On Ordinary Least Squares Research Articles

Economic policies, macroeconomic environment and entrepreneurs' expectations

PurposeThe purpose of this paper is to analyze the influence of macroeconomic variables and economic policies on expectations and confidence of entrepreneurs. It provides an econometric analysis of the expectation transmission channel under inflation targeting in Brazil, emphasizing the effect of inflation targeting credibility on the business confidence of industrial entrepreneurs.Design/methodology/approachBased on ordinary least square (OLS), generalized method of moments (GMM) and vector autoregression (VAR), the paper provides empirical evidence about the influence of inflation targeting credibility and macroeconomic policies on expectations and confidence of entrepreneurs and, as a consequence, on industrial production.FindingsThe evidence for the Brazilian economy suggest that monetary and fiscal policies as well as the credibility of the monetary regime affect economic activity by their impact on expectations of entrepreneurs.Research limitations/implicationDevelopment of macroeconomic stability is important to the expectations formed by entrepreneurs and, therefore, for industrial production. In particular, inflation targeting credibility stimulates industrial production, since it increases the confidence of entrepreneurs about the functioning of the economy and their businesses.Originality/valueThe results suggest new insights about the influence of economic policies on the real side of the economy, pointing out that the conduct of economic policies in emerging countries with inflation targets are likely to affect the expectations of entrepreneurs and therefore their production decisions.

How do transport infrastructure and policies affect house prices and rents? Evidence from Athens, Greece

The interaction between land use and transportation infrastructure is a topic that has been extensively researched and continues to be of interest as new underlying economic, infrastructure and environmental conditions emerge. In this research, the direct and indirect effects of transportation infrastructure and policies on house prices and rents are studied. Since real estate transaction data are not available, a web-scraping tool was developed to parse house prices and attributes from publicly available resources. Econometric models of two categories were then estimated: (1) hedonic price models, based on Ordinary Least Squares (OLS) and (2) spatial econometric models, such as the spatial regression model (SAR), spatial error (SEM), Durbin (SDM) and autocorrelation (SAC) model and Geographically Weighted Regression (GWR), which are increasingly used by econometricians in order to capture the effect of the – usually unobserved – spatial factors on house valuation.The results of this research indicate that proximity to transportation infrastructure has a direct impact on house and apartment purchase prices and rents, which is either positive or negative depending on the type of the transportation system. Metro, tram, suburban railway and bus stations affect the prices positively, while ISAP (the old urban railway of Attica) and national rail stations, airports and ports, have a negative effect, due to a number of externalities associated with them, such as noise.The obtained results are consistent with expectations and the literature. While these results cannot be assumed directly transferable to other locations and areas, they could be cautiously used as indications for planning applications (where dedicated models have not been developed).

Estimation of reactivity ratios of styrene/butyl acrylate copolymer by ordinary and generalized least square methods

A novel generalized least square (GLS) estimator program was employed for determination of styrene (STY)/butyl acrylate (BA) reactivity ratios synthesized by solution copolymerization method. The monomer reactivity ratios as well as the 95 % individual confidence limits were determined by application of conventional linear methods like Finemann–Ross, Ezrielev–Brokhina–Roskin, Joshi–Joshi, Kelen–Tudos, modified Kelen–Tudos, extended Kelen–Tudos and Mao–Huglin. The estimation process was performed by applying techniques based on ordinary least square (OLS) and GLS approaches and the results were compared. The results showed a fairly good agreement between the experimental and calculated copolymer compositions. The model was then successfully validated through handling regression models with error terms that are heteroskedastic or autocorrelation, or both and clearly showed that the model was able to predict the reactivity ratios by accounting response error structure. Based on the copolymer compositions determined by 1H NMR, the reactivity ratios of STY and BA were found to be 0.886634 and 0.216369, respectively, by Mao–Huglin method through the GLS approach, and this new estimation method shows the best linear estimations for the monomer reactivity ratios. The present paper shows a new estimation integral approach for determining the monomer reactivity ratios by different conventional linear methods at low and high conversions in EViews software and the calculated values are discussed in terms of regression models.

Energy In-Equivalence in Australian Marsupials: Evidence for Disruption of the Continent’s Mammal Assemblage, or Are Rules Meant to Be Broken?

