|
COEFFICIENT OF QUARTILE DISPERSION CONFIDENCE LIMITSName:
where \( s \) and \( \bar{x} \) denote the sample standard deviation and sample mean respectively. The coefficient of variation is sensitive to non-normality. An alternative statistic is the coefficient of dispersion which is defined as
with \( \tau \) and \( \eta \) denoting the mean absolute difference from the mean and the median, respectively. Another alternative is the coefficient of quartile dispersion which is defined as
with Q1 denoting the lower quartile (the 25-th percentile) and Q3 denoting the upper quartile (the 75-th percentile). These coefficients should typically only be used for ratio data. That is, the data should be continuous and have a meaningful zero. Although these statistics can be computed for data that is not on a ratio scale, the interpretation of them may not be meaningful. Currently, this command is only supported for non-negative data. If the response variable contains one or more negative numbers, an error message will be returned. The method for computing the coefficient of quartile dispersion confidence limit is from the Bonett paper (see References below). See the Bonett paper for the derivation and formula for this interval. Bonett recommends the coefficient of variation for normal (or nearly normal) data, the coefficient of dispersion for moderately non-normal data, and the coefficient of quartile dispersion given here for more extreme non-normal data.
CONFIDENCE LIMITS <y> <SUBSET/EXCEPT/FOR qualification> where <y> is the response variable; and where the <SUBSET/EXCEPT/FOR qualification> is optional. If LOWER is specified, a one-sided lower confidence limit is returned. If UPPER is specified, a one-sided upper confidence limit is returned. If neither is specified, a two-sided limit is returned. This syntax supports matrix arguments for the response variable.
CONFIDENCE LIMITS <y1> ... <yk> <SUBSET/EXCEPT/FOR qualification> where <y1> .... <yk> is a list of 1 to 30 response variables; and where the <SUBSET/EXCEPT/FOR qualification> is optional. This syntax will generate a confidence interval for each of the response variables. The word MULTIPLE is optional. That is,
LIMITS Y1 Y2 Y3 is equivalent to
Y1 Y2 Y3 You can also use the TO syntax as in
Y1 TO Y10 If LOWER is specified, a one-sided lower confidence limit is returned. If UPPER is specified, a one-sided upper confidence limit is returned. If neither is specified, a two-sided limit is returned. This syntax supports matrix arguments for the response variables.
CONFIDENCE LIMITS <y> <x1> ... <xk> <SUBSET/EXCEPT/FOR qualification> where <y> is the response variable; <x1> .... <xk> is a list of 1 to 6 group-id variables; and where the <SUBSET/EXCEPT/FOR qualification> is optional. This syntax performs a cross-tabulation of the <x1> ... <xk> and generates a confidence interval for each unique combination of the cross-tabulated values. For example, if X1 has 3 levels and X2 has 2 levels, six confidence intervals will be generated. If LOWER is specified, a one-sided lower confidence limit is returned. If UPPER is specified, a one-sided upper confidence limit is returned. If neither is specified, a two-sided limit is returned. This syntax does not support matrix arguments.
COEFFICIENT OF QUARTILE DISPERSION CONFIDENCE LIMITS Y1 ... SUBSET TAG > 2 MULTIPLE COEFFICIENT OF QUARTILE DISPERSION CONFIDENCE LIMITS Y1 TO Y5 REPLICATED COEFFICIENT OF QUARTILE DISPERSION CONFIDENCE LIMITS Y X
Although Bonett does not specify which method he uses to compute the Q1 and Q3 values, it appears as if he is taking the mean of the two closest points. To use this method to compute Q1 and Q3, enter the command
Dataplot provides three additional methods (called R6, R7, and R8). Enter HELP QUANTILE for details on how these methods compute the quantiles. To use one of these methods, enter one of the following commands
SET QUANTILE METHOD R7 SET QUANTILE METHOD R8 The default method in Dataplot is R6. As the sample size gets larger, this should be less of an issue.
LET A = LOWER COEFFICIENT OF QUARTILE DISPERSION CONFIDENCE LIMIT Y In addition to the above LET commands, built-in statistics are supported for 20+ different commands (enter HELP STATISTICS for details).
QUARTILE COEFFICIENT OF DISPEERSION CONFIDENCE LIMITS QUARTILE COEFFICIENT OF VARIATION CONFIDENCE LIMITS
Bonett and Seier (2006), "Confidence Interval for a Coefficient of Dispersion", Biometrical Journal, Vol. 48, No. 1, pp. 144-148.
. Following data from Bonett paper
.
LET Y = DATA 0.2 0.5 1.1 1.4 1.8 2.3 2.5 2.7 3.5 4.4 4.6 5.4 5.4 ...
5.7 5.8 5.9 6.0 6.6 7.1 7.9
.
