1 CLO Business Decision Making Project Part 1 Sales Decline at McDonalds Inc. LaShondra Oglen QNT/275 1/25/16 Professor Robert Robinson 2 CLO Business Decision Making Project Sales Decline at McDonalds Inc. This was an interesting assignment and after much thought, the company I selected is McDonalds. McDonalds is the world's largest chain of fast food restaurants serving numerous nations across the world. McDonalds restaurant are operated in terms of franchisee, affiliate or the cooperation. The company gains revenue from rent, fees and royalties from its franchises and sales from its operated stores. The company offers different products including hamburgers, chicken, French fries, milkshakes and desserts among many other items. Based on the policy of the company, McDonalds does not make any direct sales of food products instead organizes and supports the supply of food to restaurants through legalized third party operators. Sales Decline Problem McDonald revenue fell by 11% in the first quarter of 2015, which reflects the adverse sales fall experienced. The company is struggling to improve its sales due to the negative forecasts among its segments. The management of the company is always seeking to improve the competitiveness of the company towards meeting the consumer's needs. This would help in improving the overall sales growth and performance (Ritchie, Lewis, Nicholls & Ormston, 2013). The newly introduced menu items and promotions failed to attract new customers from its competitors. For example, its stores in France and 3 Russia failed to offset the competition in the UK. This has forced McDonald to close some of its underperforming restaurants in U.S and China. Research Variable One research variable is units of sales revenues sold by the company. Sales revenues are an important variable, which proves effective in understanding the nature and implications of the sales decline problem. The understanding and research on the amount of the sales revenue will be useful in understanding the problem facing McDonalds Inc. The sales variable is an independent variable, which depends on other variables including the promotion levels and success of marketing campaigns. Thus, the understanding of the variable is critical in promoting the overall research of the sales decline problem. Methods of Data Collection In the collection of data for the research, the research will rely on both the qualitative and quantitative research methods. This will help in collecting both qualitative and quantitative data for the variables. The qualitative research data involves the information, which is not in numerical form. This could be collected through open-ended questionnaires, unstructured interviews and observations. Qualitative data involves the descriptive data, which helps in analyzing the quantitative data appropriately (Hair Jr et al., 2015). The qualitative method is useful in studying the sales declines problem from 4 the individual stores level and perspective. This becomes increasingly important since the company will be able to directly obtain issues influencing the reduced sales in the stores. Without having a strong perception about the issues affecting sales at the individual stores level, it would be difficult to understand the overall perception of the general problem of the sales decline. In addition, the collection of the quantitative data will give the researchers numerical form data, which is organized in different units of measurements. The sales variable data obtained could be organized in designed graphs, or tables with the raw data and figures. Conducting experiments on the sales would obtain quantitative data, which could be used to understand the research problem of sales decline. Therefore, it is critical to conduct mixed quantitative and qualitative research methods and data to understand the research problem of declined sales. Validity and Reliability of Data To determine whether data collection methods would generate valid and reliable data, the evaluation methods become very important. The reliability assessment helps to assess the degree which the methods will produce consistent results and findings. The researchers will have to conduct test retest reliability, parallel forms of reliability and inter rater reliability tests which are important in assessing the degree to which the different researchers relies on the data and how they agree on the reliability of the data and information collected. 5 In terms of validity, the researchers should rely on the different validity tests and assessment programs to validate the data and information. These include face validity, construct validity, formative validity, and sampling validity. The researcher could rely on the tests to determine the validity of the data and information (Bryman & Bell, 2015). To understand whether the data is reliable and valid, the researcher will observe whether the research data aligns to the subject matter of the research concerns of sales decline at McDonalds. 6 References Bryman, A., & Bell, E. (2015). Business research methods. New York, NY: Oxford university press. Hair Jr, J. F., Wolfinbarger, M., Money, A. H., Samouel, P., & Page, M. J. (2015). Essentials of business research methods. London, UK: Routledge. Ritchie, J., Lewis, J., Nicholls, C. M., & Ormston, R. (Eds.). (2013). Qualitative research practice: A guide for social science students and researchers. London, UK: Sage. 1 CLO Business Decision Making Project Part 2 Sales Decline at McDonalds Inc. LaShondra Oglen QNT/275 2/01/16 Professor Robert Robinson 2 CLO Business Decision Making Project Part 2 Descriptive and Inferential Statistics There are generally two types of statistics in data, descriptive and inferential statistics. Descriptive statistics represent the facts related to the sample or population like mean, mode, median and standard deviation. Inferential statistics reference how a population is drawn based on the descriptive statistics of a sample. In inferential statistics, the null hypothesis is a generic statement that there is no evidence to establish a relationship among two measured phenomena, or when there are not any differences among groups. Types of Inferential Statistics Statistics provides large amounts of research data to grow viewpoints of individuals, presenting them with new ideas and data. It drives individuals to think fundamentally and offers them the ability to be creative. It assists their learning by enhancing maintenance through engagement. There are several types of inferential statistics which are helpful in analyzing data. Hypothesis testing is very common. It is the use of statistics to determine the probability that a given hypothesis is true. Hypothesis testing is a method of observing and utilizing data related to single and to multiple fields. 