When you have several candidate factors and want to see which ones actually change your results, use a main effects plot. It draws a simple line for each factor, connecting the average response at each level. If a line is steep, that factor has a significant impact on your outcome.
Understanding Variable Impact
A main effects plot provides an immediate visual summary of your data by averaging your response for every level of your chosen factors. By plotting these averages as points and connecting them with a line, Lattice allows you to see the trend of each factor at a glance.
Because this method uses simple arithmetic means, it remains easy to interpret regardless of the underlying statistical complexity. It is designed to act as a primary screening step, helping you prioritize which factors deserve further investigation in your optimization workflow.
Visualizing Multiple Factors
You can analyze up to six factors simultaneously. The platform generates a series of subplots—one for each factor—all presented against a common overall mean reference line. This reference line helps you judge whether the average response at a specific level is higher or lower than the grand average of your dataset.
By comparing the slopes of the lines across these subplots, you can quickly differentiate between factors that drive significant change and those that appear to have a negligible effect on your outcome.
Data Integrity and Reliability
Lattice prioritizes the accuracy of your raw data. Rather than performing hidden transformations or automatic data cleaning, the platform uses your original inputs to generate the chart. If there are inconsistencies or issues with your data distribution, the system will provide clear warnings rather than modifying your numbers.
This approach ensures that what you see on the chart directly reflects the reality of your experiment. You can trust that the trends displayed are based on your actual observations, keeping your process transparent and fully traceable from start to finish.
1 · Intent → method
An LLM picks svt_plot_main_effects from a fixed catalog.
2 · Method → numbers
Deterministic Python engine runs the math. Same input → same output.
3 · Numbers → plain language
A second LLM translates the result into your domain’s vocabulary.
What does a steep line on a main effects plot tell me?
A steeper line indicates a larger change in your response across the different levels of that factor. This suggests that the factor is an important driver of your results, whereas a flat or horizontal line suggests that the factor has little to no impact.
Can I use this if I have missing data in my variables?
Yes. The main effects plot uses a per-factor removal strategy, meaning it ignores missing values for each specific factor being analyzed without discarding your entire dataset. Each factor’s line will be calculated based on the available data for that specific category.
Tool input schema
Schema for svt_plot_main_effects not exported yet (run pnpm export:registry).