Quantitative Analysis PDF

IT1807 What is Quantitative Analysis? It is the act of selecting a preferred course of action EV = P (X), where among alternatives (known as decision-making) are o EV = expected value crucial parts of any organization for decision-makers o P = pr...

IT1807 What is Quantitative Analysis? It is the act of selecting a preferred course of action EV = P (X), where among alternatives (known as decision-making) are o EV = expected value crucial parts of any organization for decision-makers o P = probability of an event should make careful evaluation of the different o X = amount to be received for a particular alternatives to determine the best alternative that would event work for the company. Sample Problem: A scientific approach to managerial decision making in Using decision-making under the condition of risk, find out which raw data are processed and manipulated to what alternative should be chosen, considering the table produce meaningful information is called quantitative that shows the assessed probability on each state of nature. analysis. Raw Data > Quantitative Analysis > Meaningful Future Sales Level information. Alternatives Low Moderate High Garbage In > Process > Garbage Out. Manufacture -30 20 110 Buy from local supplier 20 60 50 Buy from foreign supplier 10 45 80 Types of Data  Alphanumeric – combination of numbers and letters State of Nature Low Moderate High  Text – sentences and paragraphs used in written Probability 25% 60% 15% communication  Image – graphics, shapes, figures etc. Solution:  Audio – human voice and other sounds Alternatives Expected Value Manufacture (0.25) (-30) + (0.60) (20) + Decision Environments (0.15) (110) Applying the maximax strategy (maximum of the = -7.5 + 12 + 16.5 maximums or the "best of the best) – It involves = 21 looking at the best that could happen for each Buy from local (0.25) (20) + (0.60) (60) + possible course of action and then choosing/selecting supplier (0.15) (50) the action with the largest value. = 5 + 36 + 7.5 Applying the maximin strategy (maximum of the = 48.5 minimums or the "best of the worst") – It involves Buy from (0.25) (10) + (0.60) (45) + looking at the worst that could happen for each foreign supplier (0.15) (80) possible course of action and then choosing/selecting = 2.5 + 27 + 12 the action with the largest value. = 41.5 Applying the Laplace strategy – It involves calculating the average of each alternative and then The best decision therefore is to buy from local supplier choosing/selecting the alternative with the largest because it has the highest expected value. average. Applying Hurwicz strategy with α as coefficient of realism – It involves multiplying the best outcome in the row by the given value of α, multiplying the worst outcome in the row by 1-α, and adding the two (2) result together. Applying the minimax regret strategy – It involves computing an opportunistic loss (or regret) of each alternative by simply subtracting the entry from that of the highest column value and selecting the maximum regret value of each row. Finally, determine the decision by choosing the minimum/lowest regret. 01 Handout 1 *Property of STI Page 1 of 6  IT1807 The Quantitative Analysis Approach The Quantitative Analysis Approach Possible Problems in Defining the Problem 1. Defining the problem Conflicting Viewpoints Potential Pitfalls 2. Developing a model Impacts on other departments 3. Acquiring input data 4. Developing a solution Beginning assumptions 5. Testing the solution Solution outdated 6. Analyzing the result 7. Implementing the results Types of Model Possible Problems in Developing a Model Iconic Model Fitting the Textbook Model Analog Model Potential Pitfalls Understanding the Mathematical Model Model Acquire Data  Ordinal data involves some kind of order or scale (such as low to high or high to Types of Data low) relationship among the variable’s observations. o Qualitative data – It is about attributes and properties; information that can't actually be Methods of collecting qualitative data measured. It is concerned with the data that is observable in terms of smell, appearance,  Focus Group - It is an open discussion taste, feel, texture, gender, nationality and so group of about 6- 8 participants led by a on and is represented either in a neutral moderator or facilitator. verbal/narrative format. Kinds of Qualitative Data  Nominal data involves naming/ identifying a thing without assigning it to an implicit or natural value or rank. 01 Handout 1 *Property of STI Page 2 of 6  IT1807  Observation - It is the process of o Quantitative data - It is the data that can be gathering open-ended, firsthand measured and expressed in numerical terms. information by observing an object or a It is concerned with measurements like height, phenomenon in a certain way. weight, volume, length, size, humidity, speed, age etc. The tabular and diagrammatic  Interview - It is a purposeful discussion presentation of data is also possible, in the between two (2) or more people by form of charts, graphs, tables, etc. Further, the asking questions directly from quantitative data can be classified as discrete respondents, either face-to- face or by or continuous data. telephone. Structured Kinds of Quantitative Data Semi-structured Unstructured  Discrete data reflects a number obtained by counting. Typically, it involves integers.  Archival Materials – This involves  Continuous data could be divided and materials such as newspapers. reduced to finer and finer levels. The number of decimal places depends on the precision of the measuring device. Classification of Quantitative Data  Experiments and Observational Study o An experiment study deliberately  Interval data is a data which not only assigns subjects to various classifies and orders the measurements, treatments for studying the reasons but also specifies the exact differences for changes in the output between the values. response(s).  