A model is created to give a better understanding of a process or system and to use the information for making predictions and decisions. Modeling is done to describe some real phenomena in the world. There are different types of modeling and one of them is the mathematical modeling. Though mathematical modeling is advantageous for example, the experiment is carried out without disrupting the systems in existence, it has its limitations. For instance, the model creation needs making of approximations therefore the output distributions of the model are not identical to the real system. Therefore, mathematical modeling gives general results but not the exact results for specified problems (Barnes, & Fulford, 2008). Mathematical modeling is also costly and requires time. In mathematical modeling, one needs to have knowledge of the processes and phenomena that take place inside the model. Therefore, specialized training is needed so as to be able to develop equations of the model and this is usually costly at takes a lot of time. A conceptual model is a system’s descriptive model and it is usually based on assumptions that aid in decision making. Conceptual modeling makes use of a formal notation hence this gives the capability of expressing information and hence enabling the interpretation of meanings without having to get the meta-model. According to Delcambre, (2005), by use of a conceptual model, gaps in data are recognized in the early stages of carrying out the project. Therefore, it is faster to identify project areas that need more investigation. Using conceptual models is also advantageous in that it gives a business analysis that is more focused. This is because it provides an understanding of the existing as well as target environment. Therefore, conceptual modeling allows an individual to easily analyze business processes and also ensure that they make a relevant analysis. Another notable advantage is that conceptual modeling does not have effects on the storage of data and its access. Models are not developed to be a replica of reality but rather to guide an individual towards the realization of that reality. Therefore, models can display simplicity which is not the reality in the real world. Such matters which are displayed by models are usually complex issues in the real world. Modeling is usually a reality abstraction hence the results of the model should be close to the real situations. However, this is not always so and there exists a gap between the model results and the reality. Though modelers can try to make a model close to reality, it is not easy to correctly model the problem. Therefore the results will differ from the real world. This is because modeling uses approximations of the results and not the exact results in reality (Barnes, & Fulford, 2008). There is also the issue of failure to understand the real system and hence the model’s results will not be identical to the real ones. Though an individual can not know bias in a data set with precision there are some biases. Biases should therefore be identified if decisions would be made based on the obtained results. In a data set, there are three different types of biases and these are missing data, data being duplicated and data being shifted and therefore inaccurate (Delcambre, 2005). However, these biases can be managed and hence increase the efficiency of the conceptual model. This can be achieved by storing the model that is used to get the data and using it to make distinguishes among results that are obtained by use of different systems. This will help to know the source of bias and hence be able to manage it. Barnes, B. & Fulford, G. R. (2008) Mathematical modeling with case studies: a differential equations approach using Maple and MATLAB. 2 Delcambre, L.M. (2005). Conceptual modeling: ER 2005: 24th International Conference on Conceptual Modeling, Klagenfurt, Austria, October 24-28, 2005: proceedings. Switzerland: Birkhäuser |