3 The process of hypothesis testing consists of several steps. 1. Defining the research hypothesis 2. Stating the null hypothesis 3. Collecting data 4. Analyzing each variable 5. Conducting appropriate statistical tests 6. Accepting or rejecting the null hypothesis 7. Deciding critical value based on confidence intervals 8. Explaining the results and findings The level of significance indicates how confident we are in research on the basis of inferential statistics. For example, if our case level of significance is 95%, which shows that there is a probability the null hypothesis is less than 5%, we reject the null hypothesis. If the probability of null hypothesis being true is greater than 5% we do not reject null hypothesis. On the other hand, P value in inferential statistics is the probability of null hypothesis being true. If the p value is less than the level of significance, we reject the null hypothesis and if p value is more than level of significance we do not reject null hypothesis. 4 Confidence Intervals Confidence intervals are ranges of value which describes the probability of occurring a point estimate. In statistics, one goal is to try to deduce the value of population parameter from sample estimate. We cannot be sure that the population will have similar parameters as a sample, therefore we approximate the characteristics of population parameters on the basis of sample properties. We require confidence intervals, which gives us the probability of a point estimate lying in particular range. Probability in Business Decision Making There are various tools, technology and trends which make the probabilistic approach useful for organization. Recently, the role of the probabilistic approach has become important due to emerging technologies like big data. As the role of data driven decisions have increased in organizations, the role of the probabilistic approach has taken center stage. Various tools like SAS, SPSS, R, and Python make uses of the various probabilistic approach in order to build predictive and analytical models which are widely used by firms. These firms use the data to drive their decisions and helps them in achieving their strategic goals. There are various social media trends, like text analytics 5 which help firms in building strategies to acquire and classify their customers by making use of probabilistic approach. For example, McDonalds uses its data bases to make strategic decisions. McDonalds has database of customers, their buying behavior, buying frequency and their buying patterns. This database can be used to segment its customers into various clusters using big data technology by using suitable tools like R by implementing clustering algorithms in R. They also display advertisements on their social media platforms based on their previous buying patterns. The Role of Linear Regression for Trend Analysis Linear Regression is the process of establishing a linear relation between to variables. In regression, the ordinary least square method is used to establish linear relation between two variables. Equation of linear Regression is Y = + i * Xi + Here Y is dependent variable Xi = Independent variables = Independent variables i = Covariance ( Y, Xi ) / Xi 6 The null hypothesis of regression is that the independent variable does not significantly affect the dependent variable or = 0. The alternate hypothesis is the independent variable does not significantly affect dependent variable or 0. Also, the Accuracy of Regression Model is judged by its r square value which explains percentage variation in dependent variable explained by independent variables. Therefore, regression can be applied toward a broad range of fields and subjects. For example, it can be used in the health care industry to find the cause of a disease or the effectiveness of a vaccine. It can also be used for business purposes to forecast sales in a firm or in the stock market to predict returns from investments, depending on economic conditions. Time Series Time series analysis is used to analyze the data which varies with a time. Time series analysis comprises methods for analyzing time series data in order to extract meaningful statistics and other characteristics of the data. Time series forecasting is the use of a model to predict future values based on previously observed values. Time series analysis can be applied to real-valued, continuous data, discrete numeric data, or discrete symbolic data. There are several techniques for time series analysis, just as there are various methods of forecasting sales, such as nave forecasting, exponential smoothening and Regression analysis. 7 References Berenson, M., Levine, D., Szabat, K. A., & Krehbiel, T. C. (2012). Basic business statistics: Concepts and applications. Pearson Higher Education AU. Croxton, F. E., & Cowden, D. J. (1939). Applied general statistics. http://www.who.int/childgrowth/publications/obesity_risk/en/ LaValle, S., Lesser, E., Shockley, R., Hopkins, M. S., & Kruschwitz, N. (2013). Big data, analytics and the path from insights to value. MIT sloan management review, 21. https://en.wikipedia.org/wiki/Time_series