Studyphase
## libraries
library(tidyverse)
## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --
## v ggplot2 3.3.5 v purrr 0.3.4
## v tibble 3.1.5 v dplyr 1.0.7
## v tidyr 1.1.4 v stringr 1.4.0
## v readr 2.0.2 v forcats 0.5.1
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
## prepare workspace
rm(list=ls())
## import data
# "full.names=T" ist wie ein passport, der path wird auch angehängt
temp = list.files(pattern="*.csv", path = "./data_ts", full.names = T)
myfiles = lapply(temp, read.csv)
myfiles2 = bind_rows(myfiles)
# bei Participant 3 sind zwei cols mehr drin: "text_end.started" und "text_end.stopped"
# muss raus!
myfiles3 = subset(myfiles2, select=-c(text_end.started, text_end.stopped))
# jetzt noch die ueberschüssige zeile raus (row 121)
myfiles4 <- myfiles3[!apply(is.na(myfiles3) | myfiles3 == "", 1, all),]
str(myfiles4)
## 'data.frame': 1320 obs. of 54 variables:
## $ ï..word : chr "STONE" "EXERCISE" "TASTE" "BRICK" ...
## $ picture : chr "Bilder/16_NTraining.bmp" "Bilder/10_MTraining.bmp" "Bilder/2_MTraining.bmp" "Bilder/17_NTraining.bmp" ...
## $ condition : chr "S1" "R1" "S2" "R2" ...
## $ transition : chr "switch" "repeat" "switch" "repeat" ...
## $ task : chr "picture" "picture" "word" "word" ...
## $ corr_answ : chr "n" "m" "x" "c" ...
## $ pos_xy : chr "[-0.35, 0.25]" "[0.35, 0.25]" "[0.35, -0.25]" "[-0.35, -0.25]" ...
## $ trialnr : int 1 2 3 4 5 6 7 8 9 10 ...
## $ phase : chr "practice" "practice" "practice" "practice" ...
## $ BlockOrder : int NA NA NA NA NA NA NA NA NA NA ...
## $ list : chr "" "" "" "" ...
## $ practice_loop.thisRepN : int 0 0 0 0 0 0 0 0 0 0 ...
## $ practice_loop.thisTrialN: int 0 1 2 3 4 5 6 7 8 9 ...
## $ practice_loop.thisN : int 0 1 2 3 4 5 6 7 8 9 ...
## $ practice_loop.thisIndex : int 0 1 2 3 4 5 6 7 8 9 ...
## $ warmup_loop.thisRepN : int NA NA NA NA NA NA NA NA NA NA ...
## $ warmup_loop.thisTrialN : int NA NA NA NA NA NA NA NA NA NA ...
## $ warmup_loop.thisN : int NA NA NA NA NA NA NA NA NA NA ...
## $ warmup_loop.thisIndex : int NA NA NA NA NA NA NA NA NA NA ...
## $ exp_loop.thisRepN : int NA NA NA NA NA NA NA NA NA NA ...
## $ exp_loop.thisTrialN : int NA NA NA NA NA NA NA NA NA NA ...
## $ exp_loop.thisN : int NA NA NA NA NA NA NA NA NA NA ...
## $ exp_loop.thisIndex : int NA NA NA NA NA NA NA NA NA NA ...
## $ image_display.started : num 203 205 207 211 213 ...
## $ image_display.stopped : chr "None" "None" "None" "None" ...
## $ word_display.started : num 203 205 207 211 213 ...
## $ word_display.stopped : chr "None" "None" "None" "None" ...
## $ resp_pract.keys : chr "n" "m" "c" "c" ...
## $ resp_pract.corr : int 1 1 0 1 1 1 1 1 0 1 ...
## $ resp_pract.rt : num 1.4 1.34 3.33 1.04 1.99 ...
## $ text_feedback.started : num 205 207 211 213 215 ...
## $ text_feedback.stopped : chr "None" "None" "None" "None" ...
## $ word : chr "STONE" "EXERCISE" "TASTE" "BRICK" ...
## $ word_corr : chr "" "" "" "" ...
## $ emotionality : chr "" "" "" "" ...
## $ picture.1 : chr "Bilder/16_NTraining.bmp" "Bilder/10_MTraining.bmp" "Bilder/2_MTraining.bmp" "Bilder/17_NTraining.bmp" ...
