Summary

It combines common analytical methods in the medical field so it can perform quickly advanced analysis of clinical tests and integrate complete evaluation indicators when predicting diseases. Besides, it can perform quickly various medical analytical methods, including various survival analytical methods and medical efficiency analysis. Based on the usage situation how researchers are using the data analysis software, we integrate the functions and methods to get closer to researchers' needs, which enables you to get the conclusions sooner when analyzing more data.

Features

• Support for test of variability and homogeneity verification method
• Support for category test of sequence variance
• Support the test of outliers with very few samples
• Support various survival analytical methods

Applications

• Medical: Advanced survival analysis such as competition risk and parameter matching.
• Industrial: Reliability analysis, etc.
• Financial: Personal consumer loans, analysis of early warning about corporate banking, etc.
• Business: Customer Relationship Management

Methods

Kaplan-Meier Kaplan-Meier Survival Function Confidence Interval

Model :

• Kaplan-Meier Confidence Intervals

Description : Description: operating Kaplan-Meier enables us to obtain the estimated value of survival rates of this population at different time points and then to draw a survival curve; however, if needing the confidence interval of this curve, we can use this module to deal with the confidence interval of Kaplan-Meier survival rates and to set the confidence level parameter to meet users’ needs.

Application : Take Kaplan-Meier survival parameter as basis to estimate the survival rates and confidence interval at different time points in a chart to give a complete presentation.

Cox Proportional Hazard Cox Proportional Hazard hypothetical diagnosis

Model :

• Diagnostics for Cox Regression Model

Description : Cox Proportional Hazard Regression is a common used regression model in survival analysis. However, the ratio meeting the risk function needs to be a constant, i.e. Proportional Hazard Assumption. And this module can serve as an assumption to see if the diagnostic data can meet the proportional hazard so that you can avoid unsuitable analytical methods.

Application : Before conducting Cox proportional hazard regression, it is better to check if the data meets the assumptions of this analytical method to ensure the correct post-analysis.

Parametric Survival Analysis

Model :

• Survival Distribution Identification
• Parametric Regression
• Parametric Proportional Hazards Regression
• Parametric AFT Regression

Description : Most survival analyses use nonparametric or semi-parametric analysis because the distribution of survival time is usually quite extreme or unknown; however, you can also try to fit the survival time to specific probability distribution and use this probability distribution to construct Parametric Regression, Parametric Proportional Hazards Regression (Proportional Hazard Model) and Parametric AFT Regression. You can make a description of the survival data according to features of the probability distribution.

Application : If your data doesn’t meet the assumption of proportional hazard, you can consider to fit the survival data to probability distribution, and then conduct the relevant regression models to construct a smooth survival curve, which will be easier to estimate and to explain your survival data.

Competing Risks Competing Risks Survival Analysis

Model :

• Competing risk CIF
• Competing risk Regression

Description : In the actual life, there may be more than one cause to an event, that means that there are multi-causes to the occurrence to the samples, also known as Competing Risk, which can count Cumulative Incidence Function in different groups and construct Competing risk Regression.

Application : It is applicable to survival data that there are more than one cause to the event (e.g. stroke patients often have multiple comorbidities so we need a survival analysis to evaluate many causes of death), and to construct its survival model to find out important impact factors .

System Requirements

Suggestion for installing IBM SPSS Statistics Base:

• Windows XP，2000，WIN 7
• Intel Pentium-compatible CPU
• Memory: ≧512MB RAM
• Hard Disk Space: ≧1 GB
• SVGA Display
• Internet Explorer 6