Analytics with six sigma in 2021

Six Sigma with Analytics' Review

Introduction

Jian Liang: 

Currently ISU MBA program graduate student, before that received  Computer Science bachelor degree from China, good at math and business analytics.

 

Natawan Chaksangchaichot:

Currently, I am studying for an MBA with a concentration in the Business Analytics field from Illinois State University. I have some experience in the R program, SPSS, and basic knowledge of Python. I think coding is a future requirement skill that drives up potential business efficiency because we can apply the coding skill in market analysis, financial analysis, web development, and lean control.

Nichakorn Sukaviriya:

I am Nichakorn or Manow from Thailand. I am a graduate student in the College of Business with a focus on Business Analytics at ISU. I did Actuarial Science for my Bachelor's degree from a university in Thailand. I believe that the knowledge I have gained for the entire course will further my professional development and allow me to apply my skills, experience, and knowledge to this type of work.

Nichayakul Kumpong: 

My name is Nichayakul Kumpong and I am originally from Thailand. I did my undergraduate in 

Supply chain management from Thammasat University. When I was a third-year student, I’ve joined an internship program at Toyota Motor Thailand and learn Japanese working culture in the department of Manufacturing management and development which focuses on benchmarking and manufacturing development. 

What's the Six Sigma

Six Sigma is a kind of technology to improve the quality process management of enterprises. With the perfect business pursuit of "zero defect", it drives the quality to improve substantially, the cost to reduce substantially, and finally realizes the improvement of financial results and the breakthrough of enterprise competitiveness.

How Six Sigma can apply in data analytics

In the age of big data, data collection and analysis are easier than ever before. The company's problems center on how best to use the data -- even what to analyze in the first place. Lean Six Sigma helps in these areas. Combining continuous process improvement with the power of advanced data analytics provides an opportunity for organizations to improve operations, whether they are retailers seeking to optimize digital marketing campaigns or manufacturers seeking higher yields and better quality on the shop floor.

About the Course

Course Name: Data Analytics for Lean Six Sigma

Instructor: Dr. Inez Zwetsloot from University of Amsterdam

Purpose of this course

In this course, you will learn data analytics techniques that are typically useful within Lean Six Sigma improvement projects. At the end of this course, you are able to analyze and interpret data gathered within such a project. You will be able to use Minitab to analyze the data.

Who will be benefitted

From a business point of view, a manager could make a better decision based on the analyzed data. It could streamline processes and operations in a company to reduce waste and costs. An employee who enrolls in this course would get higher pay. Moreover, business students may study this course for the further benefit of their career. Finally, this course benefits everyone who likes to improve themselves.

Course Summary

Week 1

• The course starts with an introduction to the Lean Six Sigma Concept. DMAIC is the problem-solving approach that included five elements—Define, Measure, Analyze, Improve and Control. All these apply to improve an existing problem. The analytics phase can help to verify the effectiveness of action through control for quantifying the better result.
• In Lean Six Sigma terminology, this metric is called a CTQ, which helps find a property of a product or a service relevant to your project objective. We can set an assumption CTQ as a Y-variable, your dependent variable, or the outcome variable.
• The analytics process needs to start with the organization dataset, scanning a unit of measurement, variable, row, column, total time as observable cases. To obtain a representative sample, we can randomly select the items using a computer to make a random selection.
• Introduced a Minitab program as fundamental knowledge for advanced analytics.

Week 2

• Learn to know the importance of identifying the numerical or categorical variable for determines which tool you should use for the analytic phase. Numerical data are numbers, while categorical data are classes or categories. Descriptive statistics presented only for numerical data due to the observation based on mathematical operations. Descriptive statistics common practices as an outliner for calculation such as average, standard deviation, relationship in positive or negative. 
• Visualization for each type of variable is an essential thing to know the cross-border distribution in each variable. For numerical variables, we used a histogram to show the information of the distribution. A box plot shows the information about the spread of data and outliers. For categorical variables, we apply a pie chart or bar chart for spotting each category. 
•  Pareto Analysis is a statistical technique for deciding on limited number selection. This analysis is used for distinguishing the vital few causes from the many trivial tasks. It also helps to count the number of occurrences or weigh the significant effect related to production lost in each stop.
• To find the correlation between CTQ and other variables, we can use graph visualization to see the correlation between two variables. The appropriate graph depends on the types of variables. If both variables are numerical, we will make a Scatterplot. If the dependent variable is numerical and the independent variable is categorical, Boxplot is making more sense. Meanwhile, the dependent variable is categorical, and the independent is numerical. We might use a transposed Boxplot. If both variables are categorical, we can make a Stacked bar chart.

Week 3

• The concepts of population and sample, and how statisticians use a sample to make statements about the population. It should be done randomly to get a representative sample. Finally, we use this analysis to make claims about the entire population. 
• How to use estimates to approximate an unknown population parameter and calculate confidence intervals to quantify the uncertainty around the estimate via Minitab. The confidence intervals will give us boundaries in which a population parameter will lie with a certain level of confidence. 
• Types of probability distribution, which relevant to lean Six Sigma consist of normal distribution, Weibull distribution, and lognormal distribution. Learn how to use probability plot in Minitab to find a correct distribution that fits best with our dataset. 
• When we know this distribution, we can use the Empirical CDF to calculate percentages. Also, we will use the crosshair function or the percentile lines to find these percentages. However, the Empirical CDF is a useful tool in the analyze phase for Lean Six Sigma project. 

