Explore the vast range of titles available.

The impact of market share on financial firm performance is one of the most widely studied relationships in marketing strategy research. However, since the meta-analysis by Szymanski, Bharadwaj, and Varadarajan (1993), substantial environmental (e.g., digitization) and methodological (e.g., accounting for endogeneity) developments have occurred. The current work presents an updated and extended meta-analysis based on all available 863 elasticities drawn from 89 studies and provides the following new empirical generalizations: (1) The average raw market share-financial performance elasticity is . 132, which is substantially lower than the effectiveness of other intermediate marketing metrics. This result challenges a widely used strategy that solely focuses on increasing market share. (2) Elasticities differ significantly between contextual settings. For example, they are lower for business-to-business firms than for business-to-consumer firms, for service firms than for manufacturing firms, and for U.S. markets than for emerging and Western European markets. The authors also observe differences between countries with respect to a general time trend (e.g., lower elasticities in recent times for Western European markets) and recessionary periods (e.g., lower elasticities in the United States, higher elasticities in non-Western economies).

Group-level variance estimates of zero often arise when fitting multilevel or hierarchical linear models, especially when the number of groups is small. For situations where zero variances are implausible a priori, we propose a maximum penalized likelihood approach to avoid such boundary estimates. This approach is equivalent to estimating variance parameters by their posterior mode, given a weakly informative prior distribution. By choosing the penalty from the log-gamma family with shape parameter greater than 1, we ensure that the estimated variance will be positive. We suggest a default log-gamma(2, λ ) penalty with λ →0, which ensures that the maximum penalized likelihood estimate is approximately one standard error from zero when the maximum likelihood estimate is zero, thus remaining consistent with the data while being nondegenerate. We also show that the maximum penalized likelihood estimator with this default penalty is a good approximation to the posterior median obtained under a noninformative prior. Our default method provides better estimates of model parameters and standard errors than the maximum likelihood or the restricted maximum likelihood estimators. The log-gamma family can also be used to convey substantive prior information. In either case—pure penalization or prior information—our recommended procedure gives nondegenerate estimates and in the limit coincides with maximum likelihood as the number of groups increases.

In single-case research, the multiple baseline design is a widely used approach for evaluating the effects of interventions on individuals. Multiple baseline designs involve repeated measurement of outcomes over time and the controlled introduction of a treatment at different times for different individuals. This article outlines a general framework for defining effect sizes in multiple baseline designs that are directly comparable to the standardized mean difference from a between-subjects randomized experiment. The target, design-comparable effect size parameter can be estimated using restricted maximum likelihood together with a small sample correction analogous to Hedges's g. The approach is demonstrated using hierarchical linear models that include baseline time trends and treatment-by-time interactions. A simulation compares the performance of the proposed estimator to that of an alternative, and an application illustrates the model-fitting process.

Background Rapid economic and social development in China has resulted in severe air pollution and consequent adverse impacts on society. The health effects of air pollution have been widely studied. Methods Using information from the China Health and Retirement Longitudinal Study (CHARLS) database, we established a hierarchical linear model combining pollution and socioeconomic and psychosocial variables to examine the effects of air pollution on public health in China. Local air pollution was characterized in multiple dimensions. Results The relationship of health to its determinants greatly differed between Eastern and Central/Western China. Higher education, higher income level, better life satisfaction, and long-term marriage were significantly associated with better health status among Chinese. In addition, regional healthcare resources were positively associated with the health of residents. As indicated by the hierarchical model with health as dependent variable, in Central/Western China, longest duration of good air quality in spring/summer was positively associated with health (estimated coefficient = 0.067, standard error = 0.026), while the mean Air Quality Index (AQI) in autumn/winter was inversely associated with health (estimated coefficient = −0.082, standard error = 0.031). Good air quality in the current study is defined as daily average AQI less than 35. Conclusions Duration (in days) of acceptable air quality was particularly important for improving public health. Future policies should target increased duration of good air quality while managing air pollution by controlling or decreasing severe air pollution.

