STATISTICAL METHOD
Kaplan-Meier Survival Analysis
Statistical Consulting for Log-Rank Comparisons
We carry out Kaplan-Meier survival analysis within your study design, coding events and censoring correctly, and reporting the curve with numbers at risk, median survival with its confidence interval and the log-rank test in publication-ready form.
No Commitment Required
Strictly Confidential
In-House PhD-Level Statisticians
Fixed Project Fee
Same-Day Response
METHOD OVERVIEW
What Is a Kaplan-Meier Analysis?
A Kaplan-Meier analysis estimates the survival function, the probability of remaining event-free over time, without assuming a model, using the product-limit estimator, which steps down at each event and drops censored participants from the risk set. It answers how long participants remain event-free and whether groups differ, and the resulting curve is unadjusted for covariates. Median survival is read where the curve crosses 0.50 and is undefined if it never does, and the log-rank test compares curves between groups. OnlineSPSS, a specialist statistical consultancy for academic, clinical and professional research, provides Kaplan-Meier survival analysis within your study design, with the relevant checks, effect estimates, uncertainty measures, interpretation and publication-ready reporting.
WHEN TO ENGAGE
When Is a Kaplan-Meier Analysis Appropriate?
A Kaplan-Meier analysis fits an unadjusted description or comparison of time to event, and these are the research situations in which researchers most often ask us to apply or confirm it.
Describing Survival in a Cohort A study needs the probability of remaining event-free at set times, such as one or five years, reported with confidence intervals for the whole cohort.
Comparing Groups on Time to Event Treatment arms or exposure groups are compared on survival with curves and a log-rank test, where adjustment for other covariates is not the aim.
Preparing a Journal Survival Figure A manuscript or conference abstract needs curves with numbers at risk, censoring marks and confidence bands that will stand up to a reviewer.
Reviewing a Survival Curve Report A reviewer has queried a median, curve or log-rank result, possibly from miscoded censoring. Independent Statistical Review rechecks the coding and the reporting.
ANALYTICAL APPROACH
How We Apply Kaplan-Meier Analysis
Within the family of Clinical, Survival & Epidemiological, the curve is a first description of the data, and its limits shape how it is reported.
Event and Censoring Coding We verify that events are coded as events and censored times as censored, since a reversed status variable inverts the curve, and confirm entry and end dates for every participant.
Survival Estimates and Median We report survival at prespecified times and the median with its confidence interval, and state that the median was not reached when the curve stays above 0.50 throughout.
Log-Rank and Its Limits The log-rank test has most power when hazards are proportional and can miss late or crossing differences. We pair it with a hazard ratio or a restricted mean survival time difference.
Reading the Curve Honestly Curves carry confidence bands, numbers at risk and censoring marks, and a note that they are unadjusted, so in observational data a gap may reflect confounding as much as exposure.
DELIVERABLES
What You Receive
As part of our Quantitative Data Analysis service, the Kaplan-Meier analysis is delivered with the estimates, checks and files needed to report and defend it.
Data & Variable Review Event and censoring indicators are cross-checked against dates, group labels against the analysis plan, and each participant's last contact date is confirmed.
Method-Specific Checks The curves are checked for crossing and late separation, which weaken the log-rank test, and censoring is compared between groups to see whether follow-up differs by arm.
Statistical Results Survival at chosen times with 95% confidence intervals, median survival where reached, the log-rank test and a hazard ratio or restricted mean difference.
Publication-Ready Tables & Figures Kaplan-Meier curves with confidence bands, numbers at risk and censoring marks and event tables, prepared in line with CONSORT, STROBE or the journal's requirements.
Interpretation Survival is described within the available follow-up and as unadjusted, any median not reached is reported as such, and the tail is read cautiously where few remain at risk.
Reproducible Analysis Files Analysis scripts in R, SAS or SPSS syntax, including the code that draws each curve and its risk table, are provided where applicable for a later data cut.
ALTERNATIVE METHODS
When Another Method May Be More Appropriate
A Kaplan-Meier curve describes unadjusted survival. These methods fit better when the question needs adjustment, a cause-specific view, a fixed-time risk or a simple event rate.
01
Cox Regression
When groups differ in age, stage or other covariates and the effect must be adjusted, a regression model gives an adjusted hazard ratio that a crude curve cannot.
02
Competing Risks Analysis
When another event, such as death from another cause, can prevent the event, cumulative incidence replaces one minus the Kaplan-Meier estimate, which overstates it.
03
Relative Risk & Odds Ratios
When the question is the risk of an outcome by a fixed time and every participant has complete follow-up, a risk ratio is simpler than a time-to-event comparison.
04
Poisson Regression
When events can recur and the aim is a rate ratio, events per person-year in Poisson regression, with robust errors for repeat events, capture what a first-event curve omits.
CASE EXAMPLE
How We Work in Practice
An illustration of how a curve and a log-rank comparison move from a statistical analysis plan to a reportable, defensible result.
ILLUSTRATIVE EXAMPLE · CLINICAL TRIAL BIOSTATISTICS · UNITED STATES
A trial sponsor's biostatistics group needed Kaplan-Meier curves and a comparison of progression-free survival between two arms for a conference abstract and a later manuscript.
