sicGroup: SIC Analysis for a Group

In sft: Functions for Systems Factorial Technology Analysis of Data

Description

Calculates the SIC for each individual in each condition of a DFP experiment. The function will plot each individuals SIC and return the results of the test for stochastic dominance and the statistical test of SIC form.

Usage

sicGroup(inData, sictest="ks", mictest=c("art", "anova"), domtest="ks", 
         alpha.sic=.05, plotSIC=TRUE, ...)

Arguments

inData	Data collected from a Double Factorial Paradigm experiment in standard form.
sictest	Which type of hypothesis test to use for SIC form. "ks" is the only test currently implemented.
mictest	Which type of hypothesis test to use for the MIC. The adjusted rank transform (art) and analysis of variance (anova) are the only tests currently implemented.
domtest	Which type of hypothesis test to use for testing stochastic dominance relations, either as series of KS tests ("ks") or the dominance test based on Dirichlet process priors ("dp"). DP not yet implemented.
alpha.sic	Alpha level for determining a difference from zero used by the SIC overview.
plotSIC	Indicates whether or not to generate plots of the survivor interaction contrasts.
...	Arguments to be passed to plot function.

Details

See the help page for the sic function for details of the survivor interaction contrast.

Value

overview	Data frame summarizing the test outcomes for each participant and condition.
Subject	The participant identifier from inData.
Condition	The condition identifier from inData.
Selective.Influence	The results of the survivor function dominance test for selective influence. Pass indicates HH < HL, LH and LL > LH, HL, but not HL, LH < HH and not LH, HL > LL, where A < B indicates that A is significantly faster than B at the level of the distribution. Ambiguous means neither HL, LH < HH, nor LH, HL > LL, but at least one of HH < HL, LH or LL >HL, LH did not hold. Fail means that at least one of HL, LH < HH or HL, LH > LL.
Positive.SIC	Indicates whehter the SIC is significantly positive at any time.
Negative.SIC	Indicates whehter the SIC is significantly negative at any time.
MIC	Indicates whether or not the MIC is significantly non-zero.
Model	Indicates which model would predict the pattern of data, assuming selective influence.
SICfn	Matrix with each row giving the values of the of the estimated SIC for one participant in one condition for values of times. The rows match the ordering of statistic.
sic	List with each element giving the result applying sic() to an individual in a condition. sic has the same ordering as overview.
times	Times at which the SICs in SICfn are calculated.

Author(s)

Joe Houpt <[e-mail]>

References

Townsend, J.T. & Nozawa, G. (1995). Spatio-temporal properties of elementary perception: An investigation of parallel, serial and coactive theories. Journal of Mathematical Psychology, 39, 321-360.

Houpt, J.W. & Townsend, J.T. (2010). The statistical properties of the survivor interaction contrast. Journal of Mathematical Psychology, 54, 446-453.

Heathcote, A., Brown, S.D., Wagenmakers, E-J. & Eidels, A. (2010) Distribution-free tests of stochastic dominance for small samples. Journal of Mathematical Psychology, 54, 454-463.

Houpt, J.W., Blaha, L.M., McIntire, J.P., Havig, P.R. and Townsend, J.T. (2013). Systems Factorial Technology with R. Behavior Research Methods.

See Also

sic capacityGroup

Examples

## Not run: 
data(dots)
sicGroup(dots)

## End(Not run)

sft documentation built on May 2, 2019, 6:04 a.m.