Business Administration - Research Publications
Permanent URI for this collection
Search Results
1 - 10 of 95
-
ItemNo Preview Availablebamlss: A Lego Toolbox for Flexible Bayesian Regression (and Beyond)(JOURNAL STATISTICAL SOFTWARE, 2021-11-01)
-
Item
-
ItemInterpretable modelling of retail demand and price elasticity for passenger flights using booking data(SAGE Publications, 2022-01-01)We propose a model of retail demand for air travel and ticket price elasticity at the daily booking and individual flight level. Daily bookings are modelled as a non-homogeneous Poisson process with respect to the time to departure. The booking intensity is a function of booking and flight level covariates, including non-linear effects modelled semi-parametrically using penalized splines. Customer heterogeneity is incorporated using a finite mixture model, where the latent segments have covariate-dependent probabilities. We fit the model to a unique dataset of over one million daily counts of bookings for 9 602 scheduled flights on a short-haul route over two years. A control variate approach with a strong instrument corrects for a substantial level of price endogeneity. A rich latent segmentation is uncovered, along with strong covariate effects. The calibrated model can be used to quantify demand and price elasticity for different flights booked on different days prior to departure and is a step towards continuous pricing; something that is a major objective of airlines. As our model is interpretable, forecasts can be created under different scenarios. For instance, while our model is calibrated on data collected prior to COVID-19, many of the empirical insights are likely to remain valid as air travel recovers in the post-COVID-19 period.
-
ItemHow the Linguistic Styles of Donald Trump and Joe Biden Reflect Different Forms of Power(SAGE Publications, 2022-01-01)Can theories of power be used to explain differences in the linguistic styles of Donald Trump and Joe Biden? We argue that the two candidates possess and use different forms of power—and that this is associated with typical language patterns. Based on their personal history, news reports, and empirical studies, we expect that Trump’s approach to power is characterized by coercive power forms and Biden’s by collaborative power forms. Using several LIWC categories and the moral foundations dictionary, we analyzed over 500 speeches and 15,000 tweets made during the 2020 election battle. Biden’s speeches can be described as analytical and frequently relating to moral values, whereas Trump’s speeches were characterized by a positive emotional tone. In tweets, Biden used more social words and words related to virtue, honesty, and achievement than Trump did. Trump’s coercive power and Biden’s collaborative power were more observable in tweets than speeches, which may reflect the fact that tweets are more spontaneous than speeches.
-
ItemReview of guidance papers on regression modeling in statistical series of medical journals.(Public Library of Science (PLoS), 2022)Although regression models play a central role in the analysis of medical research projects, there still exist many misconceptions on various aspects of modeling leading to faulty analyses. Indeed, the rapidly developing statistical methodology and its recent advances in regression modeling do not seem to be adequately reflected in many medical publications. This problem of knowledge transfer from statistical research to application was identified by some medical journals, which have published series of statistical tutorials and (shorter) papers mainly addressing medical researchers. The aim of this review was to assess the current level of knowledge with regard to regression modeling contained in such statistical papers. We searched for target series by a request to international statistical experts. We identified 23 series including 57 topic-relevant articles. Within each article, two independent raters analyzed the content by investigating 44 predefined aspects on regression modeling. We assessed to what extent the aspects were explained and if examples, software advices, and recommendations for or against specific methods were given. Most series (21/23) included at least one article on multivariable regression. Logistic regression was the most frequently described regression type (19/23), followed by linear regression (18/23), Cox regression and survival models (12/23) and Poisson regression (3/23). Most general aspects on regression modeling, e.g. model assumptions, reporting and interpretation of regression results, were covered. We did not find many misconceptions or misleading recommendations, but we identified relevant gaps, in particular with respect to addressing nonlinear effects of continuous predictors, model specification and variable selection. Specific recommendations on software were rarely given. Statistical guidance should be developed for nonlinear effects, model specification and variable selection to better support medical researchers who perform or interpret regression analyses.
