piecewise_model {seedreg}

Analysis: Piecewise regression

Description

Fit a degree 1 spline with 1 knot point where the location of the knot point is unknown.

Usage

piecewise_model(
  trat,
  resp,
  middle = 1,
  CI = FALSE,
  bootstrap.samples = 1000,
  sig.level = 0.05,
  error = "SE",
  ylab = "Germination (%)",
  xlab = expression("Temperature ("^"o" * "C)"),
  theme = theme_classic(),
  cardinal = 0,
  width.bar = NA,
  legend.position = "top",
  textsize = 12,
  pointsize = 4.5,
  linesize = 0.8,
  pointshape = 21,
  font.family = "sans"
)

Arguments

trat

Numerical or complex vector with treatments

resp

Numerical vector containing the response of the experiment.

middle

A scalar in [0,1]. This represents the range that the change-point can occur in. 0 means the change-point must occur at the middle of the range of x-values. 1 means that the change-point can occur anywhere along the range of the x-values.

CI

Whether or not a bootstrap confidence interval should be calculated. Defaults to FALSE because the interval takes a non-trivial amount of time to calculate

bootstrap.samples

The number of bootstrap samples to take when calculating the CI.

sig.level

What significance level to use for the confidence intervals.

error

Error bar (It can be SE - default, SD or FALSE)

ylab

Variable response name (Accepts the expression() function)

xlab

treatments name (Accepts the expression() function)

theme

ggplot2 theme (default is theme_classic())

cardinal

defines the value of y considered extreme (default considers 0 germination)

width.bar

bar width

legend.position

legend position (default is c(0.3,0.8))

textsize

Font size

pointsize

shape size

linesize

line size

pointshape

format point (default is 21)

font.family

Font family (default is sans)

Value

Coefficients

Coefficients and their p values

Optimum temperature

Optimum temperature (equivalent to the maximum point)

Optimum temperature response

Response at the optimal temperature (equivalent to the maximum point)

Minimal temperature

Temperature that has the lowest response

Minimal temperature response

Lowest predicted response

Predicted maximum basal value

Lower basal limit temperature based on the value set by the user (default is 0)

Predicted minimum basal value

Upper basal limit temperature based on the value set by the user (default is 0)

AIC

Akaike information criterion

BIC

Bayesian Inference Criterion

r-squared

Determination coefficient

RMSE

Root mean square error

grafico

Graph in ggplot2 with equation

Note

if the maximum predicted value is equal to the maximum x, the curve does not have a maximum point within the studied range. If the minimum value is less than the lowest point studied, disregard the value.

Author(s)

Model imported from the SiZer package

Gabriel Danilo Shimizu

Leandro Simoes Azeredo Goncalves

References

Chiu, G. S., R. Lockhart, and R. Routledge. 2006. Bent-cable regression theory and applications. Journal of the American Statistical Association 101:542-553.

Toms, J. D., and M. L. Lesperance. 2003. Piecewise regression: a tool for identifying ecological thresholds. Ecology 84:2034-2041.

Examples

library(seedreg)
data("aristolochia")
attach(aristolochia)

#================================
# Germination
#================================
piecewise_model(trat,germ)

#================================
# Germination speed
#================================
piecewise_model(trat, vel, ylab=expression("v"~(dias^-1)))