Guest Post: It’s Tough to Make Predictions, Especially about the Future (even with Machine Learning)
At its core, all Machine Learning algorithms follow a two-part process. First a sequence of increasingly complex functions is fit to part of the data (training data set). Then each model in the sequence is evaluated on how well it performs on the data that was held out (the holdout set).
Guest Post: How quickly and effectively can you drive to a solution?
Deductive logic has been used for millennia to describe the natural world. With the explosion of data availability and machine learning, some suggest inductive reasoning will make deduction obsolete – the end of science. An approach that supports learning and drives toward a solution involves both.
Guest Post: Predictive Analytics Accelerates Problem Solving
Adam Russell, Global Operations Master Black Belt explains how Tate & Lyle deploys Continuous Improvement (CI) tools, including Minitab and Salford Predictive Modeler (SPM), to challenging engineering and manufacturing problems.
Vive la France! World Cup Bar Chart and Pie Charts Show Where Reader Loyalty Lies by Country and Industry
The World Cup has finally concluded with France becoming champion for the second time. Previously we polled The Minitab Blog readers on who they thought would win. Now, it’s time to look at the results and see how many of our readers have the ability of Nostradamus (Did I mention he’s French?).
Mulligan? How Many Runs Do You Need to Produce a Complete Data Set?
In our continuing effort to use experimental design to understand how to drive the golf ball the farthest off the tee, we have decided each golfer will perform half the possible combinations of high and low settings for each factor. But how many times should each golfer replicate their runs to produce a complete data set?
What Were the Odds of Getting into Willy Wonka's Chocolate Factory?
Tomorrow marks the 47th anniversary of the premiere of the great movie Willy Wonka and the Chocolate Factory. What would your odds be of getting a golden ticket? We used Chi-Square to find out.
A (Golf) Course in Design of Experiments
As we prepare for the inaugural Minitab Insights golf tournament in Scottsdale, Arizona on September 12, we are taking a look back at this series on using Minitab to improve our game. In this first installment, we examine how solving an age-old problem in golf is much like process engineering.
Power and Sample Size – Your Insurance Policy for Statistical Analysis
When we do statistical analyses, like hypothesis testing and design of experiments, we are using a sample of data to answer questions about all of our data. The reliability of these answers is affected by the size of the sample we analyze. To minimize the risk of doing unreliable statistical analysis we can use the Power and Sample size before collecting any data to determine how much data is needed to have a good chance of finding that effect, if it exists. The minimum recommended value for this is 80%.