The CoxPH function outputs information to the summary table, coefficient table, and linear predictor table.
The following table describes the information that the function outputs to the summary table.
| Column Name | Contents |
|---|---|
| predictor | One row for each feature specified by the FeatureColumns argument |
| category | Category name if the predictor is categorical. |
| coefficient | Estimated coefficient of the input parameters |
| exp_coef | Exponent of the coefficient (The exponent of the coefficient represents the increase in units of hazard when the covariate increases by 1.) |
| std_error | Standard error of the coefficient |
| z_score | Wald test statistic for the coefficient (The Wald test statistic assumes that the coefficient has a normal distribution; that is, N(0, std_error.)) |
| p_value | p value for the z score (The p value represents the significance of each individual coefficient.) |
| significance | Significance code for the p_value (see the following table) |
| p_value | Significance Code |
|---|---|
| [0, 0.001) | *** |
| [0.001, 0.01) | ** |
| [0.01, 0.05) | * |
| [0.05, 0.1) | . |
| [0.1, 1] |
Following the summary table, the function displays the values of the following:
- Iteration#
- Convergence
- Likelikhood ratio test
- Wald test
- Score test
- Degree of freedom
The following table describes the schema of the coefficient table.
| Column Name | Data Type | Description |
|---|---|---|
| id | INTEGER | Row identifier |
| predictor | VARCHAR | Feature column name |
| coefficient | DOUBLE PRECISION | Estimated coefficient of the input parameters |
| exp_coef | DOUBLE PRECISION | Exponent of the coefficient |
| std_error | DOUBLE PRECISION | Standard error of the coefficient |
| z_score | DOUBLE PRECISION | Wald test statistic for the coefficient |
| p_value | DOUBLE PRECISION | p value for the z score |
| significance | VARCHAR | Significance code |
The following table describes the schema of the linear predictor table.
| Column Name | Data Type | Description |
|---|---|---|
| linear_predictor | DOUBLE PRECISION | Contains the k fixed covariates and coefficients of the input parameters. |
| event | INTEGER | Contains 1 if the event occurred before the time interval ended, 0 otherwise. |
| time_interval | INTEGER | Contains the time intervals of the input data; that is, end_time - start_time, in any unit of time (for example, years, months, or days). |
| accumulate_column | Any | Column copied from input_table. The linear predictor table has one such column for each column specified by the Accumulate argument. |