Launch StatClinic →
Survival Analysis

How to Interpret Cox Regression Results (Hazard Ratio Explained)

📖 18 min read 🗓 July 2026 ✓ Updated July 2026
S
StatClinic Editorial Team Statistical content for medical researchers and clinicians
"Hazard ratio 0.58, 95% CI 0.39–0.85, p = 0.006" — four numbers that decide whether a treatment gets described as protective, harmful, or inconclusive, and that most researchers were never actually taught to read carefully. This guide explains Cox regression and the hazard ratio from the ground up, in plain English, with no unnecessary formulas: what it is, when to use it, how it differs from logistic regression, how to read every part of the output table, and a full step-by-step worked example you can follow along with your own data.

What Is Cox Proportional Hazards Regression?

Cox proportional hazards regression (usually just called "Cox regression") is a statistical method used to study how long it takes for an event to happen, and whether certain factors speed it up or slow it down. The "event" is often death, but it can be any clearly defined occurrence: disease recurrence, hospital readmission, graft failure, or recovery.

What makes Cox regression different from an ordinary regression model is that it uses both pieces of information every participant provides: whether the event happened, and exactly when (or, for participants who never experienced the event during the study, how long they were observed for without it happening). It answers a very specific, clinically useful question: "at any given moment, how does this factor change a patient's instantaneous risk of the event happening right now, compared to a patient without that factor?"

Take-Home Points Cox regression models time-to-event data, using both whether and when the event happened. Its main output — the hazard ratio — describes instantaneous risk over time, not a single fixed probability.

When Should Cox Regression Be Used?

Use Cox regression whenever your outcome has two components: an event indicator (did it happen — yes/no) and a time variable (how long until it happened, or how long the patient was followed if it didn't). It is the standard method for analyzing survival-type outcomes while simultaneously adjusting for multiple predictors — age, treatment group, tumor stage, comorbidities — in a single model.

Clinical ScenarioWhy Cox Regression Fits
Time to death after cancer diagnosis, by treatment armEvent = death; time = months from diagnosis; adjusts for stage, age
Time to disease relapse after remissionEvent = relapse; time = months in remission; adjusts for baseline risk factors
Time to hospital readmission after dischargeEvent = readmission; time = days since discharge; adjusts for comorbidity burden
Time to graft failure after transplantEvent = graft failure; time = months post-transplant; adjusts for donor/recipient factors
Take-Home Points If your outcome can be described as "time until X happens," and some participants haven't experienced X by the end of the study, Cox regression is very likely the right tool.

Cox Regression vs Logistic Regression

These two are the most commonly confused regression methods in medical research, because both can technically analyze a "yes/no" outcome. The key difference is what each one does with time.

FeatureCox RegressionLogistic Regression
OutcomeTime to event + whether it happenedWhether an event happened (yes/no) only
Uses timing of the event?Yes — central to the modelNo — ignores exactly when it happened
Handles participants lost to follow-up?Yes, via censoring (see below)Not directly — typically excluded or treated as no-event
Effect measureHazard ratio (HR)Odds ratio (OR)
Typical question"How much faster/slower does the event happen?""How much more/less likely is the event by a fixed point?"
A Quick Rule of Thumb If every participant is followed for the exact same length of time and you only care whether the event happened by the end (not when), logistic regression can work. If follow-up time varies between participants, or you care about the timing of the event, Cox regression is the correct choice — using logistic regression instead throws away real information. See our logistic regression guide and odds ratio explainer for the logistic regression side of this comparison.

What Is Survival Analysis?

Survival analysis is the broader family of statistical methods, including Cox regression, designed specifically for time-to-event data. "Survival" is the traditional name from its origins in mortality research, but the methods apply equally to any event, not only death — recurrence, relapse, discharge, or infection all count.

The two most common survival analysis tools work together: Kaplan-Meier estimates and visualizes survival probability over time for one or more groups without adjusting for other variables, while Cox regression quantifies the effect of one or more predictors on survival time, with or without adjustment for other factors. Most survival analysis papers present both: a Kaplan-Meier curve to show the overall picture, and a Cox model to quantify and adjust the effect. See our full Kaplan-Meier guide for the visual half of this pairing.