## $ pict_corr : chr "" "" "" "" ...
## $ corr_resp : chr "" "" "" "" ...
## $ img_disp_exp.started : num NA NA NA NA NA NA NA NA NA NA ...
## $ img_disp_exp.stopped : chr "" "" "" "" ...
## $ word_disp_exp.started : num NA NA NA NA NA NA NA NA NA NA ...
## $ word_disp_exp.stopped : chr "" "" "" "" ...
## $ resp.keys : chr "" "" "" "" ...
## $ resp.corr : int NA NA NA NA NA NA NA NA NA NA ...
## $ resp.rt : num NA NA NA NA NA NA NA NA NA NA ...
## $ resp.started : num NA NA NA NA NA NA NA NA NA NA ...
## $ resp.stopped : chr "" "" "" "" ...
## $ participant : int 101 101 101 101 101 101 101 101 101 101 ...
## $ age : int 19 19 19 19 19 19 19 19 19 19 ...
## $ date : chr "2021_Dec_06_1148" "2021_Dec_06_1148" "2021_Dec_06_1148" "2021_Dec_06_1148" ...
## $ expName : chr "V1_RSI_150_UR" "V1_RSI_150_UR" "V1_RSI_150_UR" "V1_RSI_150_UR" ...
## $ psychopyVersion : chr "2021.2.3" "2021.2.3" "2021.2.3" "2021.2.3" ...
## $ frameRate : num 59.9 59.9 59.9 59.9 59.9 ...
## $ X : logi NA NA NA NA NA NA ...
## relevant columns
colnames(myfiles4)
## [1] "ï..word" "picture"
## [3] "condition" "transition"
## [5] "task" "corr_answ"
## [7] "pos_xy" "trialnr"
## [9] "phase" "BlockOrder"
## [11] "list" "practice_loop.thisRepN"
## [13] "practice_loop.thisTrialN" "practice_loop.thisN"
## [15] "practice_loop.thisIndex" "warmup_loop.thisRepN"
## [17] "warmup_loop.thisTrialN" "warmup_loop.thisN"
## [19] "warmup_loop.thisIndex" "exp_loop.thisRepN"
## [21] "exp_loop.thisTrialN" "exp_loop.thisN"
## [23] "exp_loop.thisIndex" "image_display.started"
## [25] "image_display.stopped" "word_display.started"
## [27] "word_display.stopped" "resp_pract.keys"
## [29] "resp_pract.corr" "resp_pract.rt"
## [31] "text_feedback.started" "text_feedback.stopped"
## [33] "word" "word_corr"
## [35] "emotionality" "picture.1"
## [37] "pict_corr" "corr_resp"
## [39] "img_disp_exp.started" "img_disp_exp.stopped"
## [41] "word_disp_exp.started" "word_disp_exp.stopped"
## [43] "resp.keys" "resp.corr"
## [45] "resp.rt" "resp.started"
## [47] "resp.stopped" "participant"
## [49] "age" "date"
## [51] "expName" "psychopyVersion"
## [53] "frameRate" "X"
keep <- c("participant", "age", "expName", "phase", "BlockOrder",
"condition", "transition", "task", "emotionality","pos_xy", "list",
"word", "word_corr", "picture", "pict_corr", "corr_resp",
"resp.corr", "resp.rt")
data_raw <- subset(myfiles4, select = keep)
colnames(data_raw)
## [1] "participant" "age" "expName" "phase" "BlockOrder"
## [6] "condition" "transition" "task" "emotionality" "pos_xy"
## [11] "list" "word" "word_corr" "picture" "pict_corr"
## [16] "corr_resp" "resp.corr" "resp.rt"
#### Rows ####
unique(data_raw$phase)
## [1] "practice" "warmup" "exp"
# relevant rows
# exclude practice trials and warmup trials
data_raw <- data_raw[data_raw$phase != 'practice' &
data_raw$phase != 'warmup', ]
data_raw$phase <- factor(data_raw$phase) # refactor data frame (in order to drop cleared levels completely)
unique(data_raw$phase) # now there won't be a error message when renaming levels
## [1] exp
## Levels: exp
str(data_raw)