The energy equivalence rule (EER) is a macroecological hypothesis that posits that total population energy use (PEU) should be independent of species body mass, because population densities and energy metabolisms scale with body mass in a directly inverse manner. However, evidence supporting the EER is equivocal, and the use of basal metabolic rate (BMR) in such studies has been questioned; ecologically-relevant indices like field metabolic rate (FMR) are probably more appropriate. In this regard, Australian marsupials present a novel test for the EER because, unlike eutherians, marsupial BMRs and FMRs scale differently with body mass. Based on either FMR or BMR, Australian marsupial PEU did not obey an EER, and scaled positively with body mass based on ordinary least squares (OLS) regressions. Importantly, the scaling of marsupial population density with body mass had a slope of −0.37, significantly shallower than the expected slope of −0.75, and not directly inverse of body-mass scaling exponents for BMR (0.72) or FMR (0.62). The findings suggest that the EER may not be a causal, universal rule, or that for reasons not yet clear, it is not operating for Australia’s unique native fauna.

Inter-Regional Wage Differentials in Portugal: An Analysis Across the Wage Distribution

Pereira J. and Galego A. Inter-regional wage differentials in Portugal: an analysis across the wage distribution, Regional Studies. Typically, studies on regional wage differentials are based on ordinary least squares (OLS) estimates. Quantile regression is an alternative approach which allows these differences to be studied across the whole wage distribution. In this study, the quantile regression framework is considered for the analysis of regional wage differences in Portugal. The findings reveal significant differences in wage equations coefficients between regions for the various quantiles. Furthermore, it is concluded that the regional wage differentials and the components explained by differences in endowments and differences in returns increase across the whole wage distribution.

Sample size requirements to detect an intervention by time interaction in longitudinal cluster randomized clinical trials with random slopes

In longitudinal cluster randomized clinical trials (cluster-RCT), subjects are nested within a higher level unit such as clinics and are evaluated for outcome repeatedly over the study period. This study design results in a three level hierarchical data structure. When the primary goal is to test the hypothesis that an intervention has an effect on the rate of change in the outcome over time and the between-subject variation in slopes is substantial, the subject-specific slopes are often modeled as random coefficients in a mixed-effects linear model. In this paper, we propose approaches for determining the samples size for each level of a 3-level hierarchical trial design based on ordinary least squares (OLS) estimates for detecting a difference in mean slopes between two intervention groups when the slopes are modeled as random. Notably, the sample size is not a function of the variances of either the second or the third level random intercepts and depends on the number of second and third level data units only through their product. Simulation results indicate that the OLS-based power and sample sizes are virtually identical to the empirical maximum likelihood based estimates even with varying cluster sizes. Sample sizes for random versus fixed slope models are also compared. The effects of the variance of the random slope on the sample size determinations are shown to be enormous. Therefore, when between-subject variations in outcome trends are anticipated to be significant, sample size determinations based on a fixed slope model can result in a seriously underpowered study.

Robust monitoring of CAPM portfolio betas

Some robust sequential procedures for the detection of structural breaks in the Capital Asset Pricing Model (CAPM) are proposed and studied. Most of the existing procedures for this model are based on ordinary least squares (OLS) estimates. Here we propose a class of cumulative sum (CUSUM)-type procedures based on M-estimates and partial weighted sums of M-residuals. The theoretical results are accompanied by a simulation study that compares the proposed procedures with those based on OLS estimates. An application to a real data set is also presented.

Estimation of Heteroscedasticity Effects in a Classical Linear Regression Model of a Cross-Sectional Data

This paper investigates the effects of heteroscedasticity in the Classical Linear Regression Model (CLRM) of auditor's remuneration. Several efforts of building a realistic econometric model for Auditor's Remuneration with regards to core banking activities have been undertaken. The work involves the use of White heteroscedasticity and Newey-West test techniques to examine the presence of heteroscedasticity, which shows that heteroscedasticity is an inherent feature of cross-sectional data. The superiority of Weighted Least Squares (WLS) on Ordinary Least Squares (OLS) was put to test in estimating the parameters of Auditor’s Remuneration model designed as: \hspace*{10mm} $ AR_i = \theta_0 + \theta_1 T A_i + \theta_2 T E_i + \theta_3 C D_i + \theta_4 P B T_i + \varepsilon$ \hspace*{6mm}And it was established that OLS is not appropriate for estimation if heteroscedasticity is present in research data, and that the model fitted using WLS is the most appropriate that is deemed fit for proper review of auditor's remuneration in banking industry.