SET WRITE DECIMALS 5
SET QUANTILE METHOD AVERAGE
COEFFICIENT OF QUARTILE DISPERSION CONFIDENCE LIMITS Y
.
LET ALPHA = 0.05
LET CQV = COEFFICIENT OF QUARTILE DISPERSION Y
LET LCDL = LOWER COEFFICIENT OF QUARTILE DISPERSION CONFIDENCE LIMIT Y
LET UCDL = UPPER COEFFICIENT OF QUARTILE DISPERSION CONFIDENCE LIMIT Y
.
PRINT CQV LCDL UCDL
The following output is generated
Two-Sided Confidence Limit for the Coefficient of
Quartile Dispersion
Response Variable: Y
Summary Statistics:
Number of Observations: 20
Sample Lower Quartile: 2.05000
Sample Upper Quartile: 5.85000
Quantile Method: Average
Sample Coefficient of Quartile Disp: 0.48101
---------------------------------------------------------------
Confidence Coefficient of Lower Upper
Value (%) Quartile Dispersion Limit Limit
---------------------------------------------------------------
80.0 0.48101 0.34624 0.61870
90.0 0.48101 0.28164 0.76061
95.0 0.48101 0.25607 0.83655
99.0 0.48101 0.20089 1.06636
99.9 0.48101 0.15464 1.38523
PARAMETERS AND CONSTANTS--
CQV -- 0.48101
LCDL -- 0.25607
UCDL -- 0.83655
Program 2:
SKIP 25
READ GEAR.DAT Y X
.
SET WRITE DECIMALS 5
SET QUANTILE METHOD AVERAGE
REPLICATED COEFFICIENT OF QUARTILE DISPERSION CONFIDENCE LIMITS Y X
The following output is generated
Two-Sided Confidence Limit for the Coefficient of
Quartile Dispersion
Response Variable: Y
Factor Variable 1: X 1.00000
Summary Statistics:
Number of Observations: 10
Sample Lower Quartile: 0.99350
Sample Upper Quartile: 1.00000
Quantile Method: Average
Sample Coefficient of Quartile Disp: 0.00326
---------------------------------------------------------------
Confidence Coefficient of Lower Upper
Value (%) Quartile Dispersion Limit Limit
---------------------------------------------------------------
80.0 0.00326 0.00105 0.00284
90.0 0.00326 0.00091 0.00327
95.0 0.00326 0.00082 0.00361
99.0 0.00326 0.00057 0.00522
99.9 0.00326 0.00035 0.00847
Two-Sided Confidence Limit for the Coefficient of
Quartile Dispersion
Response Variable: Y
Factor Variable 1: X 2.00000
Summary Statistics:
Number of Observations: 10
Sample Lower Quartile: 0.99650
Sample Upper Quartile: 1.00100
Quantile Method: Average
Sample Coefficient of Quartile Disp: 0.00225
---------------------------------------------------------------
Confidence Coefficient of Lower Upper
Value (%) Quartile Dispersion Limit Limit
---------------------------------------------------------------
80.0 0.00225 0.00045 0.00291
90.0 0.00225 0.00035 0.00379
95.0 0.00225 0.00026 0.00500
99.0 0.00225 0.00018 0.00711
99.9 0.00225 0.00008 0.01651
Two-Sided Confidence Limit for the Coefficient of
Quartile Dispersion
Response Variable: Y
Factor Variable 1: X 3.00000
Summary Statistics:
Number of Observations: 10
Sample Lower Quartile: 0.99250
Sample Upper Quartile: 0.99800
Quantile Method: Average
Sample Coefficient of Quartile Disp: 0.00276
---------------------------------------------------------------
Confidence Coefficient of Lower Upper
Value (%) Quartile Dispersion Limit Limit
---------------------------------------------------------------
80.0 0.00276 0.00074 0.00280
90.0 0.00276 0.00061 0.00338
95.0 0.00276 0.00061 0.00339
99.0 0.00276 0.00044 0.00474
99.9 0.00276 0.00024 0.00875
Two-Sided Confidence Limit for the Coefficient of
Quartile Dispersion
Response Variable: Y
Factor Variable 1: X 4.00000
Summary Statistics:
Number of Observations: 10
Sample Lower Quartile: 0.99450
Sample Upper Quartile: 1.00100
Quantile Method: Average
Sample Coefficient of Quartile Disp: 0.00326
---------------------------------------------------------------
Confidence Coefficient of Lower Upper
Value (%) Quartile Dispersion Limit Limit
---------------------------------------------------------------
80.0 0.00326 0.00112 0.00266
90.0 0.00326 0.00099 0.00301
95.0 0.00326 0.00084 0.00356
99.0 0.00326 0.00067 0.00444
99.9 0.00326 0.00043 0.00696
Two-Sided Confidence Limit for the Coefficient of
Quartile Dispersion
Response Variable: Y
