The Key Aspects of Data Analysis And Decision Making - Essay Example

Data аnаlysis and decision-making Name Institution Quantitative Method: Hypothesis testing Executive summary Quantitative decision-making is directly linked with the method applied in analyzing the data. This paper looks at the hypothesis testing as the most effective method in statistical analysis of data associated with supply chain and logical management. The paper looks at the overview and justification of the method. There is also the identification of how the hypothesis testing method is applied by the decision makers to come up with an informed decision. The paper identifies the limitations associated with the method in the supply chain issue. There is also identification of different ways through, which the consequences of these limitations can be minimized. The paper ends with the summary or the conclusion of the paper content. Introduction Quantitative decision-making requires application of quantitative methods and statistical aspects that enhance analysis of a specific data. When an organization or a department is faced with a statistical issue, which requires decision-making, it has to apply the most effective statistical concept to enhance making of an informed decision. There are different quantitative methods or concepts that are applied in quantitative data analysis by the decision makers. Hypotheses testing is amongst them. The paper seeks to discuss the hypothesis testing statistical method of data analysis. The paper analysis the method; in relation to a supply chain and logistics management problem, which requires decision-making. The paper identifies how the method can be applied effectively by decision-makers in the issue. There is also discussion of the limitations of the method in having an informed decision, and ways through which the limitation consequences can be minimised. Overview and justification of the method Hypothesis testing is termed as the statistical process where the competing hypothesis are chosen in a probability distribution in relation to the distribution observed data. It is a common method in statistical data and enhances using of statistical language when testing different models. The choice of this method is because it is an effective statistical method in quantitative decision-making. The method also gives a chance for determination of evidence where a certain argument can be rejected or hypothesized depending with the evidence where there is belief of the hypothesis being true. It is a method, which allow different claims to be presented in the form of mathematical data (Matthews, 2011). Hypothesis testing is an efficient quantitative method because it allows the decision makers to look at different conditions related to a claim and test their evidence before making a conclusion. It enhances comparison of two or more hypothesis and in most cases, there is comparison of two hypothesis. The claim to be tested is labeled as null hypothesis / H0 and the claim trying to prove the major claim to be wrong is the alternative hypothesis/ H1 (Verma, 2013). Through comparison of the two and effort to prove the null hypothesis right, the decision makers manage to make an informed decision. This is a quantitative method, which enhances determination of the direction and focus associated with the research effort. The decision makers are forced to identify the importance of conducting the testing process of the claim and it allows a chance of determining the variables that are not efficiently considered in the particular issue. It also enhances reduction of confusion associated with proving of the claim to be true or false. i) Decision-making in supply chain and logistics management In the supply chain and logistics management, hypothesis testing is applied in decision-making. The supply chain entails creation of value to the products, creation of a competitive infrastructure, as well as measurement of the wider performance strategy for effective flow of goods and services. An effective supply chain is the one with the supply and demand matching, thus having perfect market. In the demand and supply chain, the organisations have to ensure creation of customer value and valuable product development (Flynn, Huo, & Zhao, 2010). Making of effective supply chain decisions requires the organization to be free from uncertainty conditions likely to be experienced in the market. When the supplier focuses on creation of value to the customers and the organizational stakeholder, this reflects to the supplier satisfaction because one manages to get good market return. There is expectation of collaboration and coordination among all the levels and members of supply chain. The demand is expected to be equal with the supply in order to have an effective supply chain management (Verma, 2013). It is widely realized that, for there to be a balance between the supply and demand, there has to be derivation of satisfaction for both the supplier and the buyer. ii) Demand and supply; Supply being higher that the market demand The organizational problem: The supplier satisfaction is influenced by the powers of the supply chain members, that is, the buyers and suppliers. This means that, for the supplier to gain the expected or necessary satisfaction, there has to be the issue of ensuring that all the supply chain members are also comfortable as they continue being in the market. In testing the influence of supply chain connections to the supplier satisfaction, there is the importance of applying the hypothesis testing as the most suitable statistical method (Wu, & Chuang, 2010). Application of the hypothesis testing method by decision-makers in this specific issue of supply chain performance having some effect on the supplier satisfaction is relevant. There