lm() with spearman corr option ?

Hi,

A following function was  kindly provided by GGally?s maintainer, Barret Schloerke.

function(data, mapping, ...) {
    p <- ggplot(data = data, mapping = mapping) +
        geom_point(color = I("blue")) +
        geom_smooth(method = "lm", color = I("black"), ...) +
        theme_blank() +
        theme(panel.border=element_rect(fill=NA, linetype = "solid", color="black"))

    lmModel <- eval(substitute(lm(y ~ x, data = data), mapping))
    fs <- summary(lmModel)$fstatistic
    pValue <- pf(fs[1], fs[2], fs[3], lower.tail = FALSE)

    if (pValue < 0.05) {
        p <- p + theme(
            panel.border = element_rect(
                color = "red",
                size = 3,
                linetype = "solid",
                fill = "transparent"
            )
        )
    }

    p
}

Basically, this function draws red squares  over pairwise corr plots with p<0.05.  Now, since I need to use the spearman rank corr, I tried to modify the lm function by adding ?method=spearman?  but this did not work at al.  Could anybody suggest the way to add the spearman rank corr function in this particular function ?

Thanks.

Hi,

A following function was  kindly provided by GGally?s maintainer, Barret
Schloerke.

function(data, mapping, ...) {
    p <- ggplot(data = data, mapping = mapping) +
        geom_point(color = I("blue")) +
        geom_smooth(method = "lm", color = I("black"), ...) +
        theme_blank() +
        theme(panel.border=element_rect(fill=NA, linetype = "solid",
color="black"))

    lmModel <- eval(substitute(lm(y ~ x, data = data), mapping))
    fs <- summary(lmModel)$fstatistic
    pValue <- pf(fs[1], fs[2], fs[3], lower.tail = FALSE)

    if (pValue < 0.05) {
        p <- p + theme(
            panel.border = element_rect(
                color = "red",
                size = 3,
                linetype = "solid",
                fill = "transparent"
            )
        )
    }

    p
}

Basically, this function draws red squares  over pairwise corr plots with
p<0.05.  Now, since I need to use the spearman rank corr, I tried to modify
the lm function by adding ?method=spearman?  but this did not work at al.
Could anybody suggest the way to add the spearman rank corr function in
this particular function ?

Thanks.