Stage 2: Master Linear Modeling

I see most researchers struggling with statistical analysis at this level. And you’ll see it’s a big one.

As is true at each stage, this one is composed of three components.

  1. Statistical Knowledge: Linear Models in its Entirety
  2. Data Analysis Skills
  3. Software Skills: One Statistical Software Until its Easy

Luckily, they go together, so it’s not like you’re working on three separate paths.

But you could focus on one if you find you were weaker there.

Once again, you are likely to be at Stage 2 in one of two situations:

  1. You’re just starting out and just worked your way up to Stage 2 from Stage 1.
  2. You have done some work in Stage 2, but also some at Stage 3 or 4. It feels like you’re past linear models, but you have holes in your knowledge or skills.

So for example, you are doing a (Stage 3) logistic regression and still aren’t sure how to interpret interactions.

Or you’re working on a (Stage 3) linear mixed model and are not sure exactly how to decide which fixed effects to keep in your model.

Interpreting interactions and model building are both Stage 2 skills. They both get harder in those Stage 3 models, so learn them here.

We’ve created a LOT of resources at Stage 2 because this is where we see the biggest benefit to most data analysts.

Statistical Knowledge: Linear Models in its Entirety


The fundamentals of linear models were part of Stage 1. But linear modeling is a huge topic and it can get quite sophisticated. Stage 2 includes all the tricky parts of analysis of variance, analysis of covariance, and linear regression, including:

  • dummy and effect coding of categorical predictors
  • interactions
  • quadratic, polynomial and non-linear effects
  • model building
  • checking assumptions and knowing what to do if they’re not met
  • centering, rescaling, and standardizing variables
  • calculating and reporting effect sizes
  • interpreting means, graphs, and coefficients
  • how to deal with data issues like missing data, censored or truncated data, outliers and influential points, and multicollinearity
  • model fit and model fit statistics
  • multiple comparisons
  • contrasts
  • effect size statistics

We have a ton of resources to help you learn all aspects of linear models. They can all be found on these two resource pages:

One Statistical Software Until it’s Easy


Now that you’re beyond the software basics, you want to take your statistical software skills to the next level. It doesn’t really matter which one you use at this point. But whichever you pick, learn it well so that it’s not a struggle every time you boot it up.

Click on any of the icons to find a ton of resources to help you.

Data Analysis Skills


Data analysis skills fall into four categories:

1. Planning the Data Analysis

Planning includes everything from study design to sample size estimates to writing a data analysis plan.

2. Working with Data

This is often called data manipulation, but that sounds a bit nefarious. This includes setting up the data set in the right format, merging data sets, coding and recoding variables, computing new variables, etc.

3. Running the data analysis

Even with the statistical knowledge of what your model means and which statistical test to do and with the software skills to run it, there are still a lot skills involved in running a data analysis. They include:

  • how to explore the data and what to look for
  • the order in which to do things so you don’t have to re-do a lot
  • how to read the output and make decisions based on it
  • how and when to apply rules of thumb to analyses
  • what to do when your data don’t behave like a textbook says they should
  • best practices for organizing and structuring files, syntax, and data so you can reproduce the analysis a year from now

4. Presenting and Communicating Results

Not only does this include graphing and creating tables, but writing up results that your audience understands.


Master these for linear models and everything you learn at Stages 3 and 4 will be much, much easier. There are resources to learn these skills here:

Data Analysis Practice and Skills Resource Page