Panel Logistic Models Research Articles

Kenyan Exports: Tax Incentives, Firm Traits, Firm-Level, and Macroeconomic Determinants

This study sought to understand the traits of the Kenyan exporter, what drives exports performance, and how the exporter responds to targeted policy measures. A two-stage approach to modelling was used. In the first stage, the firm’s decision to export was done in a panel logistic model. In stage two, the drivers of export volumes at the macro-level were estimated using a Vector Autoregressive (VAR) model. The panel econometric modelling method was applied to 118,380 firm-level data spanning 2014 to 2019. While firm-specific characteristics (age, size, access to credit, labour intensity, and labour quality) affect exports, government policy informs of tax incentives may not create a substantial difference in the decision and volume of exports at the firm level. Exporting firms are labour intensive. The results of a VAR model using time series data from 1960 to 2020 confirm the firm-level analysis. Kenya exports are more driven by local production capacity than world demand. Secondly, exports are more labour responsive than capital responsive at a macro level. Local productivity capacity is significantly labour-driven than capital-driven. Therefore, labour-targeted policies would be more impactful. Exports response to local production capacity is instantaneous while a period of 3.5 years lapses before exports respond significantly to world-changing demand.

The more, the better? The effect of feedback and user's past successes on idea implementation in open innovation communities

AbstractEstablishing open innovation communities has evolved as an important product innovation and development strategy for companies. Yet, the success of such communities relies on the successful implementation of many user‐submitted ideas. Although extant literature has examined the impact of user experience and idea characteristics on idea implementation, little is known from the information input perspective, for example, feedback. Based on the information overload theory and knowledge content framework, we propose that the amount and types of feedback content have different effects on the likelihood of subsequent idea implementation, and such effects depend on the level of users' success experience. We tested the research model using a panel logistic model with the data of MIUI Forum. The study results revealed that the amount of feedback has an inverted U‐shaped effect on idea implementation, and such effect is moderated by a user's past success. Moreover, the type of feedback content (cost and benefit‐related feedback and functionality‐related feedback) positively affects idea implementation, and a user's past success positively moderated the above effects. Finally, we discuss the theoretical and practical implications, limitations of our research, and suggestions for future research.

An empirical investigation of patent and trademark ownership propensity and intensity in the U.S. food and drink industry

We use patent and trademark ownership data to study product, process, and marketing innovation by 157 manufacturers in the U.S. public food and drink industry. For the 2000-2014 period, most patented innovations relate to processes for manufacturing and designs for marketing, whereas patented innovations in food and drink products or compositions are relatively few. Meanwhile, intellectual property in general is more often protected by trademark ownership. Empirically, we specify a panel logistic model and a panel negative binomial model to study the relationship of firm characteristics to the propensity and intensity of patent and trademark ownership, respectively. In each model, firm size exhibits a significant and positive relationship to the propensity and intensity of patented innovations in products, processes, and marketing. Past innovation, past income, and firm age also have a positive relationship to patent and trademark ownership in most models, whereas leverage is only estimated to negatively relate to the propensity and intensity of trademark ownership. We use our main findings and conclusions to inform research, management, and policy implications.

Psychiatric symptoms and alcohol use in community violence by persons with a psychotic disorder or depression.

Prior studies have shown a significant but modest association between mental disorders and violence and an increased risk in the presence of co-occurring substance use disorders. Categorical diagnoses, however, have limited utility when assessing dynamic risk state over time. This study used data from the MacArthur Violence Risk Assessment Study to examine the relationship of symptom levels and alcohol use to violence in repeated observations within two diagnostic groups. Participants with a primary categorical diagnosis of depression (N=386) or a psychotic disorder (N=201) were identified. Subscale scores for affective or positive symptoms from the Brief Psychiatric Rating Scale and self-reported alcohol consumption were tested in panel logistic models over five ten-week intervals for their concurrent and lagged relationship to violence. An interaction term between each type of symptom and alcohol use was also tested. In models including the amount of alcohol consumed and symptom levels, a high level of affective symptoms was associated with violence during the next follow-up period only for participants with depression. There was a significant interaction between alcohol use and affective symptoms for participants with depression. The relationship of symptoms and alcohol use to community violence should be considered in the context of the individual's primary diagnosis. Further characterization of interactions between symptoms and substance use in relation to violent behavior may allow for more effective assessment of risk state and interventions for violence prevention.