Hi,
Please i need a writer who is good in coursework writing and as well as R programming to help with the chapter 3 (research methodology ) and Chapter 4 (analysis) of my coursework please. AS i already have chapter 1 and 2 already so the writer will have to read my chapter 1 and 2 to be able to do 3 and 4 But Chapter 3 will have to be submitted on the 19th of April the topic is on Impact of Video Marketing on consumer behaviour (A case study of MTN telecommunication)
You will have to look for a and DOWNLOAD a Secondary dataset for this topic we are working on for the analysis Impact of Video Marketing on Consumer behaviour (case study of MTN telecommunications Nig). Please when downloading make sure to refernce the dataset the source date and time of download pleaseand send me asap before 10PM TODAY 12/04/2021 so we can get an approval of the datatset.
The writer needs to make sure that his r analysis can be replicated by me or a marker without hassle when they run it on their computer. Make sure to use Havard referencing style strictly quantitative analaysis.
Heneeds to make sure the chapter 3 and 4 come out good so when i combine my chapter 1 and 2 everything flows together Please kindly confirm if this is what you can do please If this is something that can be done then i can upload furhter documents
The dissertation The dissertation combines what you have learned in the autumn and spring term and asks you to the analytics toolkit to a management (research) question. When looking for a dissertation topic or area keep in mind that strength of a graduate in MSc Management with Business Analytics compared with MSc in data science is that the management graduate is able to address a clear management question and communicate recommendation for managerial actions clearly. The technical skills in data analytics are stronger for the data science graduate. Hence, I suggest to focus on a management question: what can the business learn from your analysis? Nevertheless, your dissertation will deviate in specific areas from dissertations in the MSc Management framework. Most notably: · you should focus on quantitative research (which is analytics by definition) · you should analyse a large secondary data to apply advanced analytical tools · you can use the dissertation to deepen your knowledge in specific analytical methods which will shorten the literature review part. · you should spend sufficient space to visualise the key results and provide an in-depth analytical investigation · you have to submit the dataset and the R script to your supervisor The "should" means that this applies to the majority of dissertations. Please speak with your supervisor if you want to collect your own data for example and discuss the consequences and possibilities of such an approach. If you want to use another software than R, please speak with your supervisor. Phyton will probably not a problem as it is open source but some software solutions require licences. Learning material The majority of the learning material can be found in the dissertation unit. You find below an explanation of a few specific areas in which an analytics dissertation deviates from dissertation in other MSc Management programmes. The dissertation unit provides materials and videos for · developing a dissertation idea and writing a proposal · writing the literature review · research methodology (qualitative and quantitative) · discussing your research findings · milestones, template guidelines and assessment criteria Analytics require a slightly different proposal approach and a more sophisticated methodology (see below) but the other parts are relevant. Your supervisors expect that you are familiar with the unit contents. The proposal The structure of the proposal is the same as for other MSc Management dissertations but the detailed description of the dataset is unique to business analytics dissertations. Think about the proposal as a feasibility study. The proposal explores if you can deliver the dissertation within three months. The key problem is the alignment of your management or research question with the secondary dataset. The dataset has to allow you to analyse your business or management question. Keep in mind that you study MSc Management with Business Analytics not MSc Data Science, meaning that the management question and the communication of the analytical findings are in the centre of the task. A secondary dataset constrains the business and management questions that you can analyse. If you have a great and topical research question but no suitable dataset that includes variables to measure your key concepts, you will not be able to analyse this research question. Hence the development of the research question and the exploration of data goes hand-in-hand in the proposal. You will find many datasets on the internet. However, you need to double check that they are not behind a paywall or have other user restrictions. A good starting point to looking for open datasets are listed on the secondary datasets page in this section. Some of datasets might require registration and sometimes your supervisor need to download the dataset for you. The structure of your proposals is explained in the Research Project unit. Please familiarise yourself with the required parts of the proposal. In addition, business analytics dissertation proposals explain the secondary dataset you want to use and describe the key variables of the data in the methodology part. Identifying the dataset is the key part of the proposal process. If you use a primary data collection, please follow the guidelines in the Research project unit. Please also keep in mind that you have to submit your dataset to your supervisor when submitting the proposal to allow him or her to check the feasibility of your dissertation. The methodology chapter Your methodology chapter will have a specific structure if you use secondary data: · Research philosophy: briefly locate your approach in a research philosophy (max. 2 pages, see dissertation unit materials for details). · Data access: describe in detail where you got your data from (organisation), how the data has originally been collected (representative for a specific population? stratified regarding specific aspects of the population?) and for what purpose. Include ethical considerations if necessary. · Data restrictions: describe all observations (rows) you have deleted and why, use the appendix if necessary. Describe if you use different samples of the data in your analysis (meaning with a different number of observations, for example on the individual-level and the team/ product -level) and conclude with the final number of observations. This number of observations