| Title: | Test for Indifference of Indicator |
|---|---|
| Description: | Provides item exclusion procedure, which is a formal method to test 'Indifference Of iNdicator' (ION). When a latent personality trait-outcome association is assumed, then the association strength should not depend on which subset of indicators (i.e. items) has been chosen to reflect the trait. Personality traits are often measured (reflected) by a sum-score of a certain set of indicators. Item exclusion procedure randomly excludes items from a sum-score and tests, whether the sum-score - outcome correlation changes. ION has been achieved, when any item can be excluded from the sum-score without the sum-score - outcome correlation substantially changing . For more details, see Vainik, Mottus et. al, (2015) "Are Trait-Outcome Associations Caused by Scales or Particular Items? Example Analysis of Personality Facets and BMI",European Journal of Personality DOI: <10.1002/per.2009> . |
| Authors: | Uku Vainik <[email protected]>, Rene Mottus <[email protected]> |
| Maintainer: | Uku Vainik <[email protected]> |
| License: | GPL (>= 2) |
| Version: | 0.3.0 |
| Built: | 2024-11-20 03:03:44 UTC |
| Source: | https://github.com/cran/ionr |
Used by scenario_plot.
ciplotter(cix, ciy.lo, ciy.hi, eps, ...)ciplotter(cix, ciy.lo, ciy.hi, eps, ...)
cix |
values of the x axis |
ciy.lo |
spread of confidence intervals |
ciy.hi |
spread of confidence intervals |
eps |
width of the whiskars |
... |
additional base plot arguments |
For each item, correlation between the scale's sum scores and outcome is
calculated such that the particular item is excluded from the sum scores. Each of the
obtained correlations will then be compared with the original scale–outcome correlation
(sum score of all items). This comparison can be conducted with William's test for two
dependent correlations that share one variable (Steiger, 1980), using
r.test from psych. William's test characterises difference
between correlations with a p-value—a small p-value indicates that the tested
difference between correlations is unlikely to have happened by chance and could be
considered a real difference. Thus, each item will receive a p-value characterising
the 'significance' of difference between correlations—here called 'Significance Of
iNdicator Exclusion' (SONE). When one item is excluded, another round is begun
until no more items should be excluded.
ind_excl(indicators, indicators2 = vector(), outcome, covars = NULL, scalename = "scale", outcomename = "outcome", indicatornames = 1:ncol(indicators), pcrit, location1 = "topleft", location2 = "topright", draw = F, subset = vector(), coruse = "everything", multi = 1, verbose = F, ci = "estimate")ind_excl(indicators, indicators2 = vector(), outcome, covars = NULL, scalename = "scale", outcomename = "outcome", indicatornames = 1:ncol(indicators), pcrit, location1 = "topleft", location2 = "topright", draw = F, subset = vector(), coruse = "everything", multi = 1, verbose = F, ci = "estimate")
indicators |
Set of numeric indicators (items) in a matrix. |
indicators2 |
An additional set of indicators (e.g. informant-report ) |
outcome |
A numeric outcome vector. Indicators and outcome can be simulated with
|
covars |
A data frame with covariates to take into account. The outcome is residualised for these covariates. For instance, BMI was residualised for age, gender, and education in Vainik et al. (2015) EJP. |
scalename |
A string for labelling the scale |
outcomename |
A string for labelling the outcome |
indicatornames |
An array of strings for labelling the outcome. Default to numbers from 1 to n of indicators |
pcrit |
a p-value characterising the ‘significance’ of difference between
correlations—here called ‘significance of indicator exclusion’ (SONE). Look it up
from Table 2 in Vainik, Mõttus et al 2015, or simulate using
|
location1 |
Location for legends at left-side plot |
location2 |
Location for legends at right-side plot |
draw |
TRUE plots the result to a .tiff file in the working directory. Defaults to FALSE |
subset |
Allows exluding certain indicators from the start. Use numbers |
coruse |
argument for function cor(). Defaults to 'everything', as simulations have no missing data. |
multi |
influences cex of certain plot variables. Defaults to 1 |
verbose |
option for observing steps for debugging. Defaults to FALSE |
ci |
should output object and plot have 95
CI-s from |
Plots results using , using barplot2 from gplots.
