Kaplan-Meier Survival Analysis

hanaml.kaplan.meier.survival.analysis is a R wrapper for SAP HANA PAL kaplan.meier.survival.analysis.

hanaml.kaplan.meier.survival.analysis(
  data = NULL,
  event.indicator = NULL,
  confidence.level = NULL
)

Arguments

data

DataFrame
DataFrame containting the sampled data points structured as follows:

  • Follow-up time : INTEGER or DOUBLE

  • Status indicator: INTEGER

  • Occurrence number of events at the follow-up time. (multiple rows for one follow-up time possible) : INTEGER

  • Group : INTEGER or VARCHAR
event.indicator

integer, optional
Specifies one value to indicate an event has occurred. Defaults to 1.
confidence.level

double, optional
specifies the confidence level for a two-sided confidence interval on the survival estimate.
Defaults to 0.95.

Value

Returns a list of DataFrames.

  • DataFrame 1
    Estimation results after every event occurrence, structured as follows:

    • GROUP: Group

    • Time: Event occurrence time.

    • RISK_NUMBER: total number of each group before the event occurrences.

    • EVENT_NUMBER: Number of event occurrences.

    • PROBABILITY: Probability of surviving beyond event occurrence time.

    • SE: Standard error

    • CI_LOWER: Lower bound of confidence interval

    • CI_UPPER: upper bound of confidence interval

  • DataFrame 2
    Log rank survival statistics of each group. Only valid for multiple groups

    • GROUP: group

    • TOTAL_RISK: All individuals in the lifetime study

    • OBSERVED: number of observed events.

    • LOGRANK_STAT: log rank test statistics.

  • DataFrame 3
    Further statistics. Only valid for multiple groups

    • STAT_NAME : Statistics name e.g. Chi-square, df, p-value.

    • STAT_VALUE : Statistics value

Details

Kaplan Meier is one of the best options to perform non-parametric estimation of the survival function when considering a long term study, where a series of possibly censored failure times are observed. It is often used to measure the time-to-death of patients after treatment or time-to-failure of machine parts

Examples

Input DataFrame data:

> data$Head(5)$Collect()
  TIME STATUS OCCURRENCES GROUP
1    9      1           1     2
2   10      1           1     1
3    1      1           2     0
4   31      0           1     1
5    2      1           1     0

Call the function:

> result <- hanaml.kaplan.meier.survival.analysis(data=data)

Results:

> result[[3]]$Collect()
  STAT_NAME STAT_VALUE
1    chiSqr  0.3279707
2        df  2.0000000
3   p-value  0.8487545