Setting Goals: Predicting Goal Attainment Likelihood
You’ve chosen your goals carefully, ensured you can measure success and broken then down so everyone on your team knows what they need to do to help achieve them. Well done! Now you’ll start to wonder whether you are likely to achieve those goals as the coming weeks and months go by.
The future is unpredictable, so estimating the likelihood of achieving a goal is based in probabilities instead of exact mathematics. Since you’ve tied your goals back to specific metrics, when we think about goal attainment we are thinking about how likely the metric is to achieve the value in the goal. Typically, you will express the likelihood as a prediction interval which is a range of possible values that have a high probability of including the final metric value.
For example, if your goal is to increase Revenue by 10% to $2M by January 1st, you might report on goal attainment by saying that Revenue is likely to fall between $1.7M and $2.1M with 95% confidence. How do you determine that range? Let’s look at it on a chart:
As you can see, the value of your metric (in this case Revenue) is known through today. Your job is to project estimated values for Revenue into the future, and the value of those projections at your Deadline are the confidence interval for your goal. How do you create that projection? You create two different projections: a low and a high projection and together they form the projection range.
Creating those low and high estimates can be tricky depending on your data. The simplest method is to use a simple line, where the lower projection might predict slow growth (maybe 1% per week) and the upper projection predicts fast growth (maybe 10% per week). A more advanced method is to run linear regressions with different values that expect faster or slower growth. The more predictable your business, the easier it will be to create this projected range and the narrower (and more accurate) it will likely be.
How do you know that your prediction interval is 95% accurate? That is harder to do. Obviously, you are 100% confident that revenue will fall between $0 and $1B. It will be up to you to determine what reasonable assumptions give you a 95% confidence in your range, or what confidence level might make sense. There are mathematically rigorous ways to calculate the prediction interval if you do use a regression analysis which I don’t have time to get into here but are very interesting.
When you are done, you can report on a regular basis the likely range of values the goal metric will have when the goal deadline arrives. This will give you a good way to know if you are on track to reach your goals, or if you need to change your approach along the way!
This week we’ve reviewed some of the basics of goal setting and goal management, I hope you feel better equipped to choose the best goals for your company. Remember that goal setting is an art that depends on your business, your people and your needs. The more thought you put into them, the more likely you will get to your desired destination!
Quote of the Day: “A goal is not always meant to be reached, it often serves simply as something to aim at.” – Bruce Lee