Medical Edition

Survival analysis software for clinical research Kaplan-Meier survival curves with confidence bands, log-rank and weighted comparison tests, Cox proportional hazards regression with hazard ratios, restricted mean survival time and diagnostic plots.

Download 15-day trial Buy from US$ 340

Every feature from all five editions for 15 days, no sign-up.
Medical edition from US$ 340 a year · 30-day money-back guarantee.

Microsoft Excel with the Analyse-it tab selected, showing a survival analysis report: Kaplan-Meier survival curves for two groups with 95% simultaneous confidence bands, the events and censored observations table, the Compare menu open on the ribbon listing the log-rank, Wilcoxon, Tarone-Ware and Fleming-Harrington tests, and the Survival/Reliability task pane. Handwritten notes: Runs inside Excel: every analysis is on the Analyse-it tab; Four tests of equality under the Compare menu; Kaplan-Meier survival curve for each group; 95% simultaneous confidence bands; Events and censored observations; Confidence band: pointwise, Nair or Hall-Wellner; The report is an ordinary Excel worksheet: share it, archive it, open it on any PC with Excel.

Estimate survival, compare treatments, model risk

Excel has no survival analysis. Averaging the observed follow-up times treats a patient still alive at the last visit as if the event happened then. Excel’s built-in tests and regression assume every observation is complete. Clinical trials, cohort studies and registry analyses all produce time-to-event data: time to death, recurrence, graft failure, hospital readmission. Censored observations are the norm, not the exception.

What proportion survive to one year, and how precisely is that known? Do the treatment groups differ, and does the answer change with the weight given to early or late follow-up? How much does each covariate change the hazard, and does the hazard ratio hold across the whole follow-up?

Kaplan-Meier survival curves with pointwise, Nair and Hall-Wellner bands

A censored patient is still information, and the Kaplan-Meier estimator uses it. Pointwise, Nair (EP) or Hall-Wellner confidence bands are drawn on the survival curve. Median and quartile survival times come with confidence intervals, and the mean is the area under the curve. Survival and failure probabilities are reported at any time point you specify.

  • Kaplan-Meier survival curve plot with pointwise, Nair or Hall-Wellner confidence bands
  • Median and quartiles for survival/failure
  • Survival/failure probabilities and confidence intervals
  • Full or abbreviated survival function table with censored observations marked
Microsoft Excel showing a survival analysis report: Kaplan-Meier survival curves for three tumour grades with censored observations marked, and the N, events, mean and median tables beneath, with the task pane open on the survival function options. Handwritten notes: A survival curve for each tumour grade; N, events, mean and median survival; Band: pointwise, Nair or Hall-Wellner.
Kaplan-Meier survival curves for 30 brain cancer patients grouped by tumour grade, censored observations marked on each curve.

Log-rank, Wilcoxon (Breslow), Tarone-Ware and Fleming-Harrington tests

The choice of test can change the conclusion, so all four are available. Log-rank weights every point of follow-up equally, Wilcoxon (Breslow) emphasises early differences, Tarone-Ware sits between the two, and the Fleming-Harrington family lets you specify the weight function. Each tests the equality of the survival functions and handles censoring correctly.

  • Test equality of survival functions with log-rank, Wilcoxon, Tarone-Ware, Fleming-Harrington
Microsoft Excel showing a survival analysis report: the N and events, mean and median survival tables with 95% confidence intervals and quartile survival times, and the log-rank test with its chi-squared statistic, DF and p-value, with the task pane open on the test options. Handwritten notes: Median and quartile survival for each group, with 95% CIs; Log-rank test; Test: log-rank, Wilcoxon, Tarone-Ware or Fleming-Harrington.
Median and quartile survival times for the two groups, and beneath them the log-rank test of equality, p = 0.35.

Cox proportional hazards regression with likelihood ratio and Wald tests

Survival rarely depends on treatment alone. Cox proportional hazards regression models the effect of covariates on the hazard, interactions included. Parameter estimates come with Wald confidence intervals and the covariance of the estimates; likelihood ratio and Wald tests cover the overall model and each term. The baseline survival function is reported and plotted.

  • Cox proportional hazards regression new in v6.01
  • Model equation
  • Parameter estimates and Wald confidence intervals
  • Covariance of estimates
  • Baseline survival function and plot
  • Likelihood ratio and Wald test of model and terms
Microsoft Excel showing a Cox proportional hazards report: N, events and censored counts, the parameter table with estimate, Wald 95% confidence interval, SE, Wald Z and p-value for gender, age, their interaction, BMI and heart rate, and the hazard ratios beneath, with the Fit Model task pane open on the terms. Handwritten notes: N, events and censored; Estimate, Wald 95% CI, SE, Z and p for every term; Model terms, with interactions.
Cox proportional hazards fit for 500 patients with 215 events: estimate, Wald 95% CI, SE, Wald Z and p-value for each of the six terms.

