── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.4     ✔ readr     2.1.5
✔ forcats   1.0.0     ✔ stringr   1.5.1
✔ ggplot2   3.5.1     ✔ tibble    3.2.1
✔ lubridate 1.9.3     ✔ tidyr     1.3.1
✔ purrr     1.0.2     
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
here() starts at /Users/visuallearninglab/Documents/visvocab

Load data

looking_time_resampled_clean <- read.csv(here("data","processed_data","looking_times_resampled_clean.csv"))
all_looking_times <- read.csv(here("data","processed_data","looking_times_with_exclusion_info.csv"))

Overall timecourse plot of proportion target looking

#summarizing within subject for each time point
summarize_subj <- looking_time_resampled_clean %>%
  filter(trial_exclusion == 0 & exclude_participant ==0 & exclude_participant_insufficient_data == 0) %>%
  group_by(SubjectInfo.subjID, time_normalized_corrected) %>%
  summarize(N=n(),
            non_na_n = sum(!is.na(accuracy_transformed)), 
            mean_accuracy=mean(accuracy_transformed,na.rm=TRUE),
            sd_accuracy=sd(accuracy_transformed,na.rm=TRUE),
            se_accuracy=sd_accuracy/sqrt(non_na_n),
            ci=qt(0.975, non_na_n-1)*sd(accuracy_transformed,na.rm=T)/sqrt(non_na_n),
            lower_ci=mean_accuracy-ci,
            upper_ci=mean_accuracy+ci) %>%
  filter(non_na_n > 10) %>%
  ungroup()

Warning: There were 90 warnings in `summarize()`.
The first warning was:
ℹ In argument: `ci = qt(0.975, non_na_n - 1) * sd(accuracy_transformed, na.rm =
  T)/sqrt(non_na_n)`.
ℹ In group 1: `SubjectInfo.subjID = "AWMRW7"` and `time_normalized_corrected =
  -3467`.
Caused by warning in `qt()`:
! NaNs produced
ℹ Run `dplyr::last_dplyr_warnings()` to see the 89 remaining warnings.

`summarise()` has grouped output by 'SubjectInfo.subjID'. You can override
using the `.groups` argument.

#summarizing across subjects for each time point
summarize_across_subj <- summarize_subj %>%
  group_by(time_normalized_corrected) %>%
  dplyr::summarize(n=n(),
            accuracy=mean(mean_accuracy,na.rm=TRUE),
            sd_accuracy=sd(mean_accuracy,na.rm=TRUE),
            se_accuracy=sd_accuracy/sqrt(n)) %>%
  filter(n > 2)

looking_times <- ggplot(summarize_across_subj,aes(time_normalized_corrected,accuracy))+
  xlim(-2000,4000)+
  geom_errorbar(aes(ymin=accuracy-se_accuracy,ymax=accuracy+se_accuracy),width=0, alpha=0.2)+
  #geom_point(alpha=0.2)+
    geom_smooth(method="gam")+
  geom_vline(xintercept=0,size=1.5)+
  geom_hline(yintercept=0.5,size=1.2,linetype="dashed")+
  geom_vline(xintercept=300,linetype="dotted")+
  ylim(0,1)+
  xlab("Time (normalized to target word onset) in ms")+
  ylab("Proportion Target Looking")

Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
ℹ Please use `linewidth` instead.

ggsave(here("data","figures","prop_looking_across_time.png"),looking_times,width=9,height=6,bg = "white")

`geom_smooth()` using formula = 'y ~ s(x, bs = "cs")'

Warning: Removed 25 rows containing non-finite outside the scale range
(`stat_smooth()`).

