Anup Menon Nandialath

Revisiting the Determinants of Entrepreneurship: A Bayesian Approach

Entrepreneurship has long been seen as an important instrument in stimulating and generating economic growth. The amount of research trying to identify key factors that drive entrepreneurship is considerable; yet, little consensus has been achieved. We argue that this lack of consensus could be on account of model uncertainty as empirical studies often tend to be selective on what variables are included in the final model. Drawing on recent literature, we demonstrate the benefits of Bayesian model averaging (BMA) in reducing the impact of model uncertainty on empirical research in entrepreneurship. Additionally, BMA provides measures of variable importance and can be seen as a complementary approach to dominance/relative importance analysis. We show that when model uncertainty is corrected for, gross domestic product per capita, unemployment, the marginal tax rate, and the volatility of inflation are the only macro variables significantly and universally associated with aggregate entrepreneurship. Furthermore, the emphasis on inflation and taxation suggests that governments have the power to influence the quantity and distribution of entrepreneurial activity by setting incentives that are not entrepreneurship specific but overlap significantly with general and fundamental principles of economic stability.

A Structural Approach to Handling Endogeneity in Strategic Management: The Case of RBV

In this paper we posit that the lack of consensus about empirical tests of resource based view (RBV) could be the result of endogenous resource picking on the part of firms. If resources are endogenously selected, regression based methods that examine their connection to firm performance will be mis-estimated. We show that traditional remedies for endogeneity do not resolve this problem when returns to resources are heterogeneous (as theorized under RBV) and when managers act with at least partial knowledge of the expected, idiosyncratic return (as theorized under the strategic factor market hypotheses). As such, we develop a Bayesian approach that solves this endogeneity problem by directly incorporating resource picking into the modeling framework. We illustrate the validity of our approach through the use of a comprehensive simulation study and show that our proposed approach outperforms traditional linear models (including traditional cures of endogeneity and unobserved heterogeneity) under a variety of conditions. Our findings suggest that: (1) research in strategy requires a more careful and deeper understanding of potential sources of endogeneity and (2) the use of Bayesian methods in management can help develop more theoretically motivated empirical approaches to hypothesis testing.

Innovation capabilities and international performance of firms: a quantile regression approach

This study examines the relationship between various dimensions of a firm’s technological innovation capabilities and its international performance. We use panel data with multiple indicators of firm level technological capabilities including generation, dissemination, strength and speed of innovation. We employ a quantile regression analysis which allowed us to test the impact of innovation capability on international performance of high, average and poor performers. Our empirical findings indicate significant disparity between the ordinary least square and quantile regression results.

Critical thresholds for budget consolidations: a semi-parametric approach

While a lot is known regarding the determinants of successful fiscal consolidations, previous studies do not allow for the possibility of nonlinearities in factors impacting budget consolidations. By using a semi-parametric modelling approach employing penalized spline regression on a data-set for 28 OECD countries for the period 1978–2007, we demonstrate the existence of critical thresholds not only for the initial debt level but also for the accompanying monetary policy. The latter result shows when monetary policy matters most and suggests, counter to previous studies, that too lax a monetary policy decreases the success probability of a fiscal adjustment episode.

Modelling heterogeneity in perceptions of stress in Indian call centres: a latent class analysis

Stress is one of the biggest human resource (HR) problems facing high turnover industries like the Indian international call centre industry. This paper provides a comprehensive study of how the attitudes of call centre employees towards different aspects of their work affect their level of stress experienced. Our specific contribution to the literature is in understanding the heterogeneity among employees and how that affects meaningful inference in studying employees’ perceptions of stress. To achieve this goal, we compare and contrast between traditional regression models used in the extant literature with latent class regression analysis. The latent class analysis suggests the presence of four distinct groups of employees, confirming the heterogeneity present in the data. This study is unique in trying to explore how individuals may differ in their experience of stress and how there may be heterogeneity in the relationships explored between various cognitive and affective variables and experiences of stress.

Modeling the determinants of turnover intentions: a Bayesian approach

Much of what we learn from empirical research is based on a specific empirical model(s) presented in the literature. However, the range of plausible models given the data is potentially larger, thus creating an additional source of uncertainty termed: model uncertainty. The purpose of this paper is to examine the effect of model uncertainty on empirical research in HRM and suggest potential solutions to deal with the same.,Using a sample of call center employees from India, the authors test the robustness of predictors of intention to leave based on the unfolding model proposed by Harman et.al. (2007). Methodologically, the authors use Bayesian Model Averaging (BMA) to identify the specific variables within the unfolding model that have a robust relationship with turnover intentions after accounting for model uncertainty.,The findings show that indeed model uncertainty can impact what we learn from empirical studies. More specifically, in the context of the sample, using four plausible model specifications, the authors show that the conclusions can vary depending on which model the authors choose to interpret. Furthermore, using BMA, the authors find that only two variables, job satisfaction and perceived organizational support, are model specification independent robust predictors of intention to leave.,The research has specific implications for the development of HR analytics and informs managers on which are the most robust elements affecting attrition.,While empirical research typically acknowledges and corrects for the presence of sampling uncertainty through p-values, rarely does it acknowledge the presence of model uncertainty (which variables to include in a model). To the best of the authors’ knowledge, it is the first study to show the effect and offer a solution to studying total uncertainty (sampling uncertainty + model uncertainty) on empirical research in HRM. The work should open more doors toward more studies evaluating the robustness of key HRM constructs in explaining important work-related outcomes.

Did PwC lose reputation post audit failure at Satyam Computer Services? Evidence from the Indian audit market

Safeguarding reputation is one major incentive for large auditors to maintain high audit quality. We investigate the phenomenon of reputation by studying the impact of an audit failure on the reputation of a large audit firm in India. Specifically, we analyse the events surrounding the high profile audit failure of Satyam Computer Services and its resultant impact on the audit practice of PricewaterhouseCoopers (PwC) and its affiliates in India. The results of our analysis indicate that following the audit failure there was a high propensity for clients of PwC firms to switch to other firms. We interpret this behaviour as indicative of a loss of reputation for PwC due to the Satyam audit failure.

Endogeneity and dynamics of innovation and firm performance

Technological and innovation capabilities play an important role in determining the performance of firms, especially in knowledge intensive industries. Despite the plethora of studies testing the relationship between innovation capabilities and firm performance, little consensus has been achieved on the veracity of the theoretical claims. In this paper, we argue that the lack of consensus could be on account of the failure to take into account the endogeneity that arises from the decision process that underlies the relationship between development of technological capabilities and its impact on firm performance. We address both these issues and demonstrate that alternative empirical designs can help provide greater external validity.

Heterogeneity and Strategic Choices: The Case of Stock Repurchases

Strategic decisions are fundamentally tough choices. Theory suggests that managers are likely to display bounded rationality. Empirics on the other hand assume rationality in choice behavior. Recognizing this inherent disconnect between theory and empirics, we try to account for behavioral biases using a theoretically consistent choice model. The traditional approach to modeling strategic choice has been to use discrete choice models and make inference on the conditional mean effects. We argue that the conditional mean effect does not capture behavioral biases. The focus should be on the conditional variance. Explicitly modeling the conditional variance (in the discrete choice framework) provides us with valuable information on individual level variation in decision-making. We demonstrate the effect of ignoring the role of variance in choice modeling in the context of firm’s decisions to conduct open market repurchases. We show that when taking into account the heterogeneity in choices, manager’s choices of conducting open market repurchases displays considerable heterogeneity and that not accounting for such heterogeneity might lead to wrong conclusions on the mean effects.