University of Twente Student Theses
BSR lifestyles and mobility behaviouor
Bosma, E. (2017) BSR lifestyles and mobility behaviouor.
|
PDF
1MB |
| Abstract: | The Brand Strategy Research model (BSR model) has different uses for the municipality of Rotterdam. The statistical department raised the question whether lifestyles of the BSR model and mobility behaviour have correlations. This raised the idea to do a research in cooperation with DAT.Mobility. There are no datasets with both BSR-lifestyles and mobility behaviour. That is why the first step of this research is to explain the BSR lifestyles with quantitative measurable household indicators. This way, BSR-lifestyles can be added to datasets with mobility behaviour like OViN and can be evaluated further. This research concentrates on this first step. A Multinomial Logistic Regression model (MLR model) is used to explain the BSR-lifestyles in household indicators. This model has different advantages, it does not make any assumptions about normality, linearity or homoscedasticity of the variables. It can also handle more than two categories of the dependent variable. In this case, the dependent variable is the BSR-model with four categories, its lifestyles. The main goal was to use the MLR model to describe the BSR model with household indicators. A performance higher than 50%, based on the correct predicted lifestyles, was not possible. This has various reasons. Firstly, a very high performance, around 100%, would detract the psychographic classification of the BSR model. Also, people are never completely one lifestyle but have traits of all lifestyles, there is a distribution of lifestyles for every person. The lifestyle that is most present is assigned to that person, this is the dominant lifestyle. Sometimes, the dominant lifestyle is just for 40% present in data of a person. But the data we have, only contains the dominant lifestyles, not the distribution of lifestyles. That causes the fact that there can easily be made mistakes in predictions. Lastly, SmartAgent, the company that created the BSR model, uses a similar method to predict lifestyles. They accept a performance of 46%. This is a good indication for the maximum reachable performance of the model in this research. At first sight, the performance of 47% from the MLR model seems limited, but it is still applicable in other datasets. In this case, the model is applied to a dataset with mobility data, OViN 2015. There is no elaboration on these results because it is not the aim of the research and also because of time constrains. But the first results are analysed and show some plausible correlations between mobility behaviour and lifestyles. For example the blue lifestyle, who wants to show its status, has clearly more vehicles in its household. Also, the red lifestyle, often young people who live a free life, make clearly more trips per day. It is interesting to better analyse the relations between mobility indicators and lifestyles in future research. It is important to focus on the possibilities of different uses for BSR lifestyles in mobility models. Firstly, the lifestyles can be used as explanatory variables in models. They can add a new dimension to trip distributions. But because of a high number of insignificant factors while adding lifestyles to datasets and connecting them to mobility behaviour, the results will be unreliable. It is better to use the lifestyles as a way of communication with other fields, where BSR lifestyles are already used. For the municipality of Rotterdam, it is interesting to add BSR lifestyles as non-explanatory attributes to respondents. Policies can be adapted to the behaviour of the different groups. The lifestyles can be approached in an appropriate and appealing way, similar to the marketing strategies for which the BSR model was originally intended. |
| Item Type: | Essay (Bachelor) |
| Faculty: | ET: Engineering Technology |
| Subject: | 56 civil engineering |
| Programme: | Civil Engineering BSc (56952) |
| Link to this item: | https://purl.utwente.nl/essays/71815 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page