Modelling spatial heterogeneity and anisotropy: child anaemia, sanitation and basic infrastructure in sub-Saharan Africa

Public interventions in support of public health and housing in developing countries could benefit from better understanding of spatial heterogeneity and anisotropy. Estimation of directional variation within geographically weighted regression (GWR) faces problems of local parameter instability, border effects and, if extended to non- spatial attributes, potential endogeneity. This study formulates a GWR model where anisotropy is filtered out based on information from directional variograms. Along with classical regressions, the approach is applied to investigate child anaemia and its associations with household characteristics, sanitation and basic infrastructure in 173 regions of sub-Saharan Africa. Based on ordinary least squares (OLS) results, anaemia prevalence rates are up to three times more responsive to child morbidity (related to malaria and other diseases) than to other covariates. GWR estimates provide similar indications, but also point to poor sanitation facilities as a cofactor of severe anaemia particularly in east and southern Africa. The anisotropy-adjusted GWR is spatially stationary in residuals, and its estimated local parameters are less collinear than GWR with no adjustment. However, similar explanatory power and lack of significant bias in parameters estimated by the latter suggest that directional variation is largely captured by modelled co-movements among the variables.

The influence of urban physical form on trip generation, evidence from metropolitan Shiraz, Iran

This paper aims to examine the relationship between urban form and personal daily trips between urban zones across Metropolitan Shiraz, Iran. To cope with collinearity nature of trip generation determinants and also multicollinearity in model estimation, component principal analysis (PCA) was employed to identify latent dimensions of trip generation. Then, a multiple regression model with continuous independent variables was developed to measure the effect of each individual variable on entire trips generated among urban zones. The explanatory variables included both physical characteristics of the metropolitan (land use diversity, density, suburbanization, connectivity, and accessibility to public transport), and socio-economic characteristics of trip makers (age, employment status, education, migration, property value) aggregated on the urban zones scale. The empirical findings, based on ordinary least squares (OLS) estimation of 2006 data for 47 traffic area zones (TAZ) with total population over 1.1 million indicated that socio-economic characteristics were the most positive determinants of trip generation among the zones. On contrast, suburbanization (distance from central business district (CBD)) and distance from public transport facilities were negatively associated with the trip generation. However, other physical factors such as land use mix and network connectivity were found not important in influencing intra-zone trip generation, probably influencing inter-zone trip generation instead. In fact, improving local accessibility may reduce the need to intra-zonal travel, rather may also increase the tendency to travel within the neighborhood area.

Research of assembling optimized classification algorithm by neural network based on Ordinary Least Squares (OLS)

A new optimized classification algorithm assembled by neural network based on Ordinary Least Squares (OLS) is established here. While recognizing complex high-dimensional data by neural network, the design of network is a challenge. Besides, single network model can hardly get satisfying recognition accuracy. Firstly, feature dimension reduction is carried on so that the design of network is more convenient. Take Elman neural network algorithm based on PCA as sub-classifier I. The recognition precision of this classifier is relatively high, but the convergence rate is not satisfying. Take RBF neural network algorithm based on factor analysis as sub-classifier II. The convergence rate of the classifier algorithm is fast, but the recognition precision is relatively low. In order to make up for the deficiency, by carrying on ensemble learning of the two sub-classifiers and determining optimal weights of each sub-classifier by OLS principle, assembled optimized classification algorithm is obtained, so to some extent, information loss caused by dimensionality reduction in data is made up. In the end, validation of the model can be tested by case analysis.