Also returns scale-outcome correlation magnitude(s) and their comparison, if
appropriate
### Create a scale-outcome set that violates IOn_ Only 2 indicators out of 8 ### relate to the outcome, the others just relate to the 2 indicators. This setting is ### similar to the N5: Impulsiveness - BMI association in Vainik et al (2015) EJP paper. set.seed(466) a<-scale_sim(n=2500, to_n=2, tn_n=6) # Last 2 indicators have considerably higher correlation with the outcome ind_excl(a[[1]], outcome=a[[2]], pcrit=0.0037) ## boostrapped confidence intervals ind_excl(a[[1]], outcome=a[[2]], pcrit=0.0037, ci=100) # no confidence intervals ind_excl(a[[1]], outcome=a[[2]], pcrit=0.0037, ci="no") ## include covariates in the model covx=rnorm(2500) covy=rnorm(2500) outcome=a[[2]]+0.3*covx+0.4*covy covars=data.frame(covx=covx, covy=covy) # ind_excl() with covariates taken into account ind_excl(a[[1]],outcome=outcome,covars=covars, pcrit=0.0037) #effect sizes are lower when noisy covariatse are not accounted for ind_excl(a[[1]],outcome=outcome, pcrit=0.0037) # just a single covariate also needs to be in data frame covx=rnorm(2500) outcome=a[[2]]+0.3*covx covars=data.frame(covx=covx) ind_excl(a[[1]],outcome=outcome,covars=covars, pcrit=0.0037) ### Create a scale-outcome set that has ION, all 8 indicators relate to the outcome set.seed(466) b<-scale_sim(n=2500, to_n=8, cor_to_outcome = 0.35) # All indicators correlate largely on the same level with the outcome. ind_excl(b[[1]], outcome=b[[2]], pcrit=1.7*10^-4) #note that using cor_to_outcome=0.25, sometimes still indicators get wrongly flagged. # Here, the method could probably be improved.. ### Create a scale-outcome set that violates ION - only 1 indicator relates to the ### outcome. Include other-report. set.seed(466) c<-scale_sim(n=2500, to_n=1, tn_n=7, indicators2=TRUE) # Last indicator has considerably higher correlation with the outcome ind_excl(c[[1]], c[[3]], outcome=c[[2]], pcrit=0.0037)### Create a scale-outcome set that violates IOn_ Only 2 indicators out of 8 ### relate to the outcome, the others just relate to the 2 indicators. This setting is ### similar to the N5: Impulsiveness - BMI association in Vainik et al (2015) EJP paper. set.seed(466) a<-scale_sim(n=2500, to_n=2, tn_n=6) # Last 2 indicators have considerably higher correlation with the outcome ind_excl(a[[1]], outcome=a[[2]], pcrit=0.0037) ## boostrapped confidence intervals ind_excl(a[[1]], outcome=a[[2]], pcrit=0.0037, ci=100) # no confidence intervals ind_excl(a[[1]], outcome=a[[2]], pcrit=0.0037, ci="no") ## include covariates in the model covx=rnorm(2500) covy=rnorm(2500) outcome=a[[2]]+0.3*covx+0.4*covy covars=data.frame(covx=covx, covy=covy) # ind_excl() with covariates taken into account ind_excl(a[[1]],outcome=outcome,covars=covars, pcrit=0.0037) #effect sizes are lower when noisy covariatse are not accounted for ind_excl(a[[1]],outcome=outcome, pcrit=0.0037) # just a single covariate also needs to be in data frame covx=rnorm(2500) outcome=a[[2]]+0.3*covx covars=data.frame(covx=covx) ind_excl(a[[1]],outcome=outcome,covars=covars, pcrit=0.0037) ### Create a scale-outcome set that has ION, all 8 indicators relate to the outcome set.seed(466) b<-scale_sim(n=2500, to_n=8, cor_to_outcome = 0.35) # All indicators correlate largely on the same level with the outcome. ind_excl(b[[1]], outcome=b[[2]], pcrit=1.7*10^-4) #note that using cor_to_outcome=0.25, sometimes still indicators get wrongly flagged. # Here, the method could probably be improved.. ### Create a scale-outcome set that violates ION - only 1 indicator relates to the ### outcome. Include other-report. set.seed(466) c<-scale_sim(n=2500, to_n=1, tn_n=7, indicators2=TRUE) # Last indicator has considerably higher correlation with the outcome ind_excl(c[[1]], c[[3]], outcome=c[[2]], pcrit=0.0037)
See ind_excl for details.