-
ItemGender equality in the Finance industry: The challenging ‘last mile’(ANZAM, 2021-12-03)Organisational efforts to increase gender equality in leadership have had limited success, and Australia’s ranking in the global gender equality index has slipped since 2006. We call this challenging stage in gender equality efforts the ‘last mile’. To understand what hinders or assists organisational efforts in the ‘last mile’ we conducted an in-depth study of the diversity efforts in a business unit of a large Australian bank. Interviews, focus groups and archival data analyses demonstrated that the bank’s gender equality performance was better than their institutional field, and the workforce was more optimistic about gender equality outcomes than executives. Ironically, these illusions of progress hindered the bank’s ability to travel the ‘last mile’.
-
ItemInternational survey evidence on user and community co-delivery of prevention activities relevant to public services and outcomes(ROUTLEDGE JOURNALS, TAYLOR & FRANCIS LTD, 2021-10-17)
-
ItemMore on Convening Technology: Blockchain, Fashion, and the Right to Know(Wiley, 2022)For many years mired in its cryptocurrency history, blockchain held little interest to those working outside the financial world. It now offers the fashion industry and its diverse publics the enticing prospect of a transparent value chain for ethical and sustainable fashion, catering to public demands for a right to know data on authenticity and provenance. Whether this is a feasible prospect remains to be seen. Nevertheless, in staking out its position, blockchain appears to be moving into an interesting phase of its short tumultuous existence. In short, it is taking on the character of a “convening technology” – becoming “the focus of a conversation that can [potentially] address issues far beyond what it may ultimately be able to address itself”, and marshalling “resources, institutions and other forms of power”. A difficulty is reconciling this beneficial function with the need for the so-called “technology of trust” to be trustworthy in practice, requiring at least a minimal governance model.
-
ItemExact confidence limits after a group sequential single arm trial(John Wiley and Sons, 2021-05-10)Group sequential single arm designs are common in phase II trials as well as attribute testing and acceptance sampling. After the trial is completed, especially if the recommendation is to proceed to further testing, there is interest in full inference on treatment efficacy. For a binary response, there is the potential to construct exact upper and lower confidence limits, the first published method for which is Jennison and Turnbull (1983). We place their method within the modern theory of exact confidence limits and provide a new general result that ensures that the exact limits are consistent with the test result, an issue that has been largely ignored in the literature. Amongst methods based on the minimal sufficient statistic, we propose two exact methods that out‐perform Jennison and Turnbull's method across 10 selected designs. One of these we prefer and recommend for practical and theoretical reasons. We also investigate a method based on inverting Fisher's combination test, as well as a pure tie‐breaking variant of it. For the range of designs considered, neither of these methods result in large enough improvements in efficiency to justify violation of the sufficiency principle. For any nonadaptive sequential design, an R‐package is provided to select a method and compute the inference from a given realization.
-
ItemStatistical model building: Background "knowledge" based on inappropriate preselection causes misspecification(BMC, 2021-09-29)BACKGROUND: Statistical model building requires selection of variables for a model depending on the model's aim. In descriptive and explanatory models, a common recommendation often met in the literature is to include all variables in the model which are assumed or known to be associated with the outcome independent of their identification with data driven selection procedures. An open question is, how reliable this assumed "background knowledge" truly is. In fact, "known" predictors might be findings from preceding studies which may also have employed inappropriate model building strategies. METHODS: We conducted a simulation study assessing the influence of treating variables as "known predictors" in model building when in fact this knowledge resulting from preceding studies might be insufficient. Within randomly generated preceding study data sets, model building with variable selection was conducted. A variable was subsequently considered as a "known" predictor if a predefined number of preceding studies identified it as relevant. RESULTS: Even if several preceding studies identified a variable as a "true" predictor, this classification is often false positive. Moreover, variables not identified might still be truly predictive. This especially holds true if the preceding studies employed inappropriate selection methods such as univariable selection. CONCLUSIONS: The source of "background knowledge" should be evaluated with care. Knowledge generated on preceding studies can cause misspecification.