is the need of analyzing the claim in a logical manner where the statement would stop being a narrative, but becomes translated in a logical way. Through the hypothesis testing, the decision makers manage to compare all the supply chain relationships with the supplier satisfaction. This is where they look at the level of relationship between all members if the supply chain and the issue of supplier satisfaction (Dougherty, Thomas, & Lange, 2010). The hypothesis is claimed to be that; if the supplier satisfaction is in a positive relationship with the cooperation of all the supply chain members, hence, there is a chance of development of a long-term relations. If the relationship is negative, the supply chain partnership is not expected to determine the future of the market. In the null hypothesis, the supply chain members get to a position of developing goodwill, commitment, and trust that enhance sustainability of the partnership. In addition, there is the argument of the supplier performance having ability to influence the supplier satisfaction (Wu, & Chuang, 2010). In order for the decision makers to reach a more informed decision in the context of this specific issue, the satisfaction has to be reflected to some factors. These factors include; profitability and economic return. It is clear that when the supplier is making enough and expected profit and get the expected economic return, the conclusion would be that the supplier satisfaction is influenced by the supplier performance. It also extends to development of customer satisfaction where once the customer receive what they wish to get from the market, they improve their demand, thus supplier improved performance and supplier satisfaction. The decision makers in this issue also require to compare the supplier satisfaction with the buyer performance in the market. This is where they test the linkage between the customer satisfaction and buyer performance (Liu, Ke, Wei, Gu, & Chen, 2010). It is widely realized that once the buyers are performing well, there is reflection on improved supplier performance, hence; supplier satisfaction. The decision makers also look at the linkage between the supply chain satisfaction and the supplier satisfaction. It is essential for companies to monitor the metrics of their supply chain performance more often. This enhances integration of the customer specification in relation to process control, cost control, customer quality, as well as design control. In order to understand the power of the supply chain and its linkage with the supplier satisfaction, the decision makers are would effectively apply the method of hypothesis testing (Wu, & Chuang, 2010). This is where they would test the issue of supplier satisfaction against all the four hypothesis statements before making an informed decision. The decision makers manage to interpret the claim of supplier satisfaction being influenced by the power of the supply chain. It becomes possible to prove the truth of the hypothesis or reject it depending with the evidence gotten by the decision makers. In making critical decision, the decision makers have to control their arguments after consideration of the evidence gotten through testing of the entire tested hypothesis (Ou, Liu, Hung, & Yen, 2010). The decision is supposed to be based on the null of the original hypothesis and conclusion to be made basing on the claim proving the hypothesis to be true. Hypothesis testing allows the decision makers to look at the probability of making some errors when putting a certain claim. (iii) Limitation The hypothesis testing method is associated with some methodological limitation type, which it is subject in relation to the issue of supply chain power and supplier satisfaction. There is the limitation of being allowed to test only 95%. When there is testing of over one alternative hypothesis, the surrounding evidence becomes unrealistic (Glöckner, & Betsch, 2011). If the null hypothesis is found to be true, the decision makers do not bother testing the other hypothesis, but they are considered to be false. When the testing is conducting using low values, the test statistics also becomes unrealistic. It is clear that hypothesis testing is mostly used in political science during discussion of some major problems. It fits better in the disciplines associated with social science since it is practically applied in the research of the political science field. The null hypothesis allows use of the p-values in making decision and reasoning about the claim (Poletiek, 2013). To make the claim appear in a mathematical way, the decision maker has to consider the P-values and take into account the relevant actions to be taken towards getting evidence towards the null hypothesis. The issue of type 1 error and type 2 error makes the conclusion from the hypothesis testing not much promising to the decision makers. The interpretation of the null hypothesis testing tends to confuse the decision makers because it does not give a room for wrong actions to be considered in whichever way (Fellouris, & Moustakides, 2011). The P-values used in the hypothesis testing devolve the conclusion of the hypothesis being significant or in other cases not significant. In this case, there is limitation of testing the entire hypotheses otherwise or proving them wrong. It sin apparent that the statistical significance identifies assessment of confounding and bias. It is evident that the approach of hypothesis testing does not allow appropriate investigation of the population structure. The management decision making can be made without protected evidence because of lack of adequate information. Minimisation of the limitation consequences In order to minimise these negative consequences of these limitations in the particular decision situation of the