purpose of this paper is to examine the value relevance of accounting information in cases of apparent audit failures.

The authors adopt the bootstrapping technique and compare the value relevance of key accounting information across samples of firms experiencing apparent audit failures with matched non‐audit failure firms.

Accounting information is found to be less value relevant for firms experiencing apparent audit failures, regardless of auditor reputation.

This study has limitations due to the ex ante research approach adopted. Future research could address this issue by possibly incorporating an “intervening” factor into the model to indicate how the market can differentiate audit failure firms from other firms.

The paper gives support to the assertion that the market appears to rely less on accounting numbers when audit failures occur, even though formal allegations of audit failure may not appear until years after their occurrence. In addition to contributing to value‐relevance research by providing empirical evidence for the market phenomenon around the time of material misstatements, the paper demonstrates an innovative application of bootstrapping to test for differences in R².

During the past several decades, the decision-making process and the decision-makers’ role in it have changed dramatically. Because of this, the use of analytical tools, such as Excel, have become an essential component of most organizations. The analytical tools in Excel can provide today’s decision-maker with a competitive advantage. We will illustrate several powerful Excel tools that facilitate the decision support process.

The purpose of this paper is to propose a way to introduce regression analysis into courses with minimal start‐up time. Doing so makes it less likely that introducing both the software and the estimation technique will create discontinuity in the flow of the material being covered.

This paper discusses an Excel workbook that reduces the amount of time students must use to become adept at estimating model parameters.

The workbook provides a set of macros that guides students through the implementation of ordinary least squares (OLS) estimation and provides them with information that is not part of standard Excel output. It also conducts high‐low analysis.

Using this program can reduce the difficulties encountered in having students conduct the valuable exercise of model estimation.

The purpose of this paper is to estimate the multicomponent reliability by assuming the unit-Gompertz (UG) distribution. Both stress and strength are assumed to have an UG distribution with common scale parameter.

The reliability of a multicomponent stress–strength system is obtained by the maximum likelihood (MLE) and Bayesian method of estimation. Bayes estimates of system reliability are obtained by using Lindley’s approximation and Metropolis–Hastings (M–H) algorithm methods when all the parameters are unknown. The highest posterior density credible interval is obtained by using M–H algorithm method. Besides, uniformly minimum variance unbiased estimator and exact Bayes estimates of system reliability have been obtained when the common scale parameter is known and the results are compared for both small and large samples.

Based on the simulation results, the authors observe that Bayes method provides better estimation results as compared to MLE. Proposed asymptotic and HPD intervals show satisfactory coverage probabilities. However, average length of HPD intervals tends to remain shorter than the corresponding asymptotic interval. Overall the authors have observed that better estimates of the reliability may be achieved when the common scale parameter is known.

Most of the lifetime distributions used in reliability analysis, such as exponential, Lindley, gamma, lognormal, Weibull and Chen, only exhibit constant, monotonically increasing, decreasing and bathtub-shaped hazard rates. However, in many applications in reliability and survival analysis, the most realistic hazard rates are upside-down bathtub and bathtub-shaped, which are found in the unit-Gompertz distribution. Furthermore, when reliability is measured as percentage or ratio, it is important to have models defined on the unit interval in order to have plausible results. Therefore, the authors have studied the multicomponent stress–strength reliability under the unit-Gompertz distribution by comparing the MLEs, Bayes estimators and UMVUEs.

The authors aim to examine how macro, meso and micro territorial boundaries influence the loan repayment performance of female clients of mega microfinance institutions (MFIs) operating in a polarized Latin America and the Caribbean (LAC).

The study uses panel data (random effect analysis) comprising seven years and 407 MFIs of LAC.

The repayment performance of MFIs' female clients in LAC is meso and micro territorially bounded. It is positively influenced by the urbanization and gender inequality levels of the LAC countries, and by the number of loans per MFI loan officer.

Data concerning the risk of the businesses women invested in, or data related to women's access to credit, were not included; high heterogeneity in large countries must be taken into account. The authors' findings expand the understanding of territorial boundary conditions concerning female clients' repayment performance and extend the prior literature on the subject.

The authors' findings suggest that the MFIs operating in LAC should increase their number of loan officers. The MFIs of the Mexico-led cluster may also seek a better balance between female and male clients, since hiring more loan officers may be impracticable for them.

The authors empirically challenge the widely accepted assumption that female clients are always the best choice for MFIs. They also unfold territorial boundaries conditioning these clients' performance.