Survival rate refers to an organismpopulationEach individual within theprobability。IfHorizontal axisIs the elapsed time (day, month or year),Longitudinal axisFor survival rate, the survival curve can be drawn.According to the type of survival curve, we can judge the death of biological populationlaw。[1]
Under different conditions, the survival rate of the population is calculated in different ways. For example, during seed germination, the survival rate=(number of seedlings returning to growth/total number of trees) * 100%[2]Is the calculation method of seed germination occurrence and survival rate.
Survival comparison
Announce
edit
When there are two or more survival distributions, we often need to compare whether they come from the same survival distributionhypothesis testFor:
: The overall survival distribution of the samples is the same;
: The overall survival distribution of samples is different.
The available test methods include Logrank method, generalized Wilcoxon method, and Cox Mantel method.When rejected
It is considered that several survival distributions are different.
The test method of survival rate comparison has its corresponding content in SPSS, the Life Tables process and the Life Tables process module. Therefore, only the Logrank test is taken as an example to illustrate the basic principle and process.
Logrank inspection is also calledlogarithmRank test(Log Rank Test), the basic idea of which is that if the null hypothesis is true (there is no difference between the two overall survival curves), the theoretical death number calculated according to the initial number of observations and the theoretical death probability of the two treatments with different survival times should not differ significantly from the actual death number, otherwise the null hypothesis is not true, and the difference between the two survival curves is considered statistically significant,The log rank test can be used to compare the survival curves of two or more sampleshisTest statisticsThe calculation formula of is as follows:
V=(Array-1)
Where, A is the actual frequency of death, and T is the theoretical frequency.
When comparing several sample survival distributions.When all data are complete, this test is also called the Sovnge test.[3]
application
Announce
edit
The survival rate reflects the degree of damage to life caused by the disease, and can be used to evaluate the long-term efficacy of some diseases with a long course of disease.In some chronic diseases such asMalignant tumor、Cardiovascular disease、tuberculosisAnd so on.[4]