Proprtion of target looking for easy vs hard trials

#Overall baseline-corrected proportion target looking by condition
looking_data_summarized <- all_looking_times |>
  filter(trial_exclusion == 0 & exclude_participant == 0 & exclude_participant_insufficient_data == 0) |>
  distinct(Trials.trialID, SubjectInfo.subjID, .keep_all = TRUE)

avg_corrected_target_looking_by_condition <- looking_data_summarized  %>%
  group_by(SubjectInfo.subjID, Trials.trialType) %>%
  summarize(N=n(),
            #mean_age = mean(age),
            #mean_age_mo = mean(age_mo),
            average_corrected_target_looking=mean(corrected_target_looking,na.rm=TRUE),
            se=sd(corrected_target_looking,na.rm=T)/sqrt(N),
            ci=qt(0.975, N-1)*sd(corrected_target_looking,na.rm=T)/sqrt(N),
            lower_ci=average_corrected_target_looking-ci,
            upper_ci=average_corrected_target_looking+ci,
            lower_se=average_corrected_target_looking-se,
            upper_se=average_corrected_target_looking+se,
            average_critical_window_looking=mean(mean_target_looking_critical_window,na.rm=TRUE),
            critical_window_ci = qt(0.975, N-1)*sd(mean_target_looking_critical_window,na.rm=T)/sqrt(N),
            critical_window_lower_ci=average_critical_window_looking-critical_window_ci,
            critical_window_upper_ci=average_critical_window_looking+critical_window_ci)

`summarise()` has grouped output by 'SubjectInfo.subjID'. You can override
using the `.groups` argument.

#baseline-corrected target looking summarized overall
overall_corrected_target_looking_by_condition <- avg_corrected_target_looking_by_condition %>%
  group_by(Trials.trialType) %>%
  summarize(N=n(),
            corrected_target_looking=mean(average_corrected_target_looking,na.rm=TRUE),
            ci=qt(0.975, N-1)*sd(average_corrected_target_looking,na.rm=T)/sqrt(N),
            lower_ci=corrected_target_looking-ci,
            upper_ci=corrected_target_looking+ci)

overall_corrected_target_looking_by_condition %>%
  knitr::kable()

Trials.trialType	N	corrected_target_looking	ci	lower_ci	upper_ci
easy	4	-0.0603453	0.3131527	-0.3734980	0.2528074
easy-distractor	4	0.1480169	0.2753286	-0.1273117	0.4233455
hard	4	0.1128454	0.1298915	-0.0170461	0.2427368
hard-distractor	4	0.0429219	0.3310093	-0.2880874	0.3739312

set.seed(2)
avg_corrected_target_looking_by_condition <- avg_corrected_target_looking_by_condition |> filter(Trials.trialType == "easy" | Trials.trialType == "hard")
overall_corrected_target_looking_by_condition <- overall_corrected_target_looking_by_condition |>
  filter(Trials.trialType == "easy" | Trials.trialType == "hard")
jitterer <- position_jitter(width = .05,seed=1)

overall_condition_plot <- ggplot(avg_corrected_target_looking_by_condition, aes(x=Trials.trialType,y=average_corrected_target_looking, fill=Trials.trialType))+
  geom_half_violin(data=filter(avg_corrected_target_looking_by_condition, Trials.trialType=="easy"),position = position_nudge(x = -.1, y = 0), width=1,trim = FALSE, alpha = .8,color=NA,side="l")+
  geom_half_violin(data=filter(avg_corrected_target_looking_by_condition, Trials.trialType=="hard"),position = position_nudge(x = .1, y = 0), width=1,trim = FALSE, alpha = .8,color=NA,side="r")+
  geom_path(aes(group=SubjectInfo.subjID),color="black",fill=NA,alpha=0.15,size=0.75,position=jitterer)+   geom_point(aes(color=Trials.trialType,group=SubjectInfo.subjID), size = 2.5, alpha=0.15,position=jitterer)+
  geom_point(data=overall_corrected_target_looking_by_condition,aes(y=corrected_target_looking),color="black",size=5)+
  geom_line(data=overall_corrected_target_looking_by_condition,aes(y=corrected_target_looking,group=1),color="black",size=3)+
  geom_errorbar(data=overall_corrected_target_looking_by_condition,aes(y=corrected_target_looking,ymin=lower_ci,ymax=upper_ci),width=0,size=1.2,color="black")+
  geom_hline(yintercept=0,linetype="dashed")+
  theme(legend.position="none")+
  xlab("Distractor Difficulty Condition")+
  ylab("Baseline-Corrected\nProportion Target Looking")+
  theme(axis.title.x = element_text(face="bold", size=20),
        axis.text.x  = element_text(size=14),
        axis.title.y = element_text(face="bold", size=20),
        axis.text.y  = element_text(size=16),
        strip.text.x = element_text(size = 16,face="bold"))

