umx (version 1.9.1)

umxTwoStage: umxTwoStage

Description

umxTwoStage implements 2-stage least squares regression in Structural Equation Modeling. For ease of learning, the function is modeled closely on the tsls.

Usage

umxTwoStage(formula, instruments, data, subset, weights, contrasts = NULL,
  name = "tsls", ...)

Arguments

formula

The structural equation to be estimated; a regression constant is implied if not explicitly omitted.

instruments

A one-sided formula specifying instrumental variables.

data

data.frame containing the variables in the model.

subset

[optional] vector specifying a subset of observations to be used in fitting the model.

weights

[optional] vector of weights to be used in the fitting process; If specified should be a non-negative numeric vector with one entry for each observation, to be used to compute weighted 2SLS estimates.

contrasts

an optional list. See the contrasts.arg argument of model.matrix.default.

name

for the model (defaults to "tsls")

...

arguments to be passed down.

Value

-

Details

The example is a Mendelian Randomization https://en.wikipedia.org/wiki/Mendelian_randomization analysis to show the utility of two-stage regression.

References

- Fox, J. (1979) Simultaneous equation models and two-stage least-squares. In Schuessler, K. F. (ed.) Sociological Methodology, Jossey-Bass., Greene, W. H. (1993) Econometric Analysis, Second Edition, Macmillan.

See Also

- umxRAM, tsls

Other Super-easy helpers: umxEFA, umx

Examples

# NOT RUN {
library(umx)


# ====================================
# = Mendelian randomization analysis =
# ====================================

# Note: in practice: many more subjects are desirable - this just to let example run fast
df = umx_make_MR_data(1000) 
m1 = umxTwoStage(Y ~ X, instruments = ~ qtl, data = df)
coef(m1)
plot(m1)

# Errant analysis using ordinary least squares regression (WARNING this result is CONFOUNDED!!)
m1 = lm(Y ~ X    , data = df); coef(m1) # incorrect .35 effect of X on Y
m1 = lm(Y ~ X + U, data = df); coef(m1) # Controlling U reveals the true 0.1 beta weight
#
#
# }
# NOT RUN {
df = umx_make_MR_data(1e5) 
m1 = umxTwoStage(Y ~ X, instruments = ~ qtl, data = df)

# ======================
# = Now with sem::tsls =
# ======================
# library(sem) # will require you to install X11
m2 = sem::tsls(formula = Y ~ X, instruments = ~ qtl, data = df)
coef(m1)
coef(m2)
m3 = tsls(formula = Y ~ X, instruments = ~ qtl, data = (df[1, "qtl"] = NA))
# }