balsos: Bayesian Alternating Least Squares Optimal Scaling

In davidaarmstrong/damisc_nodep: Dave Armstrong's Miscellaneous Functions

Description

Estimates a Bayesian analog to the the Alternating Least Squares Optimal Scaling (ALSOS) solution for qualitative dependent variables.

Usage

	balsos(formula, data, iter=2500, chains = 1, alg = c("NUTS", "HMC", "Fixed_param"), ...)

Arguments

formula	A formula with a dependent variable that will be optimally scaled
data	A data frame.
iter	Number of samples for the MCMC sampler.
chains	Number of parallel chains to be run.
alg	Algorithm used to do sampling. See stan for more details.
...	Other arguments to be passed down to stanfit.

Details

balsos estimates a Bayesian analog to the Alternating Least Squares Optimal Scaling solution on the dependent variable. This permits testing linearity assumptions on the original scale of the dependent variable.

Value

A list with the following elements:

fit	The fitted stan output
y	The dependent variable values used in the regression.
X	The design matrix for the regression

Author(s)

Dave Armstrong

References

Jacoby, William G. 1999. ‘Levels of Measurement and Political Research: An Optimistic View.’ American Journal of Political Science 43(1):271–301.

Young, Forrest. 1981. ‘Quantitative Analysis of Qualitative Data’, Psychometrika, 46:357-388.

Young, Forrest, Jan de Leeuw and Yoshio Takane. 1976. ‘Regression with Qualitative and Quantitative Variables: An Alternating Least Squares Method with Optimal Scaling Features’. Psychometrika, 41:502-529.

davidaarmstrong/damisc_nodep documentation built on May 15, 2019, 6:25 p.m.