needs to be used in all visualisations/ analytics. · Variable definition: describe how you clean or tidy (after the steps in data restrictions) and define or transform all variables in your analysis (includes reliability/ validity if applicable). Provide a table with the final data definition that you use in your dissertation (or specify in the text). Start with the outcome variables in detail, then the key explanatory variables and be brief with control variables. · Standard analytics methods: describe which statistical methods you use (tests, regressions, statistical learning algorithms). Show awareness of the possibilities and constraints of each approach for the interpretation of your findings. Standard approaches are approaches which we have introduced in the programme already. Indicate in methodology if you discuss constraints in the discussion chapter. · Additional analytics methods (optional): if you want to delve in methods that we haven’t covered in the programme yet, you can explain it here unless you described it in detail in the literature review. If you explore additional analytics methods, your methodology chapter will be much longer than in other MSc Management dissertations. Replicability : the dataset and the R script You need to submit the R script (or similar programme code when using a different software) that replicates all tables and figures in your dissertation. The R script needs to: · run un-interrupted after your supervisor adjusted the working directory and data call line (keep in mind you submitted the dataset as part of your proposal). · data restrictions and variable definitions should be easy to reconstruct and amendable by a proficient user in the software. · The tables and figures in your dissertation should be clearly signposted in the script (> #figure 1). Primary data collection If you want to collect your own data, please follow the processes described in the dissertation unit. Prepare your questionnaire before you start the ethics checklist. Plan for time for some discussion with your supervisor about the questionnaire. If you want to use questions about attitudes, intentions or traits (for example motivation, satisfaction or intentions to buy), please use validated questions from the academic literature (always entire sub-scales, avoid choosing some questions only, reference the original developer). You can request access to free online survey account (qualtrics) by emailing the unit leader or your programme coordinator. Keep in mind that you can always be asked to send your collected data to your supervisor (replicability of your study). Image Caption A survey does not need a separate participant information sheet and consent form. You catch both with the first paragraph of the questionnaire. Below is an example, please adjust accordingly: Datasets for dissertations Dissertations in the MSc Management with Business Analytics programme need to be quantitative but students can chose to opt for a primary or secondary data analysis. A primary data analysis is extensively explained in the dissertation unit material, handbook and dissertation unit workshops. A secondary data analysis might be the more relevant direction for the majority of MSc Management with Business Analytics students because secondary datasets typically entail a large number of observations which are necessary for many analytics methods. Please find links to a number of secondary data sources below. Why do we need a theoretical framework in an analytics dissertation? Each dissertation entails a literature review summarising what scholars have written about your research aim. The literature review includes a theoretical framework (or several) and a discussion of the empirical pattern of analytics studies that are related to your research aim. But why is a theoretical framework necessary? Is analytics not about understanding the pattern in the data? In a nutshell: the key difference between an analyst and a data scientist is that an analyst incorporates management theory and management practice into the data analysis. By combining management theory and management practice with statistical approaches, the analyst is able to understand the underlying business question, or research aim, comprehensively and beyond the available data. “There is nothing so practical as a good theory.” – Kurt Lewin Your research aim identifies an outcome variable which is the variable you want to understand, and the business want to improve such as productivity, sales, customer satisfaction, employee engagement, learning gains, equality or else. To understand how a business can influence the outcome variable, you turn to a theoretical model that explains the factors that drive the outcome variable (or explanatory variables that explain the outcome variable). These factors form your hypotheses which you can test in your own data analysis. Moreover, a theoretical framework also specifies assumptions under which the explanatory variables affect the outcome variable. These assumptions help you to understand under which conditions (or context factors) the explanatory variables influence the outcome variable. Finally, the literature review summarises the research of other scholars who analysed or tested the hypotheses with different datasets. This forms the `empirical pattern of analytics studies’ part in your literature review. The theoretical framework might summarise five variables that influence your outcome variable. But you might have only two of them in your secondary dataset. What do you do? Carry on, you are not a PhD and we expect you to run data analysis and discuss the findings but not to explain the world. Run your analytics model. But when you interpret and discuss the findings of your data analysis think again about the theoretical framework: how good is an analytics model which incorporates only two out of five relevant explanatory variables? What are the consequences for the performance of your statistical model? Statistical models are based on assumptions. If you miss an important explanatory variable, your point estimates and thereby your prediction or forecast might be biased. The bias might be severe or small and a good analyst, who understands the management theory and the statistical models, can infer if the results are reliable and to what extent. In contrast, the data science approach relies on the given data. Oversimplified, it does not question if the data is sufficient to analyse the business question. The traditional data science approach is based on correlations for which missing explanatory variables are less severe. In contrast, management questions are typically causal questions for which correlations alone are not sufficient