lsm (version 0.2.1.5)

predict.lsm: Predictions and Confidence intervals

Description

Obtains predictions and confidence intervals from a fitted lsm object.

Usage

# S3 method for lsm
predict(
  object,
  newdata,
  type = c("link", "response", "odd", "OR"),
  level = 0.95,
  ...
)

Value

The option type =... returns a matrix with one column containing the requested predictions. The option interval =... returns a matrix with 3 columns containing the lower and upper extremes of the requested interval and the corresponding predictions.

Arguments

object

A fitted object of class lsm.

newdata

Optionally, a data frame in which to look for variables with which to predict.

type

The type of prediction required. The alternatives response, link, odd and OR give the predicted probabilities, logits, odds and odds ratios, repectively.

level

Confidence level to use (default is 0.95).

...

Further arguments passed to or from other methods.

Author

Dr. rer. nat. Humberto LLinás Solano [aut] (Universidad del Norte, Barranquilla-Colombia); MSc. Omar Fábregas Cera [aut] (Universidad del Norte, Barranquilla-Colombia); MSc. Jorge Villalba Acevedo [cre, aut] (Universidad Tecnológica de Bolívar, Cartagena-Colombia).

Details

Predict Method for lsm Fits

If newdata is omitted, a matrix with the predictions for each observation is obtained. That is to say, the predictions are based on the data used for the fit. In that case how cases with missing values in the original fit is determined by the na.action argument of that fit. If na.action = na.omit omitted cases will not appear in the residuals, whereas if na.action = na.exclude they will appear (in predictions and standard errors), with residual value NA.

The saturated model is characterized by the assumptions 1 and 2 presented in section 2.3 by Llinas (2006, ISSN:2389-8976).

References

[1] LLinás, H. J. (2006). Precisiones en la teoría de los modelos logísticos. Revista Colombiana de Estadística, 29(2), 239–265. https://revistas.unal.edu.co/index.php/estad/article/view/29310

[2] Hosmer, D.W., Lemeshow, S. and Sturdivant, R.X. (2013). Applied Logistic Regression, 3rd ed., New York: Wiley.

[3] Chambers, J. M. and Hastie, T. J. (1992). Statistical Models in S. Wadsworth & Brooks/Cole.

Examples

#library(lsm)

#1. AGE and Coronary Heart Disease (CHD) Status of 20 subjects:

# library(lsm)
# library(tidyverse)
# datos <- lsm::chdage
# attach(datos)
# modelo <- lsm(CHD ~ AGE, data=datos)
# head(predict(modelo, type = "link"))
# predict(modelo,newdata=data.frame(AGE=35),type = "response")
# head(predict(modelo, type = "odd"))
# head(predict(modelo, type = "OR"))