Factor Variable 1: X 5.00000
Summary Statistics:
Number of Observations: 10
Sample Lower Quartile: 0.98300
Sample Upper Quartile: 0.99700
Quantile Method: Average
Sample Coefficient of Quartile Disp: 0.00707
---------------------------------------------------------------
Confidence Coefficient of Lower Upper
Value (%) Quartile Dispersion Limit Limit
---------------------------------------------------------------
80.0 0.00707 0.00279 0.00597
90.0 0.00707 0.00250 0.00665
95.0 0.00707 0.00220 0.00755
99.0 0.00707 0.00182 0.00915
99.9 0.00707 0.00113 0.01470
Two-Sided Confidence Limit for the Coefficient of
Quartile Dispersion
Response Variable: Y
Factor Variable 1: X 6.00000
Summary Statistics:
Number of Observations: 10
Sample Lower Quartile: 0.99150
Sample Upper Quartile: 1.00550
Quantile Method: Average
Sample Coefficient of Quartile Disp: 0.00701
---------------------------------------------------------------
Confidence Coefficient of Lower Upper
Value (%) Quartile Dispersion Limit Limit
---------------------------------------------------------------
80.0 0.00701 0.00234 0.00699
90.0 0.00701 0.00200 0.00817
95.0 0.00701 0.00190 0.00858
99.0 0.00701 0.00136 0.01197
99.9 0.00701 0.00072 0.02258
Two-Sided Confidence Limit for the Coefficient of
Quartile Dispersion
Response Variable: Y
Factor Variable 1: X 7.00000
Summary Statistics:
Number of Observations: 10
Sample Lower Quartile: 0.99600
Sample Upper Quartile: 1.00300
Quantile Method: Average
Sample Coefficient of Quartile Disp: 0.00350
---------------------------------------------------------------
Confidence Coefficient of Lower Upper
Value (%) Quartile Dispersion Limit Limit
---------------------------------------------------------------
80.0 0.00350 0.00068 0.00514
90.0 0.00350 0.00051 0.00686
95.0 0.00350 0.00046 0.00752
99.0 0.00350 0.00028 0.01263
99.9 0.00350 0.00013 0.02730
Two-Sided Confidence Limit for the Coefficient of
Quartile Dispersion
Response Variable: Y
Factor Variable 1: X 8.00000
Summary Statistics:
Number of Observations: 10
Sample Lower Quartile: 0.99700
Sample Upper Quartile: 1.00200
Quantile Method: Average
Sample Coefficient of Quartile Disp: 0.00250
---------------------------------------------------------------
Confidence Coefficient of Lower Upper
Value (%) Quartile Dispersion Limit Limit
---------------------------------------------------------------
80.0 0.00250 0.00077 0.00215
90.0 0.00250 0.00067 0.00248
95.0 0.00250 0.00066 0.00249
99.0 0.00250 0.00042 0.00397
99.9 0.00250 0.00031 0.00533
Two-Sided Confidence Limit for the Coefficient of
Quartile Dispersion
Response Variable: Y
Factor Variable 1: X 9.00000
Summary Statistics:
Number of Observations: 10
Sample Lower Quartile: 0.99550
Sample Upper Quartile: 1.00050
Quantile Method: Average
Sample Coefficient of Quartile Disp: 0.00251
---------------------------------------------------------------
Confidence Coefficient of Lower Upper
Value (%) Quartile Dispersion Limit Limit
---------------------------------------------------------------
80.0 0.00251 0.00067 0.00246
90.0 0.00251 0.00056 0.00295
95.0 0.00251 0.00056 0.00297
99.0 0.00251 0.00036 0.00456
99.9 0.00251 0.00018 0.00899
Two-Sided Confidence Limit for the Coefficient of
Quartile Dispersion
Response Variable: Y
Factor Variable 1: X 10.00000
Summary Statistics:
Number of Observations: 10
Sample Lower Quartile: 0.99100
Sample Upper Quartile: 0.99700
Quantile Method: Average
Sample Coefficient of Quartile Disp: 0.00302
---------------------------------------------------------------
Confidence Coefficient of Lower Upper
Value (%) Quartile Dispersion Limit Limit
---------------------------------------------------------------
80.0 0.00302 0.00073 0.00345
90.0 0.00302 0.00058 0.00430
95.0 0.00302 0.00047 0.00531
99.0 0.00302 0.00034 0.00740
99.9 0.00302 0.00018 0.01374
Date created: 12/12/2017 |
Last updated: 12/11/2023 Please email comments on this WWW page to [email protected]. | |||||||||||||||||||||||||||||||