Take-Home Points Survival analysis is the umbrella term for time-to-event methods. Kaplan-Meier shows the picture; Cox regression quantifies and adjusts it — they are complementary, not competing, tools.

What Is Censoring?

Censoring happens when a study ends, or a participant leaves the study, before the event of interest has occurred for them — meaning their exact event time is unknown, but you do know they survived event-free for at least as long as they were observed. This is the single most important concept that makes survival analysis different from ordinary regression, because it lets a study use every participant's partial information rather than discarding anyone whose event hadn't happened by the study's end.

Practical Example — Three Types of Censoring

Patient A enrolls and dies at Month 14 — event observed, not censored.
Patient B is still alive when the 24-month study ends — censored at Month 24 (the study ended before their event, if any, occurred).
Patient C moves away and is lost to follow-up at Month 9, alive at last contact — censored at Month 9 (their event status after Month 9 is unknown).

All three types shown above are examples of right censoring, by far the most common type in medical research (the true event time is somewhere to the right of, i.e., after, the last known observation). Cox regression correctly uses censored participants' data up to the point they were censored — it does not simply drop them, and it does not treat censoring as equivalent to "no event ever."

Take-Home Points Censoring means "we don't know exactly when (or if) the event happened, only that it hadn't happened by this point." Censored participants still contribute valuable information to the model and should never be excluded or coded as event-free.

Hazard vs Risk

"Hazard" and "risk" are often used interchangeably in everyday language, but in survival analysis they mean two distinct things, and confusing them is a common source of misinterpretation.

ConceptWhat It MeasuresSimple Analogy
RiskThe cumulative probability that an event has happened by a specific point in time (a fixed number between 0 and 1)"What fraction of the road trip is behind you by mile 100?"
HazardThe instantaneous rate of the event happening right now, among those who haven't yet had it — can change at every moment"How fast is the car going right now, at this exact instant?"

A hazard is not a probability and does not have to stay between 0 and 1 — it is a rate, similar to speed. A hazard ratio compares this instantaneous rate between two groups, at any given moment, assuming that ratio stays roughly constant over the whole follow-up period (this assumption is covered in detail later in this guide).

Take-Home Points Risk is cumulative and cannot exceed 1; hazard is a rate and can be any positive number. A hazard ratio compares rates at each moment in time, not overall probabilities by the end of the study.

Hazard Ratio Explained with Simple Examples

The hazard ratio (HR) is the single number Cox regression is built to produce. It compares the hazard (instantaneous event rate) in one group to the hazard in a reference group. An HR of 1.0 means no difference; above 1.0 means a higher hazard (faster/more frequent events); below 1.0 means a lower hazard (slower/less frequent events, i.e., protective).

HR = 1.0
No difference in hazard between groups
HR = 2.0
Exposed group has 2× the instantaneous event rate
HR = 0.5
Exposed group has half the instantaneous event rate (protective)
Practical Example

HR = 1.8 for smokers vs non-smokers (outcome: lung cancer diagnosis) — at any given moment during follow-up, smokers who have not yet been diagnosed are experiencing new diagnoses at 1.8 times the rate of non-smokers who have not yet been diagnosed. This is not the same as saying "smokers have an 80% higher chance of getting lung cancer by the end of the study" — that would be a statement about cumulative risk, not hazard.

❌ Incorrect Interpretation

"HR = 1.8 means smokers have an 80% higher probability of developing lung cancer over their lifetime" — treating the hazard ratio as if it were a cumulative risk or probability statement.

✅ Correct Interpretation

"At any point during follow-up, smokers who have not yet developed lung cancer are being diagnosed at 1.8 times the instantaneous rate of non-smokers who have not yet been diagnosed."

Take-Home Points The hazard ratio is a rate comparison, not a probability comparison — resist the urge to translate it into "X% more likely," which is technically incorrect language for a hazard ratio.

Adjusted vs Unadjusted Hazard Ratios

An unadjusted (crude) hazard ratio comes from a Cox model containing only the exposure or treatment variable, with nothing else — it reflects the raw, unadjusted relationship, which may be distorted by confounding variables. An adjusted hazard ratio comes from a model that also includes other covariates (age, disease stage, comorbidities), isolating the exposure's effect from their influence. See our guide on how to choose covariates for the full logic behind deciding which variables belong in the adjustment set.

