This work is made available to you for free through a BY-NC-ND 4.0 Creative Commons license. You need to be signed in to access, which requires your acceptance of the terms of that license and our terms of use.
As we’ve seen, the goal in inferential statistics is to to reach conclusions and make decisions beyond the data you have available to you, which most often implies that you’re inferring something about a population based on a sample you took. In business, this might mean carrying out a marketing survey to infer something about the views or characteristics of an entire group of customers. In spatial applications, it might mean making some measurements with a sensor in order to infer something about its error characteristics (i.e. to calibrate it).
Descriptive statistics is key to making all of this happen because it allows us to calculate and clearly communicate measures (simple quantitative descriptions) that characterize the set of data we’re dealing with.
As you’ll learn in this module:
- We can use descriptive statistics to calculate a set of so-called descriptive measures (such as the mean, standard deviation, and other important measures). These are single numbers that help us describe, analyze, and communicate with others about the nature of our data.
- We can also calculate how ‘good’ those descriptive measures are using what we call standard errors (such as the standard error of the mean and the standard error of the standard deviation). In the context of inferential statistics, we will think of the standard errors we calculate as helping us quantify how well our descriptive measures describe the population parameters they’re meant to represent.
Examples and visual illustrations are provided in this module to bring these concepts to life and to help you build a strong intuition.
My own notes and the desired outcomes
I’m still assuming that you’re building your own “perfect set of notes” as you go through this material – to make sure you have a succinct reference to help you be efficient on a test or in your future work. So, I’m sharing my own notes here with you to help with that.
I’m also sharing the desired outcomes. As in our previous modules, there aren’t cast as true learning outcomes, despite the title. Rather, I want you to think of the second document below as a list of questions and actions you can use to check yourself as you go through the learning process.
The self-assessment problems
After the lessons below you’ll find some conceptual self-assessment problems to help you make sure you’ve got the fundamental concepts down. You’ll also find some applied self-assessment problems so you can round things out by putting your new knowledge to work.
If you’re taking this course from me as part of a university class then these self-assessments problems are the best way to study. I can’t ask exactly the same questions on a test, of course, but I do commit to you that I’ve designed the problems in a way that you can expect to do as well in the formal assessments as you can do on these self-assessment questions.
So, dig into these problems either after you’ve finished looking at the material or as you go. Hustle to figure out the answers. Leave no stone unturned. Get help if you need it. As with the notes, I’m going to assume you’re building the “perfect set of reference problems” to help you be efficient in a test or to look back at in practice.
Okay, now get started by clicking through the lessons below!