Ratio data tell us the exact value between o An observational study collect data units and also have an absolute zero. in a way that does not directly interfere with how the data arise, i.e. Methods of collecting quantitative data merely "observe".  Survey  Observations and Interviews It is used to collect/gather information from a group of people by employing printed questionnaires mailed to large samples, though it can also be done through the telephone. Possible Problems in Acquiring an Input Data Accounting Data Accounting data is usually sensitive data such as cash flows and turnovers, hence, it is not open for public research. Some cost data requirements needed by an analyst was never collected in the Using Accounting first place, hence, analyst may find it hard to Data obtain. Potential Pitfalls Validity of Data Validity of Data We tend to manipulate data according to our own purposes to make it look “good and clean”. Yet, the validity of results rest on the validity of the input data. 01 Handout 1 *Property of STI Page 3 of 6  IT1807 Develop a Solution The next step is developing the solution. This requires manipulation of the model variables in order to determine the solution that is practical and can be implemented. Manipulation can be done by: Solving equations Trial and error Complete enumeration Using an algorithm Analyze the Results and Perform Sensitivity Analysis Analyzing Data - It involves examining the collected information in ways that reveal the relationships, patterns, trends, etc. that can be found within it. Sensitivity Analysis - It allows a series of “what-if” questions to be answered for it determine possible changes in the various parameters of the original problem. There are two (2) potential roadblocks that quantitative analysts face in developing a solution. Hard to understand mathematics - There is a false notion in us that if someone thinks complicatedly or elaborately thinks well. That is not the case always, mathematics always shuns a lot of people even managers. Only one answer is limiting - QA models tend to give one solution to a problem. One way to offset this is to come up with alternative scenarios or sensitivities to give managers options to choose from. In this way other non-quantitative factors may be considered and the cost implication of deviating from the optimal solution is known. Planning and Conducting Surveys 1. Determine the goal of your survey: Simply put, what do you hope to gain from your survey? The questions you ask all need to point back to this essential idea. For instance, we want to construct a survey that shows which roads have the worst traffic conditions. The goal of the survey is to find the answer to the question: “Which spots in Metro Manila have the worst traffic conditions?” 2. Identify the sample population: Simply put, whom will you interview? Using the example above, a sample of the population would include a random sample of commuters and motorists spending more than an hour, on average, in traffic every day. 3. Choose which of the following methods to use to collect valuable information with the survey: a. Meeting the respondents in person b. Contacting the respondents through the telephone c. Conducting surveys through completing a survey on paper and mail it back d. Conducting online surveys through the Internet 4. Decide what questions to ask in what order, and how to phrase them: This is important if there is more than one piece of information you are looking for. 5. Conduct the interview and collect the information. 6. Analyze the results by making graphs and drawing conclusions: Now that the data has been collected, suitable graphs can be made to show the results to other people in the best possible way. 01 Handout 1 *Property of STI Page 4 of 6  IT1807 Planning and Conducting Experiments The practical steps needed for planning and conducting an experiment include: 1. Experiment Idea (Recognition of the goal of the experiment) Record (i.e. write down) specific question or problem that you are trying to explain or solve in an experiment using the language of cause and effect relationship. 2. Experiment Planning Gather information about the problem/question to know something about it. This includes personnel and the environment, for example, whether the experiment is run in a university environment with students or in an industrial setting. Moreover, a possible answer to the problem or question is predicted. The next step is to determine the following variables: Independent Variables (aka Experimental Factors, Controllable Factors) - It is the factor that causes a change in the dependent variable. It can be thought of as an intervention or a treatment. Dependent Variables (aka Classification Factors, Uncontrollable Factors) - It is what we hope to change through the experiment. This is the “effect” in cause and effect relationship. Experiment Designs: Completely Randomized Design - This is when each person or object upon which the treatment is applied is assigned to a treatment completely at random. Matched-pair Design - This is when the person or object upon which the treatment is applied are paired up and each of the pair is assigned to a different treatment. Randomized Block Design - This is used when the person or object upon which the treatment is applied are divided into homogeneous groups called blocks. Within each block, the person or object upon which the treatment is applied are randomly assigned treatments. Validity Evaluation: Internal validity - It occurs when causal relationship between the variables being studied can be determined. A danger is that changes might be caused by other factors. It is related to the design of the experiment, such as in the use of random assignment of treatments. External validity - It occurs when conclusions can be generalized to other people, times and contexts. Construct validity - It demonstrates that the assessment is actually measuring the quality of an instrument or experimental design. Conclusion validity - It occurs when a relationship of some kind between the two variables being examined can be found. 