ceilings

Ceilings to use for the <code><a rd-options="" href="/link/nca?package=NCA&version=2.0" data-mini-rdoc="NCA::nca">nca</a></code> or <code><a rd-options="" href="/link/nca_analysis?package=NCA&version=2.0" data-mini-rdoc="NCA::nca_analysis">nca_analysis</a></code> methods 
 &gt; nca(data, c(1, 2), 3, ceilings=c("ols", "ce_fdh", "cr_fdh"))
<table><tr><td>
 </td>
<td></td>
<td></td>
<td>
 Ceiling Technique </td>
</tr><tr><td> Name </td>
<td> Descriptive statistics and inferential statistics :</td>
<td>
 </td>
<td> </td>
</tr><tr><td> point estimates </td>
<td> </td>
<td>lh </td>
<td> Low-High </td>
</tr><tr><td> Yes </td>
<td> </td>
<td>
 cols </td>
<td> Corrected Ordinary Least Squares </td>
</tr><tr><td> Yes </td>
<td> </td>
<td>
 qr </td>
<td> Quantile Regression </td>
</tr><tr><td> Yes </td>
<td> </td>
<td>
 sfa </td>
<td> Stochastic Frontier Analysis </td>
</tr><tr><td> Yes </td>
<td> </td>
<td>
 ce_vrs </td>
<td> Ceiling Envelopment </td>
</tr><tr><td> Yes </td>
<td> </td>
<td>
 </td>
<td> with Varying Return to Scale </td>
</tr><tr><td> </td>
<td> </td>
<td>
 cr_vrs </td>
<td> Ceiling Regression </td>
</tr><tr><td> Yes </td>
<td> </td>
<td>
 </td>
<td> with Varying Return to Scale </td>
</tr><tr><td> </td>
<td> </td>
<td>
 ce_fdh </td>
<td> Ceiling Envelopment </td>
</tr><tr><td> Yes </td>
<td> </td>
<td>
	 </td>
<td> with Free Disposal Hull </td>
</tr><tr><td> </td>
<td> </td>
<td>
	cr_fdh </td>
<td> Ceiling Regression </td>
</tr><tr><td> Yes </td>
<td> </td>
<td>
	 </td>
<td> with Free Disposal Hull </td>
</tr><tr><td> </td>
<td> </td>
<td>
 </td>
<td></td>
</tr></table>

Parameter

Performs a Necessary Condition Analysis (NCA). (Dul, J. 2016. Necessary Condition Analysis (NCA). ''Logic and Methodology of 'Necessary but not Sufficient' causality." Organizational Research Methods 19(1), 10-52)
NCA identifies necessary (but not sufficient) conditions in datasets. Instead of drawing a regression line ''through the middle of the data'' in an xy-plot, NCA draws the ceiling line. The ceiling line y = f(x) separates the area with observations from the area without observations.
(Nearly) all observations are below the ceiling line: y <= f(x). The empty zone is in the upper left hand corner of the xy-plot (with the convention that the x-axis is ''horizontal'' and the y-axis is ''vertical'' and that values increase ''upwards'' and ''to the right''). The ceiling line is a (piecewise) linear non-decreasing line: a linear step function or a straight line. It indicates which level of x (e.g. an effort or input) is necessary but not sufficient for a (desired) level of y (e.g. good performance or output).

ceilings: a set of all available ceiling techniques

Description

Arguments

			Ceiling Technique
Name	Descriptive statistics and inferential statistics :
point estimates		lh	Low-High
Yes		cols	Corrected Ordinary Least Squares
Yes		qr	Quantile Regression
Yes		sfa	Stochastic Frontier Analysis
Yes		ce_vrs	Ceiling Envelopment
Yes			with Varying Return to Scale
		cr_vrs	Ceiling Regression
Yes			with Varying Return to Scale
		ce_fdh	Ceiling Envelopment
Yes			with Free Disposal Hull
		cr_fdh	Ceiling Regression
Yes			with Free Disposal Hull