Practical Example

Unadjusted: New drug vs standard care, HR = 0.72 (28% lower hazard of progression) — but patients on the new drug happened to have earlier-stage disease on average.
Adjusted (for tumor stage and age): HR = 0.81 — still protective, but part of the original crude effect was explained by the imbalance in disease stage between groups, not the drug itself.

Always report which covariates a hazard ratio was adjusted for, and generally report both the unadjusted and adjusted HR side by side so a reader can see how much confounding adjustment changed the estimate.

Take-Home Points An adjusted HR is almost always more trustworthy than a crude HR in observational data — but only if the covariates adjusted for were chosen for sound clinical and causal reasons, not convenience.

Interpreting the SPSS Cox Regression Output Table

Run via Analyze → Survival → Cox Regression in SPSS. The key output table is Variables in the Equation, shown below with realistic values for a study of a new drug's effect on disease progression, adjusted for age and tumor stage.

Example Output — Variables in the Equation
Predictor
B (SE)
Wald, Sig.
Exp(B)
95% CI for Exp(B)
Drug (yes)
-0.54 (0.20)
7.29, .007
0.58
[0.39, 0.85]
Age (years)
0.03 (0.01)
4.86, .028
1.03
[1.00, 1.06]
Tumor Stage (III/IV vs I/II)
0.71 (0.22)
10.42, .001
2.03
[1.32, 3.12]
Report: "After adjusting for age and tumor stage, the new drug was associated with a significantly reduced hazard of disease progression (aHR 0.58, 95% CI [0.39, 0.85], p = 0.007)."

What to Interpret, What to Ignore

Interpret Exp(B) — this is the hazard ratio itself, the number to report and discuss. Ignore the raw B (log-hazard) column in your write-up; it is a computational intermediate, not a clinically meaningful number on its own — similar to how logistic regression's raw B is not reported directly either, covered in our SPSS output interpretation guide. The Wald statistic is the test statistic behind the p-value; it rarely needs to be quoted directly, but the p-value it produces does.

Take-Home Points Exp(B) is your hazard ratio — always report it, never the raw B. Report the full set: HR, 95% CI, and exact p-value, for every predictor discussed, not the primary exposure alone.

Interpreting Confidence Intervals for the Hazard Ratio

The 95% confidence interval (CI) around a hazard ratio gives the plausible range for the true hazard ratio in the population, based on your sample. A CI that does not cross 1.0 confirms the result is statistically significant at the conventional threshold — consistent with, but conveying much more than, the p-value alone.

Example HR (95% CI)Interpretation
0.58 (0.39–0.85)Significant protective effect — entire interval is below 1.0
1.45 (1.05–2.01)Significant harmful effect — entire interval is above 1.0
0.85 (0.60–1.20)Not significant — interval crosses 1.0; true effect could be protective, null, or harmful
0.58 (0.09–3.71)Extremely imprecise — likely too few events to draw a reliable conclusion, despite a similar point estimate to the first row

Always report the full CI, not just the point estimate — a "significant" HR with a very wide CI (like the last row above) deserves far more caution than the same HR with a tight CI, even though both might report similar p-values. See our confidence interval guide for the general concept behind this.

Take-Home Points A CI crossing 1.0 means "not statistically significant" — same conclusion as p > 0.05, but the CI additionally tells you the plausible range and precision of the estimate, which a bare p-value cannot.

Interpreting P Values in Cox Regression

The p-value in the Sig. column tests the null hypothesis that the true hazard ratio equals 1.0 (no effect). A p-value below your chosen threshold (almost always 0.05) means the observed HR is unlikely to have arisen by chance alone if the true HR were really 1.0.

As with any regression, always report the exact p-value (e.g., p = 0.007), not just "p < 0.05," and convert any SPSS ".000" to "p < 0.001" rather than reporting it literally as zero. A p-value alone says nothing about the size of the effect — always pair it with the HR and its CI, exactly as covered in our p-value interpretation guide.

