# sfa: Fitting stochastic frontier analysis models In sfa: Stochastic Frontier Analysis

## Description

`sfa` is used to fit stochastic frontier analysis models.

## Usage

 ```1 2``` ```sfa(formula, data = NULL, intercept = TRUE, fun = "hnormal", pars = NULL, par_mu = NULL, form = "cost", method = "BFGS", ...) ```

## Arguments

 `formula` an object of class `formula` (or one that can be coerced to that class): a symbolic description of the model to be fitted. `data` a data frame. `intercept` logical. If true the model includes intercept. `fun` specifies the distribution for the inefficency term u as half-normal ("hnormal"), exponential ("exp"), or truncated-normal ("tnormal"). `pars` initial values for the parameters to be estimated. `par_mu` value for mu in the normal-/truncated-normal case. If mu is known. `form` specifies the form of the frontier model as "cost" or "production". `method` the method to be used. See `optim` for more details. `...` ignored.

## Value

`sfa` returns an object of class `sfa`:

 `y` response `x` covariables `X` design matrix `coef` coefficients `sigmau2` sigmau2 `sigmav2` sigmav2 `mu` mu of the truncated-normal distribution (Only if fun = tnormal) `par_mu` NULL if mu is not estimated `logLik` value of the log likelihood function `maxlik` log likelihood function `fun` distribution of the inefficiency term u `sc` specifies the form of the frontier model (-1 = cost, 1 = production) `hess` a symmetric matrix giving an estimate of the Hessian at the solution found (See `optim`) `ols` the linear model for the LR-test

## Examples

 ```1 2 3``` ```set.seed(225) daten <- dgp(n = 100, b = c(1, 2), sc = -1) test <- sfa(y ~ x, data = daten) ```

### Example output

```There were 18 warnings (use warnings() to see them)
```

sfa documentation built on May 29, 2017, 5:51 p.m.