The plan named the log-rank test, but the treatment was expected to act slowly, so the curves might separate late and one hazard ratio would summarize the effect poorly. Before unblinding, we kept the log-rank test as the primary comparison and added a restricted mean survival time difference at a prespecified horizon, which needs no proportional hazards, as a sensitivity analysis. We checked that progression and death were coded as events and that patients without either were censored at their last assessment. Any median not reached would be reported as such, with numbers at risk beneath every curve.
Outcome: The team received curves with numbers at risk, the log-rank result, and medians and the restricted mean survival time difference with 95% confidence intervals, plus the scripts.
This example does not describe a real client or project. We never share details of actual client work, in line with the confidentiality we promise every researcher. This illustrative example is included to show the type, scope, and standard of work involved in this kind of analysis.
SOFTWARE
Statistical Software for Kaplan-Meier Curves
Kaplan-Meier analyses and log-rank tests are run in the statistical software researchers already use, with syntax or scripts provided where applicable.
RESEARCH DISCIPLINES
Kaplan-Meier Curves Across Research Fields
Kaplan-Meier curves are reported across many research fields, each with its own event definitions, follow-up lengths and journal conventions.
A Defined Process for Your Analysis
We review your dataset, research question and design before any work begins, so the scope, deliverables, timeline and fixed project fee are clear from the outset.
01
Share Your Research Materials
Send your dataset, research question, study design and any existing analysis plan or output. We will let you know if anything else is needed to assess the project.
02
Receive Your Assessment
Your statistically trained Research Coordinator reviews the project and confirms the required analysis, deliverables, timeline and fixed project price before work begins.
03
Analysis & Delivery
Once you confirm the scope, an in-house statistician completes the agreed analysis and delivers the outputs, interpretation and reporting files.
RESEARCHER VOICE
What Researchers Say
Feedback from a researcher who needed to calculate and report confidence intervals and effect measures for a Kaplan-Meier analysis.
“Our dataset looked straightforward until we got into Kaplan-Meier Analysis and realized how effect sizes and confidence intervals should be calculated and reported. The team sorted out the analytical setup and gave us a clear explanation of what could and could not be concluded. The final tables included the effect estimates and 95% confidence intervals we needed for reporting.”
RESEARCH RESPONSIBILITY
Statistical Support Without Taking Over Your Research
We provide the statistical work for your curves and log-rank comparisons, and the study, its meaning and its authorship stay entirely with you.
Agreed Statistical Support We provide the agreed methodological, analytical and statistical reporting support for your Kaplan-Meier analysis, within the scope confirmed before work begins.
No Intellectual Contribution OnlineSPSS claims no intellectual contribution to your research. Our work is statistical support, and authorship remains yours.
Your Research Decisions The research question, the clinical reading of the curves and your conclusions remain with you, and our interpretation stays within what an unadjusted estimate and the follow-up support.
Confidential Handling Research data and project details are handled confidentially and are not published. An NDA is available where required, and can be arranged before sensitive materials are shared.
FREQUENTLY ASKED QUESTIONS
Questions About Kaplan-Meier Analysis
Short answers to what researchers ask before reporting a Kaplan-Meier analysis, from medians and the log-rank test to confidentiality and the assessment process.
Is a log-rank p-value enough to report with a Kaplan-Meier curve?
No, a log-rank p-value alone is thin reporting, because it says whether the curves differ but not by how much. Alongside the curve we report numbers at risk, survival at prespecified times or the median with confidence intervals, and a magnitude such as a hazard ratio or a restricted mean survival time difference.
What should I report if the median survival is not reached?
A median that is not reached means the curve never fell to 0.50 within follow-up, so we report it as not reached instead of extrapolating one. Alongside it we give survival at fixed time points with confidence intervals, or restricted mean survival time up to a prespecified horizon, which remains estimable.
Should I use Kaplan-Meier analysis or Cox regression?
A Kaplan-Meier curve describes survival for each group without adjustment, so it fits a first description or a randomized comparison. Cox regression is chosen when the effect must be adjusted for covariates, and the two are usually reported together, the curve for shape and the model for the adjusted estimate.
Can you review an analysis that has already been completed?
Yes, we can review a completed Kaplan-Meier analysis before submission or a response to reviewers. We check the event and censoring coding, the median and its interval, the number at risk table, whether the log-rank test suits the curves and the reporting, and confirm what stands or needs to change.
How do you protect my dataset and research confidentiality?
Your dataset, follow-up and event files and any statistical analysis plan are handled confidentially, and project information is not published. An NDA is available where required and can be arranged before sensitive materials are shared. Read more about confidentiality and data security.
What happens when I request an assessment, and how long does it take?
You share your research question, design and relevant materials, and a statistically trained Research Coordinator reviews the request and responds the same day. The analysis, deliverables, timeline and one fixed project fee are then confirmed before any work begins, so the timeline follows from the agreed scope.
Still have a question? Find more answers in our full FAQ.
NEXT STEP
Need Support With a
Kaplan-Meier Analysis?
Share your research question, follow-up design and data. We assess whether a Kaplan-Meier analysis fits your comparison and confirm the approach before any work begins.
No Commitment Required
Strictly Confidential
Fixed Project Fee
In-House PhD-Level Statisticians
Same-Day Response
Serving Researchers Since 2014