Intelligence presents an operation’s troves of data in digestible forms of spreadsheets and graphs. With the same troves, data analytics allow us to ask questions of operations for which intelligence cannot answer.
The articles of this webpage explain data analytics as being five types of questions that can be asked and answered of any operation. We are at a “new-age” because we could not do that until now—limiting us to intelligence which can only tell us what, when and where, but not why and how.
The five questions--explained below as five articles--are as follows:
Find What Matters by Asking Relationship Questions of Operations: The power of relationship questioning through regression models is to explore which and how strongly elements across the system of operational processes are related to outcomes and to each other. From the gained insight, firms are able to target the elements along its operations for which surgical change, improvement and assured compliance will be felt as earnings and return on investment. This article explains relationship questioning that improvement teams must know to ask and answer of processes, and the linear, logistic and Poisson regression models to do so.
Know that Improvements Work by Asking Difference Questions: Driving operational processes toward excellence depends upon being able to distinguish between true and false differences in a process’s outcome aspects after making improvements. We must be able to expect that the improvements made to process elements will have a significant impact and then be able to confirm that there is an impact. This article explains difference questioning of operational processes and the tools a team would put in play as it questions a process—two-mean comparison, one-way and multi-way ANOVA, ANCOVA, repeated-measures and mixed ANOVA, and MANOVA.
TIME SERIES QUESTIONS:
Explore What Did and May Happen with Time Series Questions: We make many decisions upon information which are reported sequentially at fixed periods—time series. The possibilities are productivity, KPIs, volumes, costs and many others. We hope to draw meaning from what happened and, in turn, either reconfirm or reset our expectations for what will happen. However, we must be able to clearly see any outliers and volatility, any cycles due to season or calendar, the shape, type and drivers of the series after removing any cycles, and true spread. This article explains time series analytics as the questioning that improvement teams would ask and answer of a process and the range of tools they would engage to do so—auto and cross correlation, decomposition, Holt-Winters, linear regression for series, ARMA and ARIMA.
Find the Time That is Money by Asking Duration Questions: Any operational process is a network of stages. An action item enters each stage and remains for some duration and then exits when the action is completed. The collective durations across the stages have a direct connection to the firm’s earnings and return on investment. The three facets of exploration are to view and evaluate the “baseline shape” of duration and exiting events in a stage, identify the process variables that are explanatory to the baseline shape and to look at duration with respect to multiple exiting events. This article explains how to ask and answer duration questions along the stages of an operational process and the tools of questioning—variously called duration, event history, and survival and hazards.
Dive Below the Surface of Process Functioning with Apparency Questions: What if we could dive below the surface of our operational processes? We would be able to ask questions of their functioning that are otherwise hidden to us—making the unapparent, apparent. We mine the firm's massive data to achieve three types of transparency—how the process is actually being worked, underlying subgroups to process measurements and underlying variables to captured variables. This article explains apparency questioning for operational processes and the tools the team will put into play as it questions the process—decision tree, regression tree, model tree and K-mean models.
Sources for self-directed learning: Discovering Statistics Using R, Field and Miles, 2012 | Multilevel Modeling Using R, Holmes, 2014 | Machine Learning with R, Lantz, 2015 | ggplot2, Elegant Graphics for Data Analysis, Wickham, 2016 | Introductory Time Series with R, Cowpertwait and Metcalfe, 2009 | Event History Analytics with R, Bostrom, 2012 | Package “tsoutliers,” Javier López-de-Lacalle, 2017