Main figures

[Ayumi-495]

@itchyshin I created three main figures for our paper, could you please check these? If you need more information, please let me know - I will provide it promptly.

Fig. 1

Fig. 1 code

# overall effect
p1 <- orchard_plot(ma_all,
                    group = "Study_ID",
                    xlab = "log response ratio (lnRR)", 
                    angle = 45,
                    legend.pos = "bottom.right") + 
                    scale_x_discrete(labels = c("Overall effect")) + 
                    theme(legend.direction = "horizontal",
                    legend.text = element_text(size = 6)) +
                    scale_colour_okabe_ito()+
                    scale_fill_okabe_ito()

#eyespot vs. conspicuous patterns
p2 <- orchard_plot(mr_eyespot,
                  mod = "Treatment_stimulus",
                  group = "Study_ID",
                  xlab = "log response ratio (lnRR)",
                  angle = 45,
                  legend.pos = "bottom.right") +
                  theme(legend.direction = "horizontal",
                  legend.text = element_text(size = 6)) +
                  scale_colour_okabe_ito(order = 2:3)+
                  scale_fill_okabe_ito(order = 2:3)

# prey type - real vs. artificial
p3 <- orchard_plot(mr_prey_type,
                  mod = "Type_prey",
                  group = "Study_ID",
                  xlab = "log response ratio (lnRR)",
                  angle = 45,
                  legend.pos = "bottom.right") +
                  theme(legend.direction = "horizontal",
                  legend.text = element_text(size = 6))+ 
                  scale_colour_okabe_ito(order = 4:5) +
                  scale_fill_okabe_ito(order = 4:5)

# combine
patch1 <- p1 | (p2 / p3)
patch1 + plot_annotation(tag_levels = "a")

# output figure as pdf
ggsave("fig1.pdf", width = 10, height = 5, dpi = 450)

---

Fig. 2 Bubble plots were created by multi-moderator model

Fig. 2 code

# figs were created by the below model results
mr_cons <- rma.mv(yi = lnRR,
                V = VCV, 
                mods = ~ Log_area + Number_pattern,
                random = list(~1 | Study_ID,
                              ~1 | Obs_ID),
                test = "t",
                method = "REML", 
                sparse = TRUE,
                data = dat)

# log-transformed area
p4 <- bubble_plot(mr_cons,
                  mod = "Log_area",
                  group = "Study_ID",
                  xlab = "Log-transformed area") +
                  scale_x_continuous(breaks = seq(0,7,1.5)) +
                  scale_y_continuous(breaks = seq(-2.5, 4.5, 1.5))

# number of patterns
p5 <- bubble_plot(mr_cons,
            mod = "Number_pattern",
            group = "Study_ID",
            xlab = "Number of patterns") +
                  scale_x_continuous(breaks = seq(0,11,1.5)) +
                  scale_y_continuous(breaks = seq(-2.5, 4.5, 1.5))

# combine
p4 / p5 + plot_annotation(tag_levels = "a")

# output figure as pdf
ggsave("fig2_multi.pdf", width = 10, height = 10, dpi = 450)

---

Fig. 3 Is it okay to limit the y-axis of a funnel plot range due to the presence of very large values, making the plot less readable? For now, the plot does not include some of the larger values (>80).

Fig. 3 code

# these figs were created by multi-meta-regression model results
# log-transformed area
# funnel plot
pdf("fig3.pdf")

funnel(ma_all, yaxis = "seinv", 
      xlab = "Standarised residuals",
      ylab = "Precision (inverse of SE)",
      xlim = c(-4.0, 4.5), 
      ylim = c(0.01, 80.0), 
      col = c(alpha("mediumvioletred", 0.5)),
      cex = 0.7)

dev.off()

# Egger's test and decline effect
p7 <- bubble_plot(bias_model,
            mod = "sqrt_inv_e_n",
            group = "Study_ID",
            xlab = "Square root of inverse of effective sample size") +
            scale_y_continuous(breaks = seq(-2.5, 4.5, 1.5)) 

p8 <- bubble_plot(year_model,
            mod = "Year",
            group = "Study_ID",
            xlab = "Year of publication") +  scale_y_continuous(breaks = seq(-2.5, 4.0, 1.5)) 

# combine plots created by bubble_plot()
pub <- p7 / p8
pub_b <- pub +  plot_annotation(tag_levels = 'b') 

# output figure as pdf
ggsave("fig4.pdf", width = 10, height = 10, dpi = 450)

[itchyshin]

@Ayumi-495 - The latter two figs can fit into a column (of a published page - proc b has two columns when published as a pdf)