Paste your data
One variable per column, with a header row. Paste from Excel, Sheets, or CSV - delimiter is detected automatically.
Reading a regression table
A regression table reports how a set of predictors relate to an outcome. Each row is a term in the model. The coefficient B is the estimated change in the outcome for a one-unit increase in that predictor, holding the others fixed; the standard error quantifies its uncertainty; the t-value and p-value test whether it differs from zero. A predictor with p < .05 is conventionally called a statistically significant predictor.
Model fit: R-squared and the F-test
R-squared is the proportion of variance in the outcome explained by the model. Adjusted R-squared penalizes adding predictors that do not earn their keep, so it is the fairer number to report for multiple regression. The F-test asks whether the model as a whole explains significantly more variance than an intercept-only model. All three are computed here exactly, matching the output of R's lm() or Python's statsmodels.
Standardized betas
Because B is in the predictor's original units, you cannot compare a coefficient measured in dollars against one measured in years. The standardized coefficient beta rescales every variable to standard-deviation units so the magnitudes are directly comparable - useful when a reviewer asks which predictor matters most. Need three or more group means compared instead of a regression? Use the ANOVA calculator.
Frequently asked questions
What kind of regression does this run?
It fits an ordinary least squares (OLS) linear regression with an intercept. With one predictor that is simple linear regression; with several it is multiple linear regression. For each term you get the unstandardized coefficient B, its standard error, the standardized coefficient (beta), the t-value, and the two-tailed p-value, plus overall R-squared, adjusted R-squared, and the model F-test.
How do I choose the outcome and predictors?
After you paste data, the tool lists every numeric column. Click one column as the outcome (dependent variable) and any number of others as predictors. If you leave predictors unselected, it uses all remaining numeric columns. Rows with a missing value in the outcome or any selected predictor are dropped (complete-case analysis).
What is the difference between B and beta?
B is the unstandardized coefficient in the original units: a one-unit increase in the predictor changes the outcome by B units, holding other predictors constant. Beta is the standardized coefficient (both variables converted to z-scores), which lets you compare the relative strength of predictors measured on different scales.
Can it export an APA-formatted regression table?
Yes. The APA export gives you a tab-delimited table with Predictor, B, SE B, beta, t, and p columns plus a model-fit line (R-squared, F, df, p, n) and a significance note - paste it into Word and convert text to a table. There is also a LaTeX booktabs export and a CSV export for further analysis.
Is my data sent to a server?
No. The regression is computed entirely in your browser using a built-in linear algebra routine, so your data never leaves your machine and nothing is stored.
Related tools
From a table to a figure
Plotivy turns the same data into a publication-ready correlation heatmap or coefficient plot - and hands you the Python code behind it.
Open the Analyze tool