power of supply chain being linked with supplier satisfaction various steps should be taken (Wu, & Chuang, 2010). It is also necessary not to put all the trust in the results found from the hypothesis testing of the claim in order for the decision makers not to make irrelevant and unreliable decisions. The hypothesis testing method is associated with some methodological limitation type, which it is subject in relation to the issue of supply chain power and supplier satisfaction. There is the limitation of being allowed to test only 95%. When there is testing of over one alternative hypothesis, the surrounding evidence becomes unrealistic. If the null hypothesis is found to be true, the decision makers do not bother testing the other hypothesis, but they are considered to be false. When the testing is conducting using low values, the test statistics also becomes unrealistic (Albright, Winston, & Zappe, 2010). To avoid being mislead by the fact that the hypothesis testing is applied in the political science, the decision makers are supposed to understand the hypothesis and change it into mathematical analysis, which would make the issue to end. There should be conduct of the relevant and efficient actions, which are there to allow the decision makers to get effective evidence of the hypothesis to be tested. There should be clear investigation of the errors before making of the conclusion. In addition, there should be no consideration of the null hypothesis only, but the decision makers should consider even the errors and likely biasness (Wu, & Chuang, 2010). There should be conduct of thorough investigation of the hypothesis before conclusion and this should be accompanied with finding of adequate information. In this case of power of the supply chain members having influence to the supplier satisfaction, to minimize the consequences of the hypothesis testing limitations requires minimization of the bias through evaluation of all the involved hypotheses. There is also the need of ensuring that the sample size used r the hypothesis statement has minimal error. The time spent when investing about the evidence behind the null hypothesis should be maximum and efficiently set in a way that all the information would be investigated. It is also necessary to apply the random control trials, as this enhances minimization of the risks associated with confounding factors that are likely to influence the hypothesis testing results (Masson, 2011). When the rate of type II error is minimized, it becomes possible to work on truth detection, thus also reducing the probability of type I error. Before making conclusion that the supply chain members have an influence on the supplier satisfaction, it is important for the decision makers to predict a minimal error and put a chance for expectation of the nature of the prediction error. When there is a chance of doubt in the hypothesis, the conclusion of the hypothesis has to be halfway presented. Conclusion Data analysis enables the decision makers to make an effective and efficient decision regarding a certain statistical issue. There are different statistical methods used in making quantitative decisions. Hypothesis testing is one these methods and it entails testing of a hypothesis or a claim to get its evidence in order to make an informed decision. In the supply chain and logical management, hypothesis testing is effectively used to test the null hypothesis against other hypotheses. There are some limitations associated with this method and they include bias and error likely to be associated with the null hypothesis. It is necessary to increase the sample size and apply the randomized control trials to make the consequences of the hypothesis testing method minimal. References Albright, S. C. W. C., Winston, W., & Zappe, C. (2010). Data analysis and decision making. Cengage Learning. Dougherty, M., Thomas, R., & Lange, N. (2010). Toward an integrative theory of hypothesis generation, probability judgment, and hypothesis testing. Psychology of learning and motivation, 52, 299-342. Fellouris, G., & Moustakides, G. V. (2011). Decentralized sequential hypothesis testing using asynchronous communication. Information Theory, IEEE Transactions on, 57(1), 534-548. Flynn, B. B., Huo, B., & Zhao, X. (2010). The impact of supply chain integration on performance: A contingency and configuration approach. Journal of operations management, 28(1), 58-71. Glöckner, A., & Betsch, T. (2011). The empirical content of theories in judgment and decision making: Shortcomings and remedies. Judgment and Decision Making, 6(8), 711-721. Liu, H., Ke, W., Wei, K. K., Gu, J., & Chen, H. (2010). The role of institutional pressures and organizational culture in the firm's intention to adopt internet-enabled supply chain management systems. Journal of Operations Management, 28(5), 372-384. Masson, M. E. (2011). A tutorial on a practical Bayesian alternative to null-hypothesis significance testing. Behavior research methods, 43(3), 679-690. Matthews, W. J. (2011). What might judgment and decision making research be like if we took a Bayesian approach to hypothesis testing. Judgment and Decision Making, 6(8), 843-856. Ou, C. S., Liu, F. C., Hung, Y. C., & Yen, D. C. (2010). A structural model of supply chain management on firm performance. International Journal of Operations & Production Management, 30(5), 526-545. Poletiek, F. H. (2013). Hypothesis-testing behaviour. Psychology Press. Verma, J. P. (2013). Hypothesis Testing for Decision-Making. In Data Analysis in Management with SPSS Software (pp. 167-220). Springer India. Wu, L., & Chuang, C. H. (2010). Examining the diffusion of electronic supply chain management with external antecedents and firm performance: A multi-stage analysis. Decision Support Systems, 50(1), 103-115. Read More