Stock and bond market interactions with two regime shifts: evidence from Turkey

This study aims to examine the relationship between the stock market and the government bond market in Turkey over a period from May 2001 to August 2009 in order to find out whether specific asset allocation in these markets provides benefits. This article employs several cointegration techniques such as Engle and Granger (EG, 1987), Gregory and Hansen (GH, 1996) and Hatemi-J (HJ, 2008). Furthermore, it applies the long run elasticities of Stock and Watson (1993 Stock, JH and Watson, MW. 1993. A simple estimator of cointegrating vectors in higher order integrated systems. Econometrica, 61: 783–820. [Crossref], [Web of Science ®] , [Google Scholar]) and parameter stability tests of Hansen (1992 Hansen, BE. 1992. Tests for parameter instability in regressions with I(1) processes. Journal of Business and Economic Statistics, 10: 321–35. [Taylor & Francis Online], [Web of Science ®] , [Google Scholar]) and Andrews (1993 Andrews, DWK. 1993. Tests for parameter instability and structural change with unknown change point. Econometrica, 61: 821–56. [Crossref], [Web of Science ®] , [Google Scholar]). According to the results of EG and GH tests, the government bond index is not cointegrated with any other stock market indices. In contrast to the previous tests, we find a relationship which indicates low benefits of asset allocation between some stock indices and the government bond index when we employ the HJ method which takes two structural breaks into consideration. When we use the long run elasticities based on Ordinary Least Squares (OLS) and Dynamic OLS (DOLS) procedures, we find that the government bond index has a significant effect on some stock indices. In addition, employing the stability test of Hansen (1992 Hansen, BE. 1992. Tests for parameter instability in regressions with I(1) processes. Journal of Business and Economic Statistics, 10: 321–35. [Taylor & Francis Online], [Web of Science ®] , [Google Scholar]), we find that the results of cointegration test with structural breaks (HJ) are consistent. Finally, we use Quandt–Andrews (Andrews, 1993 Andrews, DWK. 1993. Tests for parameter instability and structural change with unknown change point. Econometrica, 61: 821–56. [Crossref], [Web of Science ®] , [Google Scholar]) test and investigate possible break points in the relationship between price indices.

TESTING FOR A SHIFT IN TREND AT AN UNKNOWN DATE: A FIXED-BANALYSIS OF HETEROSKEDASTICITY AUTOCORRELATION ROBUST OLS-BASED TESTS

This paper analyzes tests for a shift in the trend function of a time series at an unknown date based on ordinary least squares (OLS) estimates of the trend function. Inference about the trend parameters depends on the serial correlation structure of the data through the long-run variance (zero frequency spectral density) of the errors. Asymptotically pivotal tests can be obtained by the use of serial correlation robust standard errors that require an estimate of the long-run variance. The focus is on the class of nonparametric kernel estimators of the long-run variance. Tests based on these estimators present two problems for practitioners. The first is the choice of kernel and bandwidth. The second is the well-known overrejection problem caused by strong serial correlation (or a possible unit root) in the errors.We provide solutions to both problems by using the fixed-basymptotic framework of Kiefer and Vogelsang (2005,Econometric Theory, 21, 1130–1164) in conjunction with the scaling factor approach of Vogelsang (1998,Econometrica65, 123–148). Our results provide practitioners with a family of OLS-based trend function structural change tests that are size robust to the presence of strong serial correlation or a unit root. Specific recommendations are provided for the tuning parameters (kernel and bandwidth) in a way that maximizes asymptotic integrated power.

Linking leader behavior and leadership consensus to team performance: Integrating direct consensus and dispersion models of group composition

We sought to establish whether mean level within-team assessments of a leader's transformational behavior and the extent of perceived variability (i.e., consensus) among team members’ ratings around this mean level are separate yet related indicators of leader quality. To this end, using data from 108 work teams in a multinational field setting, we explored the relationship between managers’ transformational leadership behavior and team performance as moderated by the extent of variability among team members’ leadership behavior ratings. Recognizing that the relationship between leader behavior and team performance is indirect, we further examined whether team empowerment served as a mediating mechanism through which transformational leadership is evoked. Study results, based on ordinary least squares (OLS) regression analyses and bootstrapped estimates, were consistent with the hypothesized conceptual scheme of moderated mediation, in that the joint effects of transformational leadership behavior and consensus about transformational leadership were found to have an indirect effect on team performance through team empowerment. These findings broaden the focus of transformational leadership theory by illustrating that, within a team context, the transformational leadership–performance linkage is more nuanced than previously believed.

Modeling of Asymmetry between Gasoline and Crude Oil Prices: A Monte Carlo Comparison

An Engle---Granger two-step procedure is commonly used to estimate cointegrating vectors and consequently asymmetric error-correction models. This study uses Monte Carlo methods and demonstrates that the Engle---Granger two-step method leads to biased estimates of asymmetric parameters and in some cases suggests symmetry in the asymmetric data generating process (DGP). The single equation error correction models (SEECM) based on ordinary least squares (OLS) and nonlinear least squares (NLS) are employed for simultaneous estimation of the cointegrating vector and the ECM. The SEECMs perform better than Engle---Granger two-step procedures in estimating the asymmetry and making inferences on its existence in various DGPs. We show that SEECM estimations are less biased and inferences are less likely to be misleading compared to the Engle---Granger two-step procedure. Unlike the asymmetric specifications based on Engle---Granger two-step approach, the asymmetric SEECMs do not refute the possibility of long-run asymmetry by allowing different cointegrating vectors for positive and negative regimes. Examining the model with real data also supports the Monte Carlo results. While the conventional approaches imply symmetry, the proposed asymmetric SEECM, which has been embedded in a Threshold Autoregressive model, uncovers asymmetry at the presence of different cointegrating vectors for positive and negative regimes.

