Dataplot Vol 1 Vol 2

# RANK CORRELATION INDEPENDENCE TEST

Name:
RANK CORRELATION INDEPENDENCE TEST
Type:
Analysis Command
Purpose:
Perform a Spearman rho rank correlation test for whether two samples are independent (i.e., not correlated).
Description:
If the measurements in the two samples are replaced with their ranks (and average ranks in the case of ties) and the Pearson correlation coefficient is computed, the result is the Spearman rho correlation coefficient.

A value of +1 indicates perfect positive correlation, a value of -1 indicates perfect negative correlation, and a value of 0 indicates no relation (i.e., independence).

The rank correlation independence test is a test whether the rank correlation coefficient is equal to zero.

For larger n (e.g., n > 30) or the case where there are many ties, the p-th upper quantile of the rank correlation statistic can be approximated by

$$w_{p} = \frac{z_{p}}{\sqrt{n-1}}$$

with zp and n denoting the p-th quantile of the standard normal distribution and the sample size, respectively. The lower quantile is the negative of the upper quantile.

For a two-sided test, the p-value is computed as twice the minimum of the lower tailed and upper tailed quantiles.

For n ≤ 30, tabulated quantiles (from Table A10 on p. 542 of Conover) are used. These quantiles are exact when there are no ties in the data.

Syntax 1:
<LOWER TAILED/UPPER TAILED> RANK CORRELATION
INDEPENDENCE TEST <y1> <y2>
<SUBSET/EXCEPT/FOR qualification>
where <LOWER TAILED/UPPER TAILED> is an optional keyword that specifies either a lower tailed or an upper tailed test;
<y1> is the first response variable;
<y2> is the second response variable;
and where the <SUBSET/EXCEPT/FOR qualification> is optional.

If neither LOWER TAILED or UPPER TAILED is specified, a two-tailed test is performed.

Lower tailed tests are used to test for negative correlation and upper tailed tests are used to test for positive correlation).

Syntax 2:
<LOWER TAILED/UPPER TAILED> RANK CORRELATION
INDEPENDENCE TEST <y1> ... <yk>
<SUBSET/EXCEPT/FOR qualification>
where <LOWER TAILED/UPPER TAILED> is an optional keyword that specifies either a lower tailed or an upper tailed test;
<y1> ... <yk> is a list of 1 to 30 response variables;
and where the <SUBSET/EXCEPT/FOR qualification> is optional.

This syntax will perform all the pair-wise tests for the <y1> ... <yk> response variables. For example,

RANK CORRELATION INDEPENDENCE TEST Y1 TO Y4

is equivalent to

RANK CORRELATION INDEPENDENCE TEST Y1 Y2
RANK CORRELATION INDEPENDENCE TEST Y1 Y3
RANK CORRELATION INDEPENDENCE TEST Y1 Y4
RANK CORRELATION INDEPENDENCE TEST Y2 Y3
RANK CORRELATION INDEPENDENCE TEST Y2 Y4
RANK CORRELATION INDEPENDENCE TEST Y3 Y4
Examples:
RANK CORRELATION INDEPENDENCE TEST Y1 Y2
RANK CORRELATION INDEPENDENCE TEST Y1 TO Y5
LOWER TAILED RANK CORRELATION INDEPENDENCE TEST Y1 Y2
UPPER TAILED RANK CORRELATION INDEPENDENCE TEST Y1 Y2
Note:
This command can be used to test for trend in a univariate variable. For example

LET N = SIZE Y
LET X = SEQUENCE 1 1 N
RANK CORRELATION INDEPENDENCE TEST Y X

According to Conover, this test is more powerful than the Cox and Stuart test. However, it is not as widely applicable as the Cox and Stuart test.

This test for trend is referred to as the Daniels test for trend.

Note:
The KENDALL TAU INDEPENDENCE TEST can be used to perform a test for independence based on the Kendall tau statistic.

The CORRELATION CONFIDENCE LIMITS command can be used to generate a confidence interval for the Pearson correlation coefficient. This can be used for a parametric test for independence (i.e., does the confidence interval contain zero?).