Week 4

• Learn to perform data analysis by using Minitab. Using a tree diagram to select the appropriate tool for the correct problem. Determine which variables are the dependent or independent variable. Also, determine whether they are categorical or numerical and determine which type of analysis method suits our data.
• Know the importance of creating a hypothesis which is a procedure to arrive at a decision. It will deal with uncertainty in a rational manner.
• Types of errors are discussed in this course, including wrong direction, time problem, third variable problem, and underlying variable problem. However, it could be avoided by performing a controlled experiment or using additional literature that explains to you the cause and effect relationship
• Types of data analysis technique for Testing numerical Y and categorical X including ANOVA (Analysis of Variance analysis), Kruskal-Wallis test (a nonparametric test), Two sample t-test, and Equality of variances test
• Know the importance of these techniques with different objectives, how to organize data, how to perform analysis, how to interpret and how to validate the conclusion using residuals analysis

Week 5

• Learn what statistical correlation is and how correlation can be used. Include what is the numerical interval of correlation index, how to determine the positive correlation, negative correlation, or no linear relationship between two variables according to the correlation coefficient, and how to determine the strong correlation and weak correlation. Finally, distinguish between linear and nonlinear relationships, and between correlation and causation.
• Explain what is regression analysis, under what circumstances are the independent variable X and dependent variable Y suitable for regression analysis, and outline the four steps of regression analysis.
• Explain how to perform the first two steps of regression analysis by using Minitab: 1. Fitted line plot and 2. Regression.  Learn how to make a fitted line plot, how to perform the main regression analysis, and how to interpret the output, including how to checking correlation,  the P-value of the correlation, how to conduct the hypothesis test, what the meaning of the R-squared value is, how the correlation p-value and R-squared value vary in the different scatterplot, and how to use the transfer function to make a prediction.
• The 3rd step of regression analysis. Explain why and how to perform a residual check to validate the result. Use Minitab to check if the residuals are normally distributed and if there are outliers or irregularities, then show the possible solutions for the non-normally distributed residuals or outliers.
• The last step of analysis regression. Explain when it is useful to calculate a prediction interval and how to use such an interval and interpret it in a correct way by using Minitab. This section also illustrates how to use crosshairs or the formula, to determine the required value of the influence factor.
• Explain when a quadratic regression is a suitable model, which makes it possible to study a curved line. Learn how to perform a quadratic regression by using Minitab and how to interpret the results. 
• A class exercise for getting a deeper understanding of the 4 steps of regression analysis.
• Explain when it is suitable to perform a Chi-square analysis: both Y variable and X variable are categorical variables. And how to perform and to interpret such an analysis. Illustrate 2 steps to perform Chi-square analysis by using Minitab: 1. Cross tabulation, 2. Chi-square analysis and p-value.
• Learn to perform a logistic regression and interpret the output by using Minitab. Know when to utilize logistic regression: Y variable is categorical and X variable is Numerical. Learn 3 steps to perform logistic regression:1. Enter data in event/trial format. 2. Make fitted line plot, 3. p-value

Conclusion

By this course of Data analytics with Lean Six Sigma, it is a valuable course. This has been proven to help improve business processes. Students can learn several statistical techniques for data analysis by using Minitab, along with a clear overview. The course has a very good structure and pace. Also, provides great examples of real situations, which makes students easy to understand. If you are looking to learn more about data analytics or refresh your knowledge of the basic components of Six Sigma. We would recommend this course as a perfect one.

Course Experience

    

In this course, you will learn to know about the technique of data analytics that can apply in Lean Six Sigma. You will learn about analyzing, data gathering, and interpreting from the small exercise and the example during the course. This course also provides a self-learning program name Minitab that helps you perform analysis via an online platform. This tool is easily used and followed because the course has not required any advanced knowledge in mathematics. You can understand by learning the simple tool for interpreting the outcome of Regression analysis, visualization, Anova. Moreover, this course also illustrates many problems that we might meet in the actual practice of Lean Six Sigma projects. The different problems that we learn to solved while taking a course. It helps to improve our analytics skills and technique that can apply in real-life situations, You will earn a worthy experience while taking that course. It enhances your analytic skill and improves your logic to identify a problem and find the best way to improve a project.

Recommendation for the course

Welcome to Data Analytics for Lean Six Sigma! You’re joining thousands of learners currently enrolled in the course. I'm excited to have you in the class and look forward to your contributions to the learning community.

To begin, we recommend taking a few minutes to explore the course site. Review the material we’ll cover each week, and preview the assignments you’ll need to complete to pass the course. Click Discussions to see forums where you can discuss the course material with fellow students taking the class.

If you have questions about course content, please post them in the forums to get help from others in the course community. For technical problems with the Coursera platform, visit the Learner Help Center.

Good luck as you get started, and we hope you enjoy the course!