There’s been a rise in interest in recent years in Analytics – high powered data collection and interrogation, often associated with large-scale ICT systems. and the US gaming giant Caesars Entertainment are two notable exemplars of so-called ‘big data’.

However there’s another powerful, but often overlooked approach: using smart analysis of small data sets to unpack the drivers of performance and enhance business results.

The need for nimble, evidence-based decision-making is all the more acute at times of significant change, and with increasingly stringent demands from stakeholders (corporate head offices, funding bodies, boards, regulators etc.). And you don’t need tons of data to do it: often just a handful of data points will yield high-value nuggets of information that enhance decision-making and, ultimately, results whether they be in terms of customer service, efficiency or reputation.

As Douglas Hubbard asserts in his book How to Measure Anything: your problem is not as unique as you think; you have more data than you think; you need less data than you think; and an adequate amount of new data is more accessible than you think.

Common analytical techniques include: t-tests to establish whether a difference or change is statistically significant; correlation to find out which out of a range of things are linked and to what degree; and regression analysis which builds on correlations to show by how much something (such as customer satisfaction with speed of service) influences another (such as overall customer satisfaction) and how precisely that link can be estimated. Regression analysis is a powerful means of finding the critical few levers to pull to improve organisational results.

All of these tools are available and easily useable in Microsoft Excel’s Data Analysis add-in.

Here are four examples of their application:

1) not long ago I utilised a t-test to establish whether a change in business operations was associated with a statistically significant difference in performance;

2) I’ve used a correlation matrix to analyse customer satisfaction to drill down to the key attributes and to understand how these attributes related to each other;

3) I’ve used regression analysis to create cost curves that show whether per-unit costs are trending up or down as production grows, and whether unit costs are at their most efficient;

4) regression analysis can also be used to make operational decisions: I’ve used it to evaluate if there were negative impacts from the deferral of specific types of maintenance.

I’m enthusiastic about the possibilities of smart strategic analysis and the use of techniques such as these to solve business problems and enhance operational, financial and customer results.

I would welcome the opportunity to apply these techniques in your organisation: please call me on phone 0414 383 374 or email me at to discuss.

Kind regards,


© Michael Carman 2010-2018