Monitoring service quality with residuals control charts

Purpose – The purpose of this paper is to devise a robust statistical process control methodology that will enable service managers to better monitor the performance of correlated service measures.Design/methodology/approach – A residuals control chart methodology based on least absolute value regression (LAV) is developed and its performance is compared to a traditional control chart methodology that is based on ordinary least squares (OLS) regression. Sensitivity analysis from the goal programming formulation of the LAV model is also performed. The methodology is applied in an actual service setting.Findings – The LAV based residuals control chart outperformed the OLS based residuals control chart in identifying out of control observations. The LAV methodology was also less sensitive to outliers than the OLS approach.Research limitations/implications – The findings from this study suggest that the proposed LAV based approach is a more robust statistical process control method than the OLS approach. In a...

Multi-Campus Studies of College Impact: Which Statistical Method is Appropriate?

In most multi-campus studies of college impact that have been conducted over the past four decades, investigators have relied on ordinary least squares (OLS) regression as the analytic method of choice. Recently, however, some investigators have advocated the use of Hierarchical Linear Modeling (HLM), a method specifically designed for analyses that involve both individual (student) and aggregate (institutional) level measures. Cross-validation analyses using a national database show that the two methods yield an equally good “fit” with empirical data. Existing OLS software has the advantage of enabling one to perform path analytical causal modeling; HLM has the advantage of yielding a more conservative estimate of the significance of institution-level effects.

TESTING FOR UNIT ROOTS IN PANELS WITH A FACTOR STRUCTURE

This paper considers various tests of the unit root hypothesis in panels where the cross-section dependence is due to common dynamic factors. Three situations are studied. First, the common factors and idiosyncratic components may both be nonstationary. In this case test statistics based on generalized least squares (GLS) possess a standard normal limiting distribution, whereas test statistics based on ordinary least squares (OLS) are invalid. Second, if the common component is I(1) and the idiosyncratic component is stationary (the case of cross-unit cointegration), then both the OLS and the GLS statistics fail. Finally, if the idiosyncratic components are I(1) but the common factors are stationary, then the OLS-based test statistics are severely biased, whereas the GLS-based test statistics are asymptotically valid in this situation. A Monte Carlo study is conducted to verify the asymptotic results.The research for this paper was carried out within research project “Unit roots and cointegration in panel data” financed by the German Research Association (DFG). We thank Paulo Rodrigues and two anonymous referees for helpful comments and suggestions.

Rethinking how family researchers model infrequent outcomes: A tutorial on count regression and zero-inflated models.

Marital and family researchers often study infrequent behaviors. These powerful psychological variables, such as abuse, criticism, and drug use, have important ramifications for families and society as well as for the statistical models used to study them. Most researchers continue to rely on ordinary least-squares (OLS) regression for these types of data, but estimates and inferences from OLS regression can be seriously biased for count data such as these. This article presents a tutorial on statistical methods for positively skewed event data, including Poisson, negative binomial, zero-inflated Poisson, and zero-inflated negative binomial regression models. These statistical methods are introduced through a marital commitment example, and the data and computer code to run the example analyses in R, SAS, SPSS, and Mplus are included in the online supplemental material. Extensions and practical advice are given to assist researchers in using these tools with their data.

Household diversity and market segmentation within a single neighborhood

Housing hedonic studies typically assume that individuals or households are similar enough to aggregate into a single demand equation for analysis, usually relying on ordinary least squares (OLS) or some other single-line equation estimator. Diversity itself is managed by non-spherical disturbance corrections, typically spatial autocorrelation or heteroskedasticity in the single line OLS estimate. This paper tests whether households in the same neighborhood can be theoretically and empirically treated as a single type or if households can be assigned into more than one type; multiple types suggests distinguishable local housing sub-markets. Our technique, a combination of the method of principal components and the seemingly unrelated regression (SUR) model, allows for one or more demand curves to represent housing demand and allows several types to compete over a fixed housing stock in a given residential neighborhood. As such, the SUR is the empirical translation of a theory that different household types can coexist in the same neighborhood.