Search results for "regression"

Evaluating temporary retail price discounts using semiparametric regression

2009

PurposeTo analyze the impact of temporary retail price discount on a consumer goods product category using semiparametric regression and considering different promotional price discount characteristics as well as brand characteristics.Design/methodology/approachA semiparametric regression model using Support Vector Machines, which aim to evaluate retailers' decisions about temporary price discounts, has been developed. The model is derived from the analysis of historical sales data, which provide precise evaluation of previous temporary price discounts periods. The model is also consistent with ample empirical evidence showing that historical retail sales data can be used to evaluate the im…

The determinants of conversion rates in SME e-commerce websites

2018

Abstract Web retailers invest significant resources to improve the proportion of website visitors that make a purchase, also known as the conversion rate. Improving this rate is particularly important to SMEs that have traditionally lagged behind larger firms as they have found it difficult to justify the significant investment involved in website development against the historical low returns associated with an online sales channel. Identifying methods that increase conversion rates reduces these perceived barriers and increases effective SME participation in the growing e-commerce sector. This paper uses 1184 observations from 6 SME websites to identify and analyse the factors, or combina…

Quantile regression for the FDI gravity equation

2015

Abstract Firm-level heterogeneity shapes foreign direct investment (FDI) flows, whereby a few firms are responsible for most of the world's FDI. Aggregate outcomes of FDI are highly skewed, and the estimates of FDI's antecedents vary largely depending on FDI level. The incidence of individual firms, however, varies across FDI's quantiles. To study the individual firms' effect on FDI flows, this study develops a quantile regression method for bilateral FDI panel data. This study estimates the differential incidence of individual firm-level projects on aggregate flows among 161 countries from 2003 to 2012. Results suggest that FDI's determinants vary across quantiles. In particular, the effec…

Three decades of subsidiary exits: Parent firm financial performance and moderators

2020

Abstract This study aimed to find important constructs and relationships among models of subsidiary divestment during the period from 1989 to 2018 using correlation matrices of 80 studies, the selection of which was based on six criteria. It revealed eight important constructs, namely firm innovativeness, environmental factors in the target country, type of experience, organizational characteristics, investment strategy, parent firm financial performance, subsidiary divestment, and the moderating effects of advertising intensity and product diversification. Furthermore, it shed light on seven relationships that should be considered in future attempts to assess parent performance related to …

Individualized evaluation of health cost and health risks

2019

Abstract This paper presents an individualized evaluation of the health costs and health risks of haze pollution by conduction channels and conduction strengths. Ordinal probit model and quantile regression are used to analyze data on individuals in Hangzhou, an environmental friendly city in China. The analyses yield four findings. First, in Hangzhou, haze pollution increases citizens' health spending by >2.49 billion US dollars. Second, health costs are mainly driven by increased risks of respiratory infection. Third, the quantile analysis of health risks shows the conduction channels and corresponding strengths vary for different population groups by age and health status. Lastly, respon…

The effect of high performance work systems on small and medium size enterprises

2015

Abstract This study analyzes the processes that explain high performance work system (HPWS) effect on company performance in small and medium size enterprises (SMEs). This study tests this relationship in SMEs by selecting three high performance work practices (HPWP) and an outcome variable based on the return on investment. A regression model with a sample of 78 companies tests the hypothesis. Results confirm the positive effect of HPWP on the performance of SMEs.

Performance analysis of research spin-offs in the Spanish biotechnology industry

2012

Abstract This study examines whether the performance of biotechnology research spin-offs in Spain differs from non spin-off firms, using empirically-based fieldwork over a 5-year period and standard dichotomous regression analysis on 7-year data. Biotechnology research spin-offs in Spain are not necessarily located in core regions, are smaller in size and tend to grow faster in terms of turnover. Corporate groups seldom control them but venture capitalists have a greater tendency to acquire shareholdings in them. Compared to non spin-off firms, research spin-off firms face more serious and more numerous challenges and disadvantages. Only two advantages are apparent: their capacity to attrac…

Predictors of tourist engagement: Travel motives and tourism destination profiles

2020

Abstract The aim of this study is to investigate the influence of travel motives and regional tourism destinations on positive/negative engagement with a destination management organisation (DMO). According to previous literature, travel motives were classified as push and pull motives, and regional tourism destinations were classified by tourist demand behaviour. To achieve the objective, the totality of posts about regional tourism destinations published on the Brand Spain's Official Facebook Fanpage during a year were analysed (418), along with audience reactions (127,750), comments (3219) and shares to such posts. A content analysis was performed, with a regression analysis (optimal sca…

Using Support Vector Semiparametric Regression to estimate the effects of pricing on brand substitution

2008

Using Daily Store-level Data to Understand Price Promotion Effects in a Semiparametric Regression Model

2009

Though it has been widely reported in the marketing literature that temporary price discounts generate substantial short-term sales increase, the shape of the deal effect curve constitutes a key research topic, for which there are still limited empirical results. To address this issue, a semiparametric regression approach is used to model the complex nature of this phenomenon. Our model is developed at the brand level using daily store-level scanner-data, which allows the study of several nonreported promotional effects, such as the influence of the day of the week both in promotional and nonpromotional periods. The results show that the weekend is the most effective in increasing promotion…