Reading the result
The line is written y = ax + b, the same form the TI-84 prints for LinReg(ax+b). The slope a is how much y changes for every 1 that x increases, and the intercept b is where the line crosses the y-axis — a number that only means something if x = 0 is realistic for your data.
| |r| | Fit | What to do |
|---|---|---|
| above 0.9 | Strong | A straight line describes the data well |
| 0.5 to 0.9 | Moderate | Usable, but look at a scatter plot before trusting predictions |
| below 0.5 | Weak | Consider a quadratic or exponential model instead |
Doing it on the calculator
Enter your x values in L1 and y values in L2 with STAT → 1: Edit, then press STAT, arrow to CALC and choose 4: LinReg(ax+b). If r and r² are missing, turn diagnostics on first. Every menu item is listed in the manual, and you can try it in the simulator.
Frequently asked questions
Why does my TI-84 not show r and r²?
Diagnostics are switched off by default. On OS 5.x press MODE and set STAT DIAGNOSTICS to ON. On any model you can instead press 2nd then 0 for CATALOG, scroll to DiagnosticOn and press ENTER twice. Run the regression again and both values appear.
What is the difference between r and r²?
r is the correlation coefficient, between −1 and 1, and its sign tells you whether the line slopes up or down. r² is that value squared, so it is always positive, and it tells you what share of the variation in y the line explains.
Does a high r² mean x causes y?
No. Correlation measures how well a straight line fits, nothing more. Two variables can move together because both depend on something else entirely, so a strong fit is never evidence of cause on its own.
What is the difference between LinReg(ax+b) and LinReg(a+bx)?
Only the naming. LinReg(ax+b) calls the slope a and the intercept b, which is what most courses expect. LinReg(a+bx) calls the intercept a and the slope b, matching the convention used in some statistics textbooks.