3. Experiment Operation Preparation - It is concerned with preparing the subjects as well as the material needed (e. g., data collection forms). The participants must be informed about the intention; we must have their consent and they must be committed. Execution - It is concerned with ensuring that the experiment is conducted according to the plan and design of the experiment, which includes data collection. Data Validation - It is concerned with ensuring that the actual collected data is correct and provide a valid picture of the experiment. 4. Analysis and Interpretation Descriptive statistics provides information about the properties of the produced data and allow readers to understand important things about it from a single glance. Data set reduction Hypothesis testing allows us to estimate how likely it is that our results were produced by chance rather than a genuine experimental effect. 5. Presentation and Package This includes primarily documentation of the results, which can be made either through a research paper for publication, a lab package for replication purposes or as part of a company’s experience base. 01 Handout 1 *Property of STI Page 5 of 6  IT1807 References: 1.3 - Steps for Planning, Conducting and Analyzing an Experiment (2018) Retrieved from: https://onlinecourses.science.psu.edu/stat503/node/7 Agricultural economic analysis unit 3 - decision methods decision making under uncertainty (n. d.) Retrieved from: http://www.shsu.edu/law001/site/u3m3p6.html Arao, R., CoPo, A., Laddaran, A., Mejia, L. & Villanueva, A. (2014). Quantitative approaches in decision making with computer application and case study analysis. Sampaloc, Manila: Rex Book Store, Inc. Chapter 1 Introduction to Quantitative Analysis (2006) Retrieved from: https://view.officeapps.live.com/op/view.aspx?src=http%3A%2F%2Fwps.prenhall.com%2Fwps%2Fmedia%2Fobjects%2F2497%2F2557002%2Fppt%2F qntmeth9_ppt_ch01.ppt Data and information (2014) Retrieved from: https://www.slideshare.net/buxooabdullah/data-and-information-33807344 Decision making under uncertainty (2018) Retrieved from: https://www.wisdomjobs.com/e-university/quantitative-techniques-for-management- tutorial-297/decision-making-under-uncertainty-10067.html Decision theory (n. d.) Retrieved from: https://people.richland.edu/james/summer02/m160/decision.html Deshpande, S., Gogtay, N. & Thatte, U. (2016). Data Types Retrieved from: http://www.japi.org/june_2016/09_sfr_data_types.pdf How to Conduct a True Experiment (n. d.) Retrieved from: https://www.wikihow.com/Conduct-a-True-Experiment Observational studies and experiments, sampling and source bias (2015) Retrieved from: http://researchhubs.com/post/ai/data-analysis-and-statistical- inference/observational-studies-and-experiments-sampling-and-source-bias.html Planning and conducting surveys (2018) Retrieved from: https://www.ck12.org/statistics/planning-and-conducting-surveys/lesson/Planning-and- Conducting-Surveys-ALG-I/ Qualitative v. quantitative data (2018) Retrieved from: https://www.shmoop.com/probability-statistics/qualitative-quantitative-data.html Rawat, S. (n. d.). Decision-making under certainty, risk and uncertainty Retrieved from: http://www.businessmanagementideas.com/decision- making/decision-making-under-certainty-risk-and-uncertainty/3371 Render, B., Stair, R., & Hanna, M. (2011). Quantitative analysis for Management (11th ed.). Upper Saddle River, New Jersey: Pearson Education, Inc. Round function (n. d.) Retrieved from: https://support.office.com/en-us/article/round-function-c018c5d8-40fb-4053-90b1-b3e7f61a213c?ui=en- US&rs=en-US&ad=US Section 1.6: The Design of Experiments (n. d.) Retrieved from: https://faculty.elgin.edu/dkernler/statistics/ch01/1-6.html Section 2.1 ~ Data Types and Levels of Measurement (2014) Retrieved from: https://www.slideserve.com/waseem/section-2-1-data-types-and-levels- of-measurement Statistics How To (2018) Retrieved from: http://www.statisticshowto.com/experimental-design/#Validity Surbhi, S. (2016). Difference between qualitative and quantitative data Retrieved from: https://keydifferences.com/difference-between-qualitative- and- quantitative-data.html Syllabus B: Decision-making Techniques (2018) Retrieved from: https://www.acowtancy.com/textbook/acca-f5/b6-dealing-with-risk-and-uncertainty- in-decision-making/maximax-maximin-and-minimax-regret/notes Taylor, C. (2018). How to move a chart onto a new sheet in excel Retrieved from: http://smallbusiness.chron.com/move-chart-onto-new-sheet-excel- 28703.html Telephone Survey Pros and Cons (n. d.) Retrieved from: http://www.thewhetstonegroup.com/resources/lead/Telephone%20Survey%20Pros%20and%20Cons.pdf Understanding qualitative, quantitative, attribute, discrete, and continuous data types (2018) Retrieved from: http://blog.minitab.com/blog/understanding-statistics/understanding-qualitative-quantitative-attribute-discrete-and-continuous-data-types Wile, E. (2017). Advantages & disadvantages of online surveys Retrieved from: https://bizfluent.com/list-6763255-advantages-disadvantages-online- surveys.htm 01 Handout 1 *Property of STI Page 6 of 6