Take-Home Points The p-value answers "is this HR different from 1.0 by more than chance would explain?" — it does not measure how large or clinically important the effect is. That's what the HR and its CI are for.

Checking the Proportional Hazards Assumption

Cox regression assumes the hazard ratio between groups stays roughly constant over the entire follow-up period — this is the "proportional" in "proportional hazards." If a treatment's benefit is large early on but fades by month 24, a single overall hazard ratio poorly summarizes what is actually a changing effect, and the model's p-value and CI become unreliable.

1

Visual check: log-minus-log survival plot

Plot log(-log(survival)) against log(time) for each group. Roughly parallel lines support the assumption; lines that cross or diverge suggest violation.

2

Formal test: Schoenfeld residuals

Test each covariate's Schoenfeld residuals against time. A non-significant result (p > 0.05) supports proportional hazards for that variable; a significant result suggests violation.

3

If violated: adapt the model

Options include a time-dependent covariate, stratifying by the violating variable, splitting follow-up into time periods, or an alternative model that doesn't require this assumption.

Reversed Logic — Same as a Normality Test For the Schoenfeld residuals test, a non-significant result (p > 0.05) is the result you want — it means the assumption holds. A significant result means the assumption is violated. This is the same "reversed" direction as a normality test or the Hosmer-Lemeshow test in logistic regression, and is easy to misread if you're expecting significance to be the "good" outcome.
Take-Home Points Always check and report the proportional hazards assumption — via Schoenfeld residuals, a log-minus-log plot, or both — before trusting a single overall hazard ratio. A non-significant Schoenfeld test is the reassuring result here.

Common Mistakes in Interpreting Cox Regression

Mistake 1: Reading the Hazard Ratio as a Risk or Probability

Saying "HR = 1.8 means an 80% higher chance of the event" converts a rate comparison into a probability statement, which is not what a hazard ratio measures.

✓ Fix: Use rate language — "1.8 times the instantaneous event rate" — not probability language.

Mistake 2: Reporting the Raw B Instead of Exp(B)

The log-hazard coefficient (B) is not directly interpretable by a clinical reader and should never be reported as if it were the hazard ratio.

✓ Fix: Always report Exp(B) — the exponentiated coefficient — as your hazard ratio.

Mistake 3: Excluding Censored Participants from the Analysis

Dropping everyone who didn't experience the event by the end of the study discards real information and can bias the result, sometimes substantially.

✓ Fix: Include censored participants with their correct censoring time — this is exactly what Cox regression is designed to handle correctly.

Mistake 4: Never Checking the Proportional Hazards Assumption

Reporting a single hazard ratio without checking whether the effect is actually constant over time can mask a clinically important pattern, such as an early benefit that disappears later.

✓ Fix: Run and report a Schoenfeld residuals test (or log-minus-log plot) for every covariate before finalizing the model.

Mistake 5: Confusing Hazard Ratio with Odds Ratio or Relative Risk

These three effect measures are calculated differently and are not numerically interchangeable, even though they often point in a similar direction.

✓ Fix: Label the effect measure correctly based on the model actually used — HR for Cox regression, OR for logistic regression, RR for a direct risk comparison.

Mistake 6: Claiming Causation from an Observational Cox Model

An adjusted hazard ratio from an observational study, no matter how many covariates were included, cannot rule out unmeasured confounding the way randomization can.

✓ Fix: Use association language ("was associated with") for observational studies, reserving causal language for randomized designs.

Step-by-Step Medical Example

Study: Does a new anticoagulant reduce the hazard of stroke in patients with atrial fibrillation, compared to standard therapy, over 24 months of follow-up?

1

Define the outcome

Event = ischemic stroke (yes/no); Time = months from enrollment to stroke, or to last contact/study end if stroke-free (censored).

2

Choose covariates

Age, prior stroke/TIA, hypertension, and diabetes — all established stroke risk factors, selected via clinical knowledge and the CHA₂DS₂-VASc score, as covered in our covariate selection guide.

3

Run the Cox model

Analyze → Survival → Cox Regression in SPSS; treatment group as the primary predictor, the four covariates entered together.

