| Title: | Svensson's Method |
|---|---|
| Description: | Obtain parameters of Svensson's Method, including percentage agreement, systematic change and individual change. Also, the contingency table can be generated. Svensson's Method is a rank-invariant nonparametric method for the analysis of ordered scales which measures the level of change both from systematic and individual aspects. For the details, please refer to Svensson E. Analysis of systematic and random differences between paired ordinal categorical data [dissertation]. Stockholm: Almqvist & Wiksell International; 1993. |
| Authors: | Yingyan Zhu [aut, cre] |
| Maintainer: | Yingyan Zhu <[email protected]> |
| License: | GPL-3 |
| Version: | 0.1.0 |
| Built: | 2025-02-15 05:24:45 UTC |
| Source: | https://github.com/lexizhu/svenssonm |
Generate Contingency table for Svensson's Method
con_ta(x, y, level = 5)con_ta(x, y, level = 5)
x |
a numeric vector of data values, each element range from 1 to level. |
y |
a numeric vector of data values, must have same length as x. |
level |
the dimension of the contingency table, the default is 5. |
A contingency table based on x and y.
sresult for summary of Svensson's method analysis.
x <- c (1:5,5:1) y <- c(1:5,1,1,5,4,1) con_ta(x,y,)x <- c (1:5,5:1) y <- c(1:5,1,1,5,4,1) con_ta(x,y,)
In Svensson's method, the individual change is described by the relative rank variance (RV), the observable part, and the internal rank variance (IV), the unobservable part, together. A measure of the closeness of observations to the rank transformable pattern of change is defined as the augmented correlation coefficient (ralpha) and its p-value.
rv(t) rvse(t) iv(t) ralpha(t) pralpha(t)rv(t) rvse(t) iv(t) ralpha(t) pralpha(t)
t |
The contingency table for Svensson's method, a two-dimension matrix. |
rv and iv give the RV and IV value. rvse gives the standard
error of RV. ralpha and pralpha give the augmented correlation coefficient
and the corresponding p-value.
con_ta for generating contingency table. syschange
for systematic change. sresult for summary of Svensson's method analysis.
x <- c (1:5,5:1) y <- c(1:5,1,1,5,4,1) z <- con_ta(x,y,) rv(z) rvse(z) iv(z) ralpha(z) pralpha(z)x <- c (1:5,5:1) y <- c(1:5,1,1,5,4,1) z <- con_ta(x,y,) rv(z) rvse(z) iv(z) ralpha(z) pralpha(z)
The percentage agreement (PA) which shows the proportion of the subjects who did not change their choices.
pa(t)pa(t)
t |
The contingency table for Svensson's method, a two-dimension matrix. |
pa gives the PA value, multiply by 100 to get a percentage number.
con_ta for generating contingency table. sresult for summary of
Svensson's method analysis.
x <- c (1:5,5:1) y <- c(1:5,1,1,5,4,1) z <- con_ta(x,y,) pa(z)x <- c (1:5,5:1) y <- c(1:5,1,1,5,4,1) z <- con_ta(x,y,) pa(z)
List all the results for Svensson's Method. Including percentage agreement, systematic change and individual change.
sresult(t)sresult(t)
t |
The contingency table for Svensson's method, a two-dimension matrix. |
sresult lists the results for Svensson's method. PA for percentage agreement,
RP for relative position, RC for relative concentration, RV for relative rank variance,
SE(RP), SE(RC), SE(RV) for the corresponding standard error and CI(RP), CI(RC), CI(RV) for
the 95% confidence interval. IV for internal rank variance, R.Alpha for augmented correlation
coefficient, P.R.Alpha for the corresponding p-value (significant level 0.05).
con_ta for generating contingency table.
x <- c (1:5,5:1) y <- c(1:5,1,1,5,4,1) z <- con_ta(x,y,) sresult(z)x <- c (1:5,5:1) y <- c(1:5,1,1,5,4,1) z <- con_ta(x,y,) sresult(z)
The value and the standard error of relative position (RP), the systematic change in position between the two ordered categorical classification. Also, the value and the standard error of relative concentration (RC), a comprehensive evaluation of the systematic change.
rp(t) rpse(t) rc(t) rcse(t)rp(t) rpse(t) rc(t) rcse(t)
t |
The contingency table for Svensson's method, a two-dimension matrix. |
rp and rc give the RP and RC value. rpse and rcse
give the standard error of RP and RC.
con_ta for generating contingency table. indichange
for individual change. sresult for summary of Svensson's method analysis.
x <- c (1:5,5:1) y <- c(1:5,1,1,5,4,1) z <- con_ta(x,y,) rp(z) rpse(z) rc(z) rcse(z)x <- c (1:5,5:1) y <- c(1:5,1,1,5,4,1) z <- con_ta(x,y,) rp(z) rpse(z) rc(z) rcse(z)