Provides response time distributions (density/PDF, distribution
function/CDF, quantile function, and random generation): (a) Ratcliff
diffusion model (Ratcliff & McKoon, 2008,
Changes to Version 0.6-6 (bug-fix version, released July 2016)
o Bug when passing start point with s != 1 removed.
Changes to Version 0.6-x (released July 2016)
o Start point z in diffusion model is now on absolute scale and not relative to be in line with A (start point of LBA) which is also on absolute scale. (Thanks to Steve Lewandowsky for noticing this.)
o PDFs, CDFs, and quantile functions of both models now accept a data.frame as first argument containing both RTs/probabilities and responses. Allows more convenient way to pass data.
o renamed boundary (argument in diffusion functions) to response to be in line with LBA functions. (Thanks to Steve Lewandowsky for suggesting this.)
o added diffusion constant s as argument to all diffusion functions.
o added scale_p and scale_max arguments to quantile functions which automatically scale the entered probability to more conveniently obtain predicted quantiles.
o LBA functions now accept factor as response (which is converted via as.numeric). This allows to pass results from rdiffusion directly to LBA function.
o changed integration routine in pdiffusion to pracma::integral() which seems to be more robust. (Thanks to Anna-Lena Schubert and Steve Lewandowsky for reporting problems with the previous version.)
o removed bug preventing lnorm as distribution in rLBA. (Thanks to Steve Lewandowsky for reporting this bug.)
Changes to Version 0.5-x (released May 2016)
o Calculation of the CDF for the diffusion model was incorrect (this bug was present in all prior versions of rtdists). pdiffusion now simply integrates the PDF to obtain the CDF using R's integrate which provides the correct result (albeit slower). o Added rr98 data set: Experiment 1 from Ratcliff and Rouder (1998, Psych. Science). We thank Roger Ratcliff and Jeff Rouder for providing the data. o Added vignette showing how to analyze the data from Ratcliff and Rouder (1998) with both diffusion and LBA model. o Quantile functions work more robust and try uniroot if optimize does not converge.
Changes to Version 0.4-x (released April 2016)
o Added dLBA(), pLBA(), qLBA(), and rLBA(). dLBA() is a fully vectorized versions of n1PDF which has response as second argument, allowing to get the density for each response and corresponding response time in one step. As for the diffusion model (see below), this allows a likelihood function which only includes one call to the density function. pLBA() and qLBA() are the correpsonding CDF and quantile functions, respectively. rLBA() is a fully vectorized version of the RNG functions and should be used from now on as top-level function. o t0 in the LBA now accepts accumulator and trialwise parameters just as A and b. st0 now accepts trialwise parameter (not accumulator wise). o Diffusion model function have been renamed to ddiffusion, pdiffusion, and rdiffusion. Added quantile function for diffusion model, qdiffusion. o Diffusion model functions are now completely vectorized and accept vectors as parameters (including for boundary). As for the LBA, this allows a likelihood function which only includes one call to the density function (see examples). o Boundary parameter for diffusion functions accept numeric/factor vectors. o t0 in the diffusion model now corresponds to the lower bound of the uniform distribution from which t0 is drawn (it was the mean before). The specifications of t0 now agree between LBA and diffusion model. o Density for diffusion model is now always positive. o First argument in most functions (vector of response times) renamed to rt (was t before). o PDF and CDF LBA functions more robust (now mostly return 0 instead of NaN) for problematic parameter values (such as A = 0) [2015-09-17].