ind_excl_inc(indicators, outcome, indicatornames = 1:ncol(indicators), pcrit = 0.05, verbose = F, coruse = "everything")ind_excl_inc(indicators, outcome, indicatornames = 1:ncol(indicators), pcrit = 0.05, verbose = F, coruse = "everything")
indicators |
Set of numeric indicators (items) in a matrix. |
outcome |
A numeric outcome vector. Indicators and outcome can be simulated with
|
indicatornames |
An array of strings for labelling the outcome. Default to numbers from 1 to n of indicators |
pcrit |
a p-value characterising the ‘significance’ of difference between
correlations—here called ‘significance of indicator exclusion’ (SONE). Look it up
from Table 2 in Vainik, Mõttus et al 2015, or simulate using
|
verbose |
option for observing steps for debugging. Defaults to FALSE |
coruse |
argument for function cor(). Defaults to 'everything', as simulations have no missing data. |
Provides the results of a single step in indicator exclusion procedure. See example for details
## Create a scale-outcome set that violates ION. Only 2 last indicators out of 8 ## relate to the outcome, the others just relate to the 2 indicators set.seed(466) a<-scale_sim(n=2500, to_n=2, tn_n=6) # run the exclusion procedure. Pcrit taken from Table 2 in Vainik et al., 2015, # European Journal of Personality res=ind_excl_inc(a[[1]],a[[2]], pcrit=0.0037) # which indicators does the procedure exclude? res## Create a scale-outcome set that violates ION. Only 2 last indicators out of 8 ## relate to the outcome, the others just relate to the 2 indicators set.seed(466) a<-scale_sim(n=2500, to_n=2, tn_n=6) # run the exclusion procedure. Pcrit taken from Table 2 in Vainik et al., 2015, # European Journal of Personality res=ind_excl_inc(a[[1]],a[[2]], pcrit=0.0037) # which indicators does the procedure exclude? res
Provides an overview of the indicator exclusion results. Marked(x) indicators are excluded in the indicator exclusion procedure. See ind_excl for details.
correlations between single indicator and outcome
correlations between sum-score and outcome with and without the marked indicators
ind_excl_plot(indicators, indicators2 = vector(), outcome, scalename = "scale", outcomename = "outcome", indicatornames = 1:ncol(indicators), tagged = vector(), tagged2 = vector(), location1 = "topleft", location2 = "topright", pcrit = 0.05, multi = 1, coruse = "everything", ci = "estimate")ind_excl_plot(indicators, indicators2 = vector(), outcome, scalename = "scale", outcomename = "outcome", indicatornames = 1:ncol(indicators), tagged = vector(), tagged2 = vector(), location1 = "topleft", location2 = "topright", pcrit = 0.05, multi = 1, coruse = "everything", ci = "estimate")
indicators |
Set of numeric indicators (items) in a matrix. |
indicators2 |
An additional set of indicators (e.g. informant-report ) |
outcome |
A numeric outcome vector. Indicators and outcome can be simulated with
|
scalename |
A string for labelling the scale |
outcomename |
A string for labelling the outcome |
indicatornames |
An array of strings for labelling the outcome. Default to numbers from 1 to n of indicators |
tagged |
items to be marked as excluded by the indicator exclusion procedure |
tagged2 |
same as 'tagged' for second scale (e.g., informant report) |
location1 |
Location for legends at left-side plot |
location2 |
Location for legends at right-side plot |
pcrit |
a p-value characterising the ‘significance’ of difference between
correlations—here called ‘significance of indicator exclusion’ (SONE). Look it up
from Table 2 in Vainik, Mõttus et al 2015, or simulate using
|
multi |
influences cex of certain plot variables. Defaults to 1 |
coruse |
argument for function cor(). Defaults to 'everything', as simulations have no missing data. |
ci |
should output object and plot have 95
CI-s from |
See ind_excl
See ind_excl for details.
