spearman -- Compute the generalized Spearman's rho correlation coefficient.
The spearman task computes the generalized Spearman's rank order correlation coefficient between two variables. It can treat mixed censoring including censoring in the independent variable, but can have only one independent variable. It is not known how this method responds to ties in the data. However, there is no reason to believe that it is more accurate than Kendall's tau in this case, and it should also used be with caution in the presence of tied values.
The test assumes the null hypothesis. The probability given by this program is the probability that there is no correlation between the variables. If the probability is small, that means "the probability that these two variables are not correlated is small" or approximately "these variables are correlated". If you see the result 0.000, it means "< 0.001".
The usual Spearman's rho correlation estimate for uncensored data is simply the correlation between the ranks of the independent and dependent variables. In order to extend the procedure to censored data, the Kaplan-Meier estimate of the survival curve is used to assign ranks to the observations. Consequently, the ranks assigned to the observations may not be whole numbers. Censored points are assigned half (for left-censored) or twice (for right-censored) the rank that they would have had were they uncensored. This method is based on preliminary findings and has not been carefully scrutinized either theoretically or empirically. It is offered in the code to serve as a less computer intensive approximation to the Kendall's tau correlation, which becomes computationally infeasible for large data sets. The generalized Spearman's Rho routine is not dependable for small data sets (n < 30). In that situation the generalized Kendall's tau routine (bhkmethod) should be relied upon.
- input [string]
- Input file(s); this can be a list of files. Following each file name is a list of column names in brackets. Thes column names specify which columns in the file contain the information used by this task. The brackets MUST contain three names in the following format: [censor_indicator, independent_var, dependent_var]. The censor indicator specifies the censorship of the data point. The different kinds of censorship are explained in the censor help file. The second name in the brackets specifies the column containing the independent variable. The third name specifies the column containing the dependent variable. If the input file is an STSDAS table, the names in brackets are the table column names. If the input file is a text file, the names in brackets are the column numbers. A title string will be printed if the input file is a table containing the header parameter TITLE.
- (verbose = no) [boolean]
- Provide detailed output?
The detailed output includes the number of data points and the number of censored points and type of censorship.
1. Sequentially process several files. The following will compute the bhk correlation for the two files indicated. The first is an STSDAS table, and the second is a text file.
st> spearman kriss.tab[Censor,LogL2500A,LogL2keV],iraslum.dat[1,2,3]The above command will apply the spearman task to the data in the table "kriss.tab", using the columns "Censor" for the censoring indicator, "LogL2500A" for the independent variable column, and "LogL2keV" for the dependent variable column. Then use the file "iraslum.dat" (text file), columns 1, 2, and 3 (censor, independent, dependent).
Type "help statistics option=sys" for a higher-level description of the statistics package.