Muses from The Lazy Statistician: How to use general analytic methods to solve specific analytical problems
The lazy statistician loves to adapt general frameworks that have broad application to a specific analytical problem. Why, you ask? Simple: a general framework is one where the assumptions are well understood, the tolerances for messy data are understood, and the framework usually delivers 90-95% of the value that a newer or more exotic analytical framework can provide. But the general framework can be set up much faster – call it the 90/10 rule – get 90 percent of the value with 10 percent of the effort when you use a general analytical method with broad application.
My current favorite “general framework with broad application” is SkuBrain, a supply chain management forecasting tool that rocks when it comes to creating SKU-level forecasts and order plans. We at Halo have “pivoted” SkuBrain to perform general ledger budget forecasting.
This “pivot” was a weekend exercise that required no mods or development – it was a simple matter of identifying a few constraints, working through those constraints by way of data prep, and finding that data prep was the fastest route to using a general framework with broad application. BTW, that is a core truth – when using a general framework with broad application, you may need to transpose your data. Fortunately at Halo, that’s easy.
Any other lazy statisticians out there who want to adapt SkuBrain for life sciences research and forecast outcomes at the level of the genotype? Simply array your data at the level of analysis that fits your needs. This could be down to patient-level forecasting of dose response curves based on day-over-day blood assays. Or discovering disease sub-types by grouping cases on other dimensions such as family history or responsivity to previous treatment protocols, and building sub-type forecasts that can be compared to actual outcomes. Pharmacosurveillance with SkuBrain – I like that.
How about financial services and creating branch-specific forecasts for bank deposit growth trends? Why not drill deeper, into branch representative-level forecasting and analysis of sales and customer satisfaction trends? Create an objective, data-driven assessment of where client-facing sales associates are exceeding todays goals, controlling for past trends. Then roll that report up to the branch and region, or dis-aggregate to the level of product – this is what SkuBrain plus a little data munging can do. Get a free trial of SkuBrain and see how easy to use it is, and get lazy.