Warning in geom_path(aes(group = SubjectInfo.subjID), color = "black", fill =
NA, : Ignoring unknown parameters: `fill`

overall_condition_plot

ggsave(here("data","figures","condition_based_looking.png"),overall_condition_plot,width=9,height=6,bg = "white")

Target image difficulty

# summarize average accuracy within participant (by word alone)
condition_based_looking <- looking_data_summarized  |>
  filter(!grepl("distractor", Trials.trialType)) |>
  distinct(SubjectInfo.subjID, Trials.trialID, Trials.targetImage, Trials.leftImage, Trials.rightImage, corrected_target_looking)

target_looking_by_target_word <- looking_data_summarized  |>
  filter(!grepl("distractor", Trials.trialType)) |>
  group_by(SubjectInfo.subjID, Trials.targetImage) |>
  summarize(target_looking_diff = corrected_target_looking[match("easy", Trials.trialType)] - corrected_target_looking[match("hard", Trials.trialType)],
            baseline_window_looking_diff = mean_target_looking_baseline_window[match("easy", Trials.trialType)] - mean_target_looking_baseline_window[match("hard", Trials.trialType)], 
            critical_window_looking_diff = mean_target_looking_critical_window[match("easy", Trials.trialType)] - mean_target_looking_critical_window[match("hard", Trials.trialType)])

`summarise()` has grouped output by 'SubjectInfo.subjID'. You can override
using the `.groups` argument.

#clean names for individual images for plot
overall_target_looking_by_word <- target_looking_by_target_word %>%
  filter(!is.na(target_looking_diff)) %>%
  group_by(Trials.targetImage) %>%
  summarize(N=n(),
            corrected_target_looking=mean(target_looking_diff,na.rm=TRUE),
            ci=qt(0.975, N-1)*sd(target_looking_diff,na.rm=T)/sqrt(N),
            lower_ci=corrected_target_looking-ci,
            upper_ci=corrected_target_looking+ci
          )

Warning: There was 1 warning in `summarize()`.
ℹ In argument: `ci = qt(0.975, N - 1) * sd(target_looking_diff, na.rm =
  T)/sqrt(N)`.
ℹ In group 1: `Trials.targetImage = "acorn"`.
Caused by warning in `qt()`:
! NaNs produced

word_prefs <- ggplot(overall_target_looking_by_word,aes(reorder(Trials.targetImage,corrected_target_looking),corrected_target_looking))+
  geom_hline(yintercept=0,linetype="dashed")+
  geom_errorbar(aes(ymin=lower_ci,ymax=upper_ci),width=0)+
  geom_point(aes(size=N))+
  xlab("Target Word")+
  ylab("Easy trial prefered target looking")+
  theme(axis.title.x = element_text(face="bold", size=15),
        axis.text.x  = element_text(size=10,angle=90,vjust=0.5,hjust=1),
        axis.title.y = element_text(face="bold", size=15),
        axis.text.y  = element_text(size=10),
        strip.text.x = element_text(size = 10,face="bold")
        ) +
  scale_y_continuous(breaks = seq(-1, 1, by = 0.2)) +
  scale_size_continuous(name = "Number of participants")
  
word_prefs

ggsave(here("data","figures","easy_trial_pref_by_word.png"),word_prefs,width=9,height=6,bg = "white")