ind_excl_step(indicators, outcome, indicatornames = 1:ncol(indicators), exclude = vector(), coruse = "everything", round = F)ind_excl_step(indicators, outcome, indicatornames = 1:ncol(indicators), exclude = vector(), coruse = "everything", round = F)
indicators |
Set of numeric indicators (items) in a matrix. |
outcome |
A numeric outcome vector. Indicators and outcome can be simulated with
|
indicatornames |
An array of strings for labelling the outcome. Default to numbers from 1 to n of indicators |
exclude |
Exclude an item excluded at previous step, e.g., as decided by |
coruse |
argument for function cor(). Defaults to 'everything', as simulations have no missing data. |
round |
Allows rounding of values in returned matrix. |
Provides the results of a single step in indicator exclusion procedure. See example for details
## Create a scale-outcome set that violates ION. Only 2 indicators out of 8 relate to ## the outcome, the others just relate to the 2 indicators set.seed(466) a<-scale_sim(n=2500, to_n=2, tn_n=6) res=ind_excl_step(a[[1]],a[[2]]) print(res) # note that the p-values for upper items (7 & 8 ) are much smaller than for the rest #row number indicator number #r.test.t t value of the r.test. #t.test.p p value of the r.test. #cor_excl correlation between outcome and sum-score when an item is excluded. #cor_all correlation between outcome and sum-score when all items are included # (i.e., full scale). #cor.excl_all correlation between two sum-scores.## Create a scale-outcome set that violates ION. Only 2 indicators out of 8 relate to ## the outcome, the others just relate to the 2 indicators set.seed(466) a<-scale_sim(n=2500, to_n=2, tn_n=6) res=ind_excl_step(a[[1]],a[[2]]) print(res) # note that the p-values for upper items (7 & 8 ) are much smaller than for the rest #row number indicator number #r.test.t t value of the r.test. #t.test.p p value of the r.test. #cor_excl correlation between outcome and sum-score when an item is excluded. #cor_all correlation between outcome and sum-score when all items are included # (i.e., full scale). #cor.excl_all correlation between two sum-scores.
a wrapper that runs the maximum and minimum scenarios using scenario_sim and provides the optimal p -value
optimal_p(sizes, n_sim = 100, plotting = "", n_indicators = 8, to_min = (round((n_indicators/2), 0)) - 1, ...)optimal_p(sizes, n_sim = 100, plotting = "", n_indicators = 8, to_min = (round((n_indicators/2), 0)) - 1, ...)
sizes |
An array of sample sizes to be simulated. Can be single value. |
n_sim |
number of simulations. 1000 is a start, 10000 was used in paper, but takes a long time |
plotting |
Plots the result with |
n_indicators |
How many many indicators are there in a scale. The package is tested with 8 indicators (default), but should work with other number. |
to_min |
How many indicators relate to the outcome in the lack of ION condition. In |
... |
further tweaking of the scale simulator, see |
Returns the P criterion, as well as the p values for max and min scenario for each sample size. If min pvalue > max pvalue, then p criterion is NA.
set.seed(466) n_sim=100 ptm <- proc.time() a=optimal_p(sizes=750, n_sim=n_sim, n_indicators=8, cor_to_outcome=0.25) stp=proc.time() - ptm print(paste("Currently elapsed:",round(stp[3],1))) print(paste("Time estimate for n_sim=5000:",round(stp[3]*5000/n_sim,1)))set.seed(466) n_sim=100 ptm <- proc.time() a=optimal_p(sizes=750, n_sim=n_sim, n_indicators=8, cor_to_outcome=0.25) stp=proc.time() - ptm print(paste("Currently elapsed:",round(stp[3],1))) print(paste("Time estimate for n_sim=5000:",round(stp[3]*5000/n_sim,1)))
Takes max and min scenarious and produces a table and optionally a plot.
See scenario_sim or optimal_p.
