diallel-methods: Methods for the diallel analyses

diallel-methodsR Documentation

Methods for the diallel analyses

Description

The results of Griffing, Hayman and PartialDiallel are lists with a class, so the usual model functions of R work on them: print() shows the main tables, summary() adds the tests of every effect, anova() returns the analysis of variance, coef() the estimates, vcov() and confint() their covariance matrix and confidence intervals, fitted() and residuals() the plot-level fitted values and residuals of the block analysis, predict() the predicted means of crosses (Griffing's fixed model), and plot() or autoplot() the figures.

Usage

## S3 method for class 'summary.da_griffing'
print(x, digits = 4L, ...)

## S3 method for class 'summary.da_hayman'
print(x, digits = 4L, ...)

## S3 method for class 'summary.da_partial'
print(x, digits = 4L, ...)

## S3 method for class 'da_result'
anova(object, ...)

## S3 method for class 'da_griffing'
coef(object, ...)

## S3 method for class 'da_hayman'
coef(object, ...)

## S3 method for class 'da_partial'
coef(object, ...)

## S3 method for class 'da_griffing'
vcov(object, ...)

## S3 method for class 'da_partial'
vcov(object, ...)

## S3 method for class 'da_griffing'
confint(object, parm = NULL, level = 0.95, ...)

## S3 method for class 'da_partial'
confint(object, parm = NULL, level = 0.95, ...)

## S3 method for class 'da_result'
fitted(object, ...)

## S3 method for class 'da_result'
residuals(object, ...)

## S3 method for class 'da_result'
nobs(object, ...)

## S3 method for class 'da_result'
df.residual(object, ...)

## S3 method for class 'da_griffing'
predict(object, newdata = NULL, type = c("gca", "full"), ...)

## S3 method for class 'da_result'
autoplot(object, ...)

Arguments

x, object

a result of Griffing(), Hayman() or PartialDiallel().

digits

significant digits of printed numbers (default 4).

...

passed on (to plot() for autoplot(); otherwise not used).

parm

effects to include (names; default all).

level

confidence level (default 0.95).

newdata

data frame with columns Cross1 and Cross2 (parent labels); default every pair of parents.

type

"gca" (default) or "full"; see Details.

Details

Standard errors and tests use the error variance of a cell mean \sigma^2_m = MS_E/B on the error degrees of freedom f_E: t = \hat{\theta}/\mathrm{SE}(\hat{\theta}), two-sided p-values from the t distribution on f_E degrees of freedom, and confidence intervals \hat{\theta} \pm t_{1-\alpha/2, f_E}\,\mathrm{SE}(\hat{\theta}). In Griffing's fixed model the gca effects have \mathrm{Var}(\hat{g}_i) = v_1\sigma^2_m and \mathrm{Cov}(\hat{g}_i, \hat{g}_j) = (v_1 - v_{12}/2) \sigma^2_m, where v_1 and v_{12} are the variance coefficients of \hat{g}_i and of \hat{g}_i - \hat{g}_j (see Griffing). In the partial diallel \mathrm{Var}(\hat{g}^I_i) = (1 - 1/L)\sigma^2/(BM), \mathrm{Var}(\hat{g}^{II}_j) = (1 - 1/M)\sigma^2/(BL) and \mathrm{Var}(\hat{S}_{ij}) = (L-1)(M-1)\sigma^2/(BLM). Hayman's components are tested on P-2 degrees of freedom.

Summary. summary(object, top = 5) lists the top crosses with the largest sca effects (Griffing's Model 1 and the partial diallel); top is passed through ....

Prediction (Griffing, Model 1): the mean of cross i \times j is predicted by \hat{\mu} + \hat{g}_i + \hat{g}_j from general combining ability alone (type = "gca", the prediction for crosses not grown or not yet tested) or by \hat{\mu} + \hat{g}_i + \hat{g}_j + \hat{S}_{ij} + \hat{R}_{ij} (type = "full", which reproduces the observed means).

Value

print() returns x invisibly. summary(): an object of class summary.da_griffing, summary.da_hayman or summary.da_partial (a list of tables, each a data.table or data.frame) with a print method. anova(): the analysis of variance (class anova). coef(): a named numeric vector (Griffing Model 1: gca effects g_<parent>, sca effects s_<i>:<j>, reciprocal effects r_<i>:<j>; Griffing Model 2: variance components; Hayman: the components of variation; partial diallel: gca effects gI_<parent>, gII_<parent>). vcov(): covariance matrix of the gca effects. confint(): a matrix with columns for the lower and upper limits. fitted(), residuals(): numeric vectors, one value per plot. nobs(): number of plots; df.residual(): error degrees of freedom. predict(): a data.table with Cross1, Cross2 and predicted. autoplot(): a ggplot object.

Author(s)

Muhammad Yaseen (myaseen208@gmail.com)

References

Griffing, B. (1956). Concept of general and specific combining ability in relation to diallel crossing systems. Australian Journal of Biological Sciences, 9(4), 463–493. \Sexpr[results=rd]{tools:::Rd_expr_doi("10.1071/BI9560463")}

Hayman, B. I. (1954). The theory and analysis of diallel crosses. Genetics, 39(6), 789–809. \Sexpr[results=rd]{tools:::Rd_expr_doi("10.1093/genetics/39.6.789")}

See Also

Griffing, Hayman, PartialDiallel, da-methods

Examples

#-------------------------------------------------------------
## The model functions on Griffing's fixed model
#-------------------------------------------------------------
fit <-
  Griffing(
      y          = Yield
    , Rep        = Rep
    , Cross1     = Cross1
    , Cross2     = Cross2
    , data       = GriffingData1
    , Method     = 1
    , Model      = 1
    , Reciprocal = c("combined", "split")[1]
    )
fit
summary(object = fit, top = 5)
anova(fit)
coef(fit)[1:8]
vcov(fit)
confint(object = fit, parm = NULL, level = 0.95)
head(fitted(fit))
head(residuals(fit))
nobs(fit)
df.residual(fit)
predict(
    object  = fit
  , newdata = data.frame(Cross1 = c(3, 7), Cross2 = c(7, 8))
  , type    = c("gca", "full")[1]
  )
plot(x = fit, which = c("gca", "sca", "biplot", "residuals", "qq")[4])

#-------------------------------------------------------------
## Hayman and the partial diallel
#-------------------------------------------------------------
h <-
  Hayman(
      y      = Yield
    , Rep    = Rep
    , Cross1 = Cross1
    , Cross2 = Cross2
    , data   = HaymanData
    )
summary(object = h, top = 5)
coef(h)
p <-
  PartialDiallel(
      y      = y
    , Rep    = Rep
    , Cross1 = Cross1
    , Cross2 = Cross2
    , data   = PartialDiallelData
    )
summary(object = p, top = 5)
confint(object = p, parm = NULL, level = 0.95)

DiallelAnalysisR documentation built on Nov. 6, 2026, 5:08 p.m.