Note:
By default, critical values are based on tabulated values for n ≤ 30. The command

SET RANK CORRELATION CRITICAL VALUES NORMAL APPROXIMATION

can be used to specify that they should be based on the normal approximation given above. This may be preferred if there are ties in the data. To reset the default, enter the command

SET RANK CORRELATION CRITICAL VALUES TABLE
Note:
The RANK CORRELATION INDEPENDENCE TEST will accept matrix arguments. If a matrix is given, the data elements in the matrix will be collected in column order to form a vector before performing the test.
Note:
Dataplot saves the following internal parameters after a rank correlation independence test:

 STATVAL = the value of the test statistic STATCDF = the CDF of the test statistic PVALUE = the p-value for the two-sided test PVALUELT = the p-value for the lower tailed test PVALUEUT = the p-value for the upper tailed test CUTLOW90 = the 90% lower tailed critical value CUTUPP90 = the 90% upper tailed critical value CUTLOW95 = the 95% lower tailed critical value CUTUPP95 = the 95% upper tailed critical value CTLOW975 = the 97.5% lower tailed critical value CTUPP975 = the 97.5% upper tailed critical value CUTLOW99 = the 99% lower tailed critical value CUTUPP99 = the 99% upper tailed critical value CTLOW995 = the 99.5% lower tailed critical value CTUPP995 = the 99.5% upper tailed critical value CTLOW999 = the 99.9% lower tailed critical value CTUPP999 = the 99.9% upper tailed critical value
Note:
The following statistics can also be computed

LET A = RANK CORRELATION Y1 Y2
LET A = RANK CORRELATION CDF Y1 Y2
LET A = RANK CORRELATION PVALUE Y1 Y2
LET A = RANK CORRELATION LOWER TAILED PVALUE Y1 Y2
LET A = RANK CORRELATION UPPER TAILED PVALUE Y1 Y2

The cdf and p-values are based on the normal approximation given above.

Note:
The run sequence plot can be used to graphically assess whether or not there is trend in the data. The 4-plot can be used to assess the more general assumption of "independent, identically distributed" data.

The paired data can also be analyzed using other techniques for comparing two response variables (e.g., t-test, bihistogram, quantile-quantile plot).

Default:
None
Synonyms:
None
Related Commands:
 KENDALL TAU INDEPENDENCE TEST = Compute an independence test based on the Kendall tau statistic. CORRELATION CONFIDENCE LIMITS = Generate confidence limits for the Pearson correlation coefficient. COX AND STUART TEST = Compute a Cox and Stuart trend test. T-TEST = Compute a t-test. 4-PLOT = Generate a 4-plot. RUN SEQUENCE PLOT = Generate a run sequence plot. BIHISTOGRAM = Generates a bihistogram. QUANTILE-QUANTILE PLOT = Generate a quantile-quantile plot.
Reference:
Conover (1999), "Practical Nonparametric Statistics," Third Edition, Wiley, pp. 319-327.
Applications:
Confirmatory Data Analysis
Implementation Date:
2013/3
Program:

skip 25
set write decimals 5
.
let statval  = rank correlation y1 y2
let statcdf  = rank correlation cdf y1 y2
let pvalue   = rank correlation pvalue y1 y2
let pvallt   = rank correlation lower tailed pvalue y1 y2
let pvalut   = rank correlation upper tailed pvalue y1 y2
print statval statcdf pvalue pvallt pvalut
.
rank correlation independence test y1 y2
.
upper tailed rank correlation independence test y1 y2
.
set rank correlation critical values normal approximation
upper tailed rank correlation independence test y1 y2

The following output is generated.

