Survival analysis originated from biomedical research, and the endpoint of the study was “survival and death”, hence the name survival analysis. Survival analysis, also known as historical event analysis and failure time analysis, is currently widely used in economics, engineering, and sociology. Survival analysis is a statistical analysis method that combines the time at which an end event occurs and considers both outcomes and survival time. We can make use of incomplete data to statistically describe and statistically infer the distribution characteristics of survival time. The main influencing factors affecting survival time can also be analyzed by multi-factor model. Survival analysis methods provide a comprehensive and accurate assessment of clinical follow-up materials.
Our Services
Our statistical experts will select the appropriate survival analysis method based on the cost, operational feasibility and data type provided, making your tasks easier and more efficient.
(1) Describe the survival process. According to the sample survival data, the distribution characteristics of survival time will be studied, the survival rate and average survival time will be estimated, and the survival curve will be drawn. According to the length of survival time, the survival rate at each time point can be estimated, and the median survival time is estimated based on the survival rate. At the same time, according to the survival curve, the survival characteristics are analyzed. The data of the frequency table is analyzed by the life table method. The Kaplan-Meier method (also called the positive limit method) is often used for description and analysis. Calculating the survival rate needs to consider the order of survival time. That is a non-parametric statistical method.
(2) Comparative survival process. The survival rate of each sample can be compared by survival rate and its standard error to explore whether there is a difference in the survival process of each population. For example, comparing the effects of bcl2 and p53 protein expression on breast cancer survival rate can find important markers affecting breast cancer survival. Log-rank test or Breslow test is generally used. The null hypothesis assumes that the two or more groups have the same overall lifetime distribution, but do not specify the specific distribution form. That is also a non-parametric statistical method.
(3) Analysis of influencing factors. The focus is on exploring the factors affecting survival time through survival analysis models. Usually, survival time and outcome are used as dependent variables, and factors affecting them are used as independent variables, such as age, gender, pathological features, lymph node metastasis, treatment plan, and the expression pattern of genes. By fitting the survival analysis model, the protective factors and risk factors affecting the survival time will be screened out, which provides an important reference for clinical treatment.
(1) Nonparametric method is characterized by the fact that the data is only based on the order statistics provided by the sample to estimate the survival rate. The commonly used methods are multiplication positive limit method and life algorithm. For a comparison of two or more overall survival rates, its null hypothesis assumes that two or more sets of overall survival time distributions are the same, without inferring specific distribution patterns and parameters.
(2) Parameter method is characterized by assuming that the survival time obeys a specific parameter distribution, and then analyzing the time that affects survival according to the characteristics of the known distribution. The commonly used methods are the exponential distribution method, Weibull distribution method, lognormal regression analysis method, and Logistic regression analysis. The parameter method obtains an estimate of the survival rate from the estimated parameters and can make statistical judgments based on the parameter estimates.
(3) Semiparametric method, which combines the characteristics of parametric and nonparametric methods, is mainly used to analyze factors affecting survival time and survival rate and is a multi-factor analysis method. A typical method of the semiparametric method is the Cox model analysis method.
We guarantee the confidentiality and sensitivity of our customers' data. We are committed to providing you with timely and high-quality deliverables. At the same time, we guarantee cost-effective, complete and concise reports.
If you are unable to find the specific service you are looking for, please feel free to contact us.
References:
1. Delpla Ianis, Florea Mihai, Pelletier Geneviève et al. (2018) ‘Optimizing disinfection by-product monitoring points in a distribution system using cluster analysis’. Chemosphere, 208: 512-521.
2. Fong Allan, Clark Lindsey, Cheng Tianyi et al. (2017) ‘Identifying influential individuals on intensive care units: using cluster analysis to explore culture’. J Nurs Manag, 25(5): 384-391.
3. Gould D J, Navaie D, Purssell E et al. (2018)’Changing the paradigm: messages for hand hygiene education and audit from cluster analysis’. J. Hosp. Infect., 98(4): 345-351.