Regression Analysis Software for Microsoft Excel
PFrom simple linear regression to full ANOVA, ANCOVA, and GLM models — build, diagnose, and iterate on regression models directly in Excel, with the depth you’d expect from a professional statistics package.
Try free for 15 days — no credit card required
Trusted by 75,000 researchers, analysts, and scientists at leading universities, hospitals, and companies worldwide — for over 30 years.
The complete model-building workflow, not just a formula
Excel’s LINEST function gives you coefficients. Analyse-it gives you the full picture: parameter estimates, confidence intervals, VIF, standardized betas, Type I and Type III tests for each term, leverage plots, residual diagnostics, outlier and influence analysis, and prediction — all in a logical, interactive workflow.
Iterate until the model is right
Good model fitting is iterative. Analyse-it’s interactive approach lets you add or remove terms, transform variables, switch between model families, and re-run diagnostics immediately — without re-entering your data or starting from scratch. The model improves as you work.
Professional depth without the professional price tag
Minitab and JMP provide excellent regression tools, but at a cost and complexity that’s hard to justify for most analysts. Analyse-it covers the same regression ground — including ANOVA, ANCOVA, and complex interaction models — at a fraction of the price, inside Excel, with a shorter learning curve.
Regression in Excel is a workaround. The built-in Analysis ToolPak gives you a static output table with no diagnostics and no way to iterate. LINEST gives you numbers, not understanding. And for anything beyond simple linear regression — polynomial terms, categorical factors, interactions, logistic regression — you’re on your own.
Analyse-it treats regression as what it actually is: a process of building, examining, and refining a model. You start with your data in Excel, choose your model structure, and get a complete analysis — fit statistics, parameter estimates, diagnostic plots, leverage plots, and the ability to predict new observations. When the diagnostics suggest a problem, you adjust the model and re-run immediately. The results update. The process stays inside Excel.
Whether you’re fitting a simple linear model, building a full factorial ANOVA, or working with binary outcomes using logistic regression, the workflow is the same: clear, logical, and complete.
What's included
- Simple regression Linear, polynomial (2nd to 6th order), logarithmic, exponential, power, and probit regression. Transform X and Y variables. F-test for lack of fit. Scatter plot with fit line and confidence bands.
- Multiple linear regression Build models with any combination of continuous and categorical predictors. Simple, crossed, polynomial, and factorial terms. Categorical variables coded automatically as dummy variables. Full factorial and ANOVA/ANCOVA models.
- Binary logistic regression Model binary outcomes with a complete logistic regression implementation including parameter estimates, confidence intervals, and model fit statistics.
- Complete fit statistics R², adjusted R², AIC, BIC. Parameter estimates with confidence intervals and VIF. Standardized betas. Correlation and covariance of estimates matrices. Model equation for documentation and prediction.
- Term-level hypothesis tests and leverage plots Sequential (Type I SS) and partial (Type III SS) tests for every term in the model. Leverage (partial residual) plots to visualize the effect of each predictor after accounting for all others.
- Diagnostic plots Raw and standardized residual plots, sequence and lag plots, residual distribution. Outlier and Influence plot using Cook’s D and Studentized Residuals to identify problematic observations.
- Categorical variable analysis Effect means with confidence intervals for categorical predictors. Main effect and interaction plots. Multiple comparisons of effect means: Tukey-Kramer, Dunnett, Hsu, Scheffe, and Student’s t.
- Save model variables and predict Save fitted values, residuals, standardized residuals, studentized residuals, leverage, and Cook’s D back to the dataset for further analysis. Predict new observations directly from the model.
- More than just regression Regression is part of the Standard edition, which also covers descriptive analysis, hypothesis testing, ANOVA for group comparisons, correlation, PCA, factor analysis, and categorical data analysis. One tool. One Excel workflow. Everything you need.
Join 75,000 scientists who rely on Analyse-it. No credit card required. Full functionality from day one.
Try free for 15 days — no credit card required