## 'data.frame': 1056 obs. of 18 variables:
## $ participant : int 101 101 101 101 101 101 101 101 101 101 ...
## $ age : int 19 19 19 19 19 19 19 19 19 19 ...
## $ expName : chr "V1_RSI_150_UR" "V1_RSI_150_UR" "V1_RSI_150_UR" "V1_RSI_150_UR" ...
## $ phase : Factor w/ 1 level "exp": 1 1 1 1 1 1 1 1 1 1 ...
## $ BlockOrder : int 1 2 3 4 1 2 3 4 1 2 ...
## $ condition : chr "S1" "R1" "S2" "R2" ...
## $ transition : chr "switch" "repeat" "switch" "repeat" ...
## $ task : chr "picture" "picture" "word" "word" ...
## $ emotionality: chr "neutral" "neutral" "negative" "negative" ...
## $ pos_xy : chr "[-0.35, 0.25]" "[0.35, 0.25]" "[0.35, -0.25]" "[-0.35, -0.25]" ...
## $ list : chr "v1_S1.xlsx" "v1_R1.xlsx" "v1_S2.xlsx" "v1_R2.xlsx" ...
## $ word : chr "JOURNAL" "SLEEP" "NAZI" "SNAKE" ...
## $ word_corr : chr "c" "x" "c" "c" ...
## $ picture : chr "Bilder/205_N.bmp" "Bilder/111_M.bmp" "Bilder/35_M.bmp" "Bilder/280_N.bmp" ...
## $ pict_corr : chr "n" "m" "m" "n" ...
## $ corr_resp : chr "n" "m" "c" "c" ...
## $ resp.corr : int 1 1 1 1 1 1 1 0 1 1 ...
## $ resp.rt : num 1.212 0.924 2.646 1.754 1.242 ...
data_raw$participant <- factor(data_raw$participant)
data_raw$expName <- factor(data_raw$expName)
data_raw$BlockOrder <- factor(data_raw$BlockOrder)
data_raw$condition <- factor(data_raw$condition)
data_raw$transition <- factor(data_raw$transition)
data_raw$task <- factor(data_raw$task)
data_raw$emotionality <- factor(data_raw$emotionality)
data_raw$pos_xy <- factor(data_raw$pos_xy)
data_raw$list <- factor(data_raw$list)
data_raw$word <- factor(data_raw$word)
data_raw$picture <- factor(data_raw$picture)
str(data_raw)
## 'data.frame': 1056 obs. of 18 variables:
## $ participant : Factor w/ 11 levels "2","3","4","101",..: 4 4 4 4 4 4 4 4 4 4 ...
## $ age : int 19 19 19 19 19 19 19 19 19 19 ...
## $ expName : Factor w/ 4 levels "V1","V1_RSI_150_UR",..: 2 2 2 2 2 2 2 2 2 2 ...
## $ phase : Factor w/ 1 level "exp": 1 1 1 1 1 1 1 1 1 1 ...
## $ BlockOrder : Factor w/ 4 levels "1","2","3","4": 1 2 3 4 1 2 3 4 1 2 ...
## $ condition : Factor w/ 4 levels "R1","R2","S1",..: 3 1 4 2 3 1 4 2 3 1 ...
## $ transition : Factor w/ 2 levels "repeat","switch": 2 1 2 1 2 1 2 1 2 1 ...
## $ task : Factor w/ 2 levels "picture","word": 1 1 2 2 1 1 2 2 1 1 ...
## $ emotionality: Factor w/ 2 levels "negative","neutral": 2 2 1 1 1 2 2 1 1 2 ...
## $ pos_xy : Factor w/ 4 levels "[-0.35, -0.25]",..: 2 4 3 1 2 4 3 1 2 4 ...
## $ list : Factor w/ 12 levels "v1_R1.xlsx","v1_R2.xlsx",..: 3 1 4 2 3 1 4 2 3 1 ...
## $ word : Factor w/ 96 levels "ALCOHOLIC","ANGER",..: 48 78 63 79 87 31 37 77 20 12 ...
## $ word_corr : chr "c" "x" "c" "c" ...
## $ picture : Factor w/ 96 levels "Bilder/1_M.bmp",..: 57 8 88 84 34 64 87 22 4 65 ...
## $ pict_corr : chr "n" "m" "m" "n" ...
## $ corr_resp : chr "n" "m" "c" "c" ...
## $ resp.corr : int 1 1 1 1 1 1 1 0 1 1 ...
## $ resp.rt : num 1.212 0.924 2.646 1.754 1.242 ...
# convert s to ms in column resp.rt
data_raw$resp.rt <- data_raw$resp.rt * 1000
study_long <- data_raw %>%
group_by(participant, expName, age, transition, task, emotionality) %>%
summarise(acc = mean(resp.corr), rt = median(resp.rt)) %>%
ungroup()
## `summarise()` has grouped output by 'participant', 'expName', 'age', 'transition', 'task'. You can override using the `.groups` argument.
# save
save(study_long, file = "study_long.Rda")
#### Descriptives ####
rm(list=ls())
load("study_long.Rda")
str(study_long)
## tibble [88 x 8] (S3: tbl_df/tbl/data.frame)
## $ participant : Factor w/ 11 levels "2","3","4","101",..: 1