Multichannel retailers need to understand how to allocate marketing budgets to customer segments and online and offline sales channels. We propose an integrated methodological approach to assess how email and direct mail effectiveness vary by channel and customer value segment. We apply this approach to an international beauty retailer in six countries and to an apparel retailer in the United States. We estimate multi-equation hierarchical linear models and find that sales responsiveness to email and direct mail varies by customer value segment. Specifically, direct mail drives customer acquisition in the offline channel, while email drives sales for both online and offline channels for current customer segments. A randomized field experiment with the beauty retailer provides causal support for the findings. The proposed reallocation of marketing resources would yield a revenue lift of 13.5% for the beauty retailer and 9.3% for the apparel retailer, compared with the 6.5% actual increase in the field experiment.

The interest in the value relevance of marketing investments has given rise to numerous studies on the marketing-finance interface. This study integrates extant research findings and establishes empirical generalizations on marketing's impact on firm value. Specifically, the authors conduct a meta-analysis of prior econometric elasticity estimates of the stock market impact of marketing actions and marketing assets. Analyses based on 488 elasticities drawn from 83 studies reveal a mean elasticity of .04 for advertising expenditure variables and of .54 for marketing asset variables. Among marketing assets, customer-related assets show a higher mean elasticity of .72, compared with .33 for brand-related assets. Further analyses show that advertising elasticities are lower in more concentrated industries and that marketing asset elasticities are higher during recession times. Researchers should also be aware that characteristics of the research design (e.g., the type of firm value metric used, the omission of control variables, or not accounting for endogeneity) may affect the estimation results.

Background With the advent of the new media era, the understanding of adolescent internet addiction needs to be enriched. It is also necessary to distinguish the related factors of adolescent internet addiction at different levels to clarify the mechanisms of this phenomenon. Methods This study used hierarchical linear model analysis to explore the effects of student-level factors and school-level factors on adolescent internet addiction, along with cross-level moderating effects. A total of 1,912 students between the 4th and 8th grades in China participated in the study. Participants completed the Self-Esteem Scale, Parents Phubbing Scale, Classroom Environment Scale, and the Diagnostic Questionnaire of Internet Addiction. Results Correlational analyses revealed that internet addiction was found to be negatively correlated with both self-esteem and the teacher-student relationship ( p  < 0.01), while father phubbing, mother phubbing, and learning burden were shown to positively correlate with internet addiction ( p  < 0.01). Hierarchical linear model analysis suggested that student-level variables, including self-esteem, and mother phubbing, were significant predictors of internet addiction ( β = −0.077, p  < 0.001 and β  = 0.028, p  < 0.01, respectively). At the school level, learning burden significantly and negatively predicted internet addiction ( β  = 0.073, p  < 0.05). Furthermore, the relationship between self-esteem and internet addiction was significantly moderated by learning burden ( β = −0.007, p  < 0.05). Meanwhile, the teacher-student relationship also had a significant moderating effect on the association between mother phubbing and internet addiction ( β = −0.005, p  < 0.01). Conclusions This study revealed the relationships between self-esteem, parental phubbing, and classroom environment with adolescent internet addiction, and these findings could provide insights into reducing adolescent internet addiction from the perspective of individuals, families, and schools.

This study aims to investigate factors contributing to poverty, one of the most significant social problems in Western societies. To this end, 13 countries that have made a variety of efforts to reduce poverty, and therefore experienced similar development processes related to welfare, were selected. To overcome the methodological limitations of previous studies, the study utilized a Hierarchical Generalized Linear Model to simultaneously analyze individual-level and state-level factors that might affect the poverty status of a household, employing household data from the fifth wave of Luxembourg Income Study and Comparative Welfare State data. By comparing the magnitude of individual- and state-level effects in the analysis process, the model can empirically illuminate which of the two levels is more responsible for households' destitution. Furthermore, by analyzing the level of and characteristics of poverty in each country, this study examines whether there are discrepancies in the level of poverty across types of welfare states and what factors contribute to these discrepancies.

We compare various extensions of the Bradley–Terry model and a hierarchical Poisson log-linear model in terms of their performance in predicting the outcome of soccer matches (win, draw, or loss). The parameters of the Bradley–Terry extensions are estimated by maximizing the log-likelihood, or an appropriately penalized version of it, while the posterior densities of the parameters of the hierarchical Poisson log-linear model are approximated using integrated nested Laplace approximations. The prediction performance of the various modeling approaches is assessed using a novel, context-specific framework for temporal validation that is found to deliver accurate estimates of the test error. The direct modeling of outcomes via the various Bradley–Terry extensions and the modeling of match scores using the hierarchical Poisson log-linear model demonstrate similar behavior in terms of predictive performance.