4

Check the proportional hazards assumption

Schoenfeld residuals test for treatment group: p = 0.41 (non-significant) — assumption holds.

5

Interpret and report the result

Adjusted HR for the new anticoagulant = 0.62, 95% CI [0.41, 0.94], p = 0.024.

Final Reported Result

"After adjusting for age, prior stroke/TIA, hypertension, and diabetes, patients receiving the new anticoagulant had a significantly lower hazard of ischemic stroke compared to standard therapy (aHR 0.62, 95% CI [0.41, 0.94], p = 0.024). The proportional hazards assumption was confirmed via Schoenfeld residuals (p = 0.41)." Run this analysis directly with the Cox regression calculator, and see our full reporting-by-test guide for more worked examples across other tests.

Practical Interpretation Checklist

1

Confirm event and time variables are correctly defined

Event coded consistently (1 = event, 0 = censored); time measured from a clear, consistent starting point.

2

Report Exp(B), not raw B

The hazard ratio is the exponentiated coefficient — always report this, never the log-hazard.

3

Report the 95% CI alongside every HR

Never quote a hazard ratio without its confidence interval.

4

Report the exact p-value

Three decimal places, or "p < 0.001" — never "p = 0.000" or bare "p < 0.05."

5

State whether the HR is adjusted or unadjusted

And list every covariate included if adjusted.

6

Check and report the proportional hazards assumption

Schoenfeld residuals test or log-minus-log plot, for the primary predictor at minimum.

7

Use rate language, not probability language

"X times the instantaneous hazard," not "X% more likely."

8

Match causal language to study design

Association language for observational studies; causal language reserved for randomized designs.

Frequently Asked Questions

What does a hazard ratio of 1 mean? +
A hazard ratio of exactly 1.0 means there is no difference in the instantaneous risk of the event between the two groups being compared. A hazard ratio above 1 means the exposure group has a higher hazard (event happens faster/more often); a hazard ratio below 1 means the exposure group has a lower hazard (event happens slower/less often, i.e., a protective effect).
Is a hazard ratio the same as relative risk? +
No, though they are frequently confused. Relative risk compares the cumulative probability of an event occurring by a fixed point in time. A hazard ratio compares the instantaneous rate of the event at any given moment, accounting for exact timing and censoring throughout follow-up. The two are often numerically similar when the event is rare, but are not interchangeable, especially when event rates are high or follow-up varies substantially.
Why is my hazard ratio significant but the confidence interval very wide? +
A wide confidence interval despite significance usually signals a small number of events (not necessarily a small total sample size) — Cox regression's precision depends on the number of events observed, not the number enrolled. A study with 500 participants but only 15 events will produce a much less precise estimate than one with 200 participants and 80 events. Interpret such results cautiously.
What happens if the proportional hazards assumption is violated? +
The single hazard ratio becomes a poor summary of an effect that actually changes over the follow-up period, and the p-value and CI become unreliable. Options include a time-dependent covariate, stratifying the model by the violating variable, splitting follow-up into time periods with separate hazard ratios, or switching to an alternative model such as an accelerated failure time model.
Can a hazard ratio be used to say a treatment causes a survival benefit? +
A hazard ratio from a randomized controlled trial can support a causal interpretation, since randomization prevents confounding. A hazard ratio from an observational study can only be interpreted as an adjusted association, not a proven causal effect, no matter how many covariates were adjusted for, because unmeasured confounding can never be fully excluded outside of randomization.
How is a hazard ratio reported in a results section? +
The standard format is: adjusted HR = value, 95% CI [lower, upper], p = value, alongside which covariates the model adjusted for and confirmation the proportional hazards assumption was checked. Example: "After adjusting for age and tumor stage, treatment was associated with a significantly reduced hazard of disease progression (aHR 0.58, 95% CI [0.39, 0.85], p = 0.006)." Always report the exact p-value and the confidence interval, not the hazard ratio alone.

Run Your Cox Regression With Confidence

Use StatClinic's free Cox regression and Kaplan-Meier calculators to run your survival analysis and get a journal-ready, correctly worded results sentence generated automatically. Free, no registration required.

Try StatClinic Free →