Hazard ratios per level, per unit change and at levels of an interaction

The hazard ratio is the number a clinician reads. Hazard ratios with Wald Z confidence intervals are reported at each level of a categorical covariate and for a specified unit change in a continuous one. With an interaction in the model, ask for the ratio at specific levels of the interacting covariate: treatment A versus B in patients over 65.

  • Hazard ratio and Wald Z CI at each level / specified unit change and at specific levels of interacting covariates
Microsoft Excel showing the Hazard ratios section of a Cox proportional hazards report: female versus male at five ages, a one-year increase in age for each gender, and a five-unit increase in BMI at four BMI values, each with a Wald 95% confidence interval, then the Effect of Model and Effect of Terms likelihood ratio tests, with the task pane open on Hazard Ratios. Handwritten notes: Hazard ratios for female vs male at chosen ages; Per unit of age, per 5 of BMI, each with a Wald 95% CI; Likelihood ratio tests of the model and each term; Which ratios to report: per level, per unit change.
Hazard ratios from the same model, each with its Wald 95% CI: female versus male at five ages and a one-year increase in age for each gender. The five-unit increase in BMI is evaluated at four BMI values.

Restricted mean survival time, and log and log–log S(t) plots

Hazard ratios depend on the proportional hazards assumption; two outputs cover the case where it does not hold. Restricted mean survival time is the average event-free time up to a time horizon you specify. The summary does not depend on the assumption and is increasingly used in clinical trial reporting as a complement or alternative to hazard ratios. Transformed log and log–log S(t) versus time plots show whether the hazards are proportional. Where the curves cross or diverge, consider stratification or report RMST instead of hazard ratios.

  • Mean (area under survival curve) and restricted mean
  • Transformed log and log–log S(t) vs time plots

Example analyses

See survival analysis results in detail — Kaplan-Meier curves, group comparison tests and Cox proportional hazards — using example datasets you can download and follow along with.

Kaplan Meier 3 pages Kaplan-Meier survival
Brain cancer survival, 30 patients. Two analyses of one dataset — survival by treatment, 19 patients against 11 and survival by tumour grade over three groups. Survival curves with confidence bands, mean and median survival with CIs, quartile survival times and a log-rank test for each.
Fit PH Model 2 pages Cox proportional hazards
Worcester Heart Attack Study, 500 patients. 215 events and 285 censored. Sex, age, their interaction, body mass index as a quadratic and heart rate. Parameter estimates with Wald 95% CIs, hazard ratios evaluated at several ages and BMI values and likelihood ratio tests for the model and each term.

Part of the Medical edition

Survival analysis is one part of the Medical edition, alongside diagnostic accuracy, Bland-Altman agreement and reference intervals. The edition also includes the full Standard edition for hypothesis testing, regression and descriptive statistics.

Related guides in the Learn section: Kaplan-Meier survival curves, comparing survival between groups and Cox proportional hazards.

Software you can trust

Validated calculations you can defend at peer review Every calculation is performed by Analyse-it — no Excel formulas, no third-party functions. Results are validated against published datasets and thousands of internal test cases before every release. How Analyse-it is developed and validated →
Patient data stays on your PC Analyse-it runs entirely within Microsoft Excel on your PC. No cloud processing, no data transmission. Patient data and research data stay within your facility under your own data governance controls.
Standard Excel workbooks anyone can open Every analysis is an ordinary .xlsx workbook. Share with co-authors, attach to a manuscript submission, archive for publication queries. No proprietary format, no licence required to view results. Co-authors and reviewers see exactly what you see.
Results that cannot be accidentally broken Analysis output contains computed values, not formulas. Nothing to accidentally overwrite, no cell references to break, no formula errors to introduce. The results you published are exactly what you will find when you reopen the workbook months or years later, when a reviewer asks.

Free trial and pricing

Try it on your own data first. The 15-day trial is every feature from all five editions, with no sign-up and no licence key — install it and start straight away.

Download 15-day trial See pricing or get a quote →

Medical edition: US$ 340 per year or US$ 815 for a perpetual licence. Every purchase carries a 30-day money-back guarantee. Need a quote for purchasing? Add the licence to the cart and save it as a PDF quote.