PARAMETERS AND CONSTANTS--

STATVAL --        0.59002
STATCDF --        0.97482
PVALUE  --        0.05036
PVALLT  --        0.97482
PVALUT  --        0.02518

Two Sample Rank Correlation Test for Independence

First Response Variable:  Y1
Second Response Variable: Y2

H0: The Two Samples are Independent
Ha: The Two Samples Are Not Independent

Number of Observations:                               12

Sample One Summary Statistics:
Sample Mean:                                   587.08333
Sample Standard Deviation:                      58.01482
Sample Minimum:                                530.00000
Sample Maximum:                                740.00000

Sample Two Summary Statistics:
Sample Mean:                                     3.59999
Sample Standard Deviation:                       0.28603
Sample Minimum:                                  3.20000
Sample Maximum:                                  4.00000

Test:
Spearman Rho Rank Correlation Value:             0.59001
CDF Value (Normal Approximation):                0.97481
Two-Sided P-Value (Normal Approximation):        0.05036

Conclusions (Two-Tailed Test)

H0: Samples are Independent
------------------------------------------------------------
Null
Significance           Test       Critical     Hypothesis
Level      Statistic   Region (+/-)     Conclusion
------------------------------------------------------------
80.0%        0.59001        0.39860         REJECT
90.0%        0.59001        0.49650         REJECT
95.0%        0.59001        0.58040         REJECT
99.0%        0.59001        0.72030         ACCEPT

Two Sample Rank Correlation Test for Independence

First Response Variable:  Y1
Second Response Variable: Y2

H0: The Two Samples are Independent
Ha: The Two Samples Are Positively Correlated

Number of Observations:                                   12

Sample One Summary Statistics:
Sample Mean:                                       587.08333
Sample Standard Deviation:                          58.01482
Sample Minimum:                                    530.00000
Sample Maximum:                                    740.00000

Sample Two Summary Statistics:
Sample Mean:                                         3.59999
Sample Standard Deviation:                           0.28603
Sample Minimum:                                      3.20000
Sample Maximum:                                      4.00000

Test:
Spearman Rho Rank Correlation Value:                 0.59001
CDF Value (Normal Approximation):                    0.97481
Upper Tailed P-Value (Normal Approximation):         0.02518

Conclusions (Upper 1-Tailed Test)

H0: Samples are Independent
------------------------------------------------------------
Null
Significance           Test       Critical     Hypothesis
Level      Statistic     Region (>)     Conclusion
------------------------------------------------------------
90.0%        0.59001        0.39860         REJECT
95.0%        0.59001        0.49650         REJECT
97.5%        0.59001        0.58040         REJECT
99.0%        0.59001        0.67130         ACCEPT
99.5%        0.59001        0.72030         ACCEPT
99.9%        0.59001        0.81120         ACCEPT

Two Sample Rank Correlation Test for Independence

First Response Variable:  Y1
Second Response Variable: Y2

H0: The Two Samples are Independent
Ha: The Two Samples Are Positively Correlated

Number of Observations:                                   12

Sample One Summary Statistics:
Sample Mean:                                       587.08333
Sample Standard Deviation:                          58.01482
Sample Minimum:                                    530.00000
Sample Maximum:                                    740.00000

Sample Two Summary Statistics:
Sample Mean:                                         3.59999
Sample Standard Deviation:                           0.28603
Sample Minimum:                                      3.20000
Sample Maximum:                                      4.00000

Test:
Spearman Rho Rank Correlation Value:                 0.59001
CDF Value (Normal Approximation):                    0.97481
Upper Tailed P-Value (Normal Approximation):         0.02518

Conclusions (Upper 1-Tailed Test)

H0: Samples are Independent
------------------------------------------------------------
Null
Significance           Test       Critical     Hypothesis
Level      Statistic     Region (>)     Conclusion
------------------------------------------------------------
90.0%        0.59001        0.38640         REJECT
95.0%        0.59001        0.49594         REJECT
97.5%        0.59001        0.59095         ACCEPT
99.0%        0.59001        0.70142         ACCEPT
99.5%        0.59001        0.77664         ACCEPT
99.9%        0.59001        0.93174         ACCEPT



NIST is an agency of the U.S. Commerce Department.

Date created: 03/08/2013
Last updated: 11/04/2015