optimal_p_out(scenario_max, scenario_min, sizes, n_sim, to_min, plotting = "", multi = 1)optimal_p_out(scenario_max, scenario_min, sizes, n_sim, to_min, plotting = "", multi = 1)
scenario_max |
SONE data from |
scenario_min |
SONE data from |
sizes |
An array of sample sizes to be simulated. Can be single value. |
n_sim |
number of simulations. 1000 is a start, 10000 was used in paper, but takes a long time |
to_min |
How many indicators relate to the outcome in the lack of ION condition. In |
plotting |
Plots the result with |
multi |
influences cex of certain plot variables. Defaults to 1 |
set.seed(466) sizes=c(500,1000) n_sim=50 # make bigger for more accurate estimates.. to_n=8 cor_to_outcome=0.25 ptm <- proc.time() # timing # takes a few seconds.. scen1=scenario_sim(sizes=sizes,n_sim=n_sim,to_n=to_n, cor_to_outcome=cor_to_outcome) proc.time() - ptm ptm <- proc.time() # A scenario with 3 out of 8 items relating to outcome, 3 different samples to_n=3 scen2=scenario_sim(sizes=sizes,n_sim=n_sim,to_n=to_n, cor_to_outcome=cor_to_outcome) proc.time() - ptm optimal_p_out(scen1[[1]],scen2[[1]],sizes = sizes,n_sim=n_sim,to_min = to_n, plot='yes', multi=1) # Should be equivalent. Some variation can be expected when n_sim is below 1000 ptm <- proc.time() a=optimal_p(sizes=sizes, n_sim=n_sim, n_indicators=8, plotting='yes', cor_to_outcome=cor_to_outcome) proc.time() - ptm print(a[[1]])set.seed(466) sizes=c(500,1000) n_sim=50 # make bigger for more accurate estimates.. to_n=8 cor_to_outcome=0.25 ptm <- proc.time() # timing # takes a few seconds.. scen1=scenario_sim(sizes=sizes,n_sim=n_sim,to_n=to_n, cor_to_outcome=cor_to_outcome) proc.time() - ptm ptm <- proc.time() # A scenario with 3 out of 8 items relating to outcome, 3 different samples to_n=3 scen2=scenario_sim(sizes=sizes,n_sim=n_sim,to_n=to_n, cor_to_outcome=cor_to_outcome) proc.time() - ptm optimal_p_out(scen1[[1]],scen2[[1]],sizes = sizes,n_sim=n_sim,to_min = to_n, plot='yes', multi=1) # Should be equivalent. Some variation can be expected when n_sim is below 1000 ptm <- proc.time() a=optimal_p(sizes=sizes, n_sim=n_sim, n_indicators=8, plotting='yes', cor_to_outcome=cor_to_outcome) proc.time() - ptm print(a[[1]])
Simulates a personality scale which correlates to an outcome. The function can specify the number of indicators (i.e. indicators) truly relating to the outcome. Also, the function can create a secondary scale, for instance mimicing informant-report
scale_sim(n, to_n, tn_n = 0, indicators2 = FALSE, cor_to_tn = 0.3, cor_to_outcome = 0.4, to_min = 0.4, to_max = 0.7, tn_min = 0.4, tn_max = 0.7, n.cat = 5, sdev = 0.8)scale_sim(n, to_n, tn_n = 0, indicators2 = FALSE, cor_to_tn = 0.3, cor_to_outcome = 0.4, to_min = 0.4, to_max = 0.7, tn_min = 0.4, tn_max = 0.7, n.cat = 5, sdev = 0.8)
n |
Number of participants |
to_n |
Number of indicators in a Trait relating to Outcome |
tn_n |
Number of indicators in a Trait Not relating to outcome. |
indicators2 |
if TRUE, a secondary set of indicators is created, e.g. to mimic informant-report. Defaults to FALSE |
cor_to_tn |
Correlation between to and tn. Defaults to 0.3 |
cor_to_outcome |
correlation between to and outcome. Defaults to 0.4 |
to_min |
minimum factor loading for to_n. Defaults to 0.4 |
to_max |
maximum factor loading for to_n. Defaults to 0.7 |
tn_min |
minimum factor loading for tn_n. Defaults to 0.4 |
tn_max |
maximum factor loading for tn_n. Defaults to 0.7 |
n.cat |
number of response options. when you go larger than 5, update the standard deviation as well. Defaults to 5 |
sdev |
standard deviation. Defaults to 0.8 |
A list object, first object is indicators' matrix and second object is outcome vector. If indicators2=TRUE, then a third object is added, which is the secondary indicators' matrix.
## Create a scale-outcome set that violates ION. Only 2 indicators out of 8 relate ## to the outcome, the others just relate to the 2 indicators This setting is similar ## to the N5: Impulsiveness - BMI association in Vainik et al (2015) EJP paper. set.seed(466) a<-scale_sim(n=2500, to_n=2, tn_n=6) # Last 2 indicators have considerably higher correlation with the outcome cor(a[[1]],a[[2]]) ## Create a scale-outcome set that has ION, all 8 indicators relate to the outcome set.seed(466) b<-scale_sim(n=2500, to_n=8) # All indicators correlate largely on the same level with the outcome. cor(b[[1]],b[[2]]) ## Create a scale-outcome set that violates ION - only 1 indicator relates to ##the outcome. Include other-report. set.seed(466) c<-scale_sim(n=2500, to_n=1, tn_n=7, indicators2=TRUE) # Last 2 indicators have considerably higher correlation with the outcome cor(c[[1]],c[[2]]) cor(c[[3]],c[[2]])## Create a scale-outcome set that violates ION. Only 2 indicators out of 8 relate ## to the outcome, the others just relate to the 2 indicators This setting is similar ## to the N5: Impulsiveness - BMI association in Vainik et al (2015) EJP paper. set.seed(466) a<-scale_sim(n=2500, to_n=2, tn_n=6) # Last 2 indicators have considerably higher correlation with the outcome cor(a[[1]],a[[2]]) ## Create a scale-outcome set that has ION, all 8 indicators relate to the outcome set.seed(466) b<-scale_sim(n=2500, to_n=8) # All indicators correlate largely on the same level with the outcome. cor(b[[1]],b[[2]]) ## Create a scale-outcome set that violates ION - only 1 indicator relates to ##the outcome. Include other-report. set.seed(466) c<-scale_sim(n=2500, to_n=1, tn_n=7, indicators2=TRUE) # Last 2 indicators have considerably higher correlation with the outcome cor(c[[1]],c[[2]]) cor(c[[3]],c[[2]])
Plots the results like in Study 1 of the Vainik et al. paper an overview of the indicator exclusion results. Starred indicators are excluded in the indicator exclusion procedure. See scenario_sim for details. NB! Scenario with no ION violations needs scenario_plot80()
See scenario_sim for examples
scenario_plot(dat, sizes, n_sim, to_n, tn_n = 8 - to_n, multi = 1, jitter = 0.05, letter = "", ...) scenario_plot80(dat, sizes, n_sim, multi = 1, letter = "", ...)scenario_plot(dat, sizes, n_sim, to_n, tn_n = 8 - to_n, multi = 1, jitter = 0.05, letter = "", ...) scenario_plot80(dat, sizes, n_sim, multi = 1, letter = "", ...)
dat |
simulated data |
sizes |
An array of sample sizes to be simulated. Can be single value. |
n_sim |
number of simulations. 1000 is a start, 10000 was used in paper, but takes a long time |
to_n |
Number of indicators in a Trait relating to Outcome |
tn_n |
Number of indicators in a Trait Not relating to outcome. |
multi |
influences cex of certain plot variables. |
jitter |
Avoid overalp between lines |
letter |
assigns plot a letter, useful for combining multiple plots |
... |
additional options for axis |
scenario_plot80: For plotting scenarios where ION is not violated
A wrapper that takes a scenario, and produces the Significance Of iNdicator Exclusion (SONE) values for each exclusion and calculates efficacy. Used by optimal_p.
scenario_sim(sizes, n_sim, to_n, tn_n = 8 - to_n, ...)scenario_sim(sizes, n_sim, to_n, tn_n = 8 - to_n, ...)
sizes |
An array of sample sizes to be simulated. Can be single value. |
n_sim |
number of simulations. 1000 is a start, 10000 was used in paper, but takes a long time |
to_n |
Number of indicators in a Trait relating to Outcome |
tn_n |
Number of indicators in a Trait Not relating to outcome. |
... |
further tweaking of the scale simulator, see |
Returns a list of SONE values and related efficacy. See example for details
SONE results. Feed this to scenario_plot or scenario_plot80 (see examples)
Summary efficacy. Such data comprises Table 1 in Vainik, Mottus et al., 2015 EJP
Full efficacy data.
#A scenario with 8 items relating to outcome, testing 2 different samples sizes=c(250,500) n_sim=100 to_n=8 scen1=scenario_sim(sizes,n_sim,to_n) # takes a few seconds.. scenario_plot80(scen1[[1]],sizes,n_sim) # A scenario with 2 out of 8 items relating to outcome, 2 different samples to_n=2 scen2=scenario_sim(sizes,n_sim,to_n) # takes a few seconds.. scenario_plot(scen2[[1]],sizes,n_sim,to_n)#A scenario with 8 items relating to outcome, testing 2 different samples sizes=c(250,500) n_sim=100 to_n=8 scen1=scenario_sim(sizes,n_sim,to_n) # takes a few seconds.. scenario_plot80(scen1[[1]],sizes,n_sim) # A scenario with 2 out of 8 items relating to outcome, 2 different samples to_n=2 scen2=scenario_sim(sizes,n_sim,to_n) # takes a few seconds.. scenario_plot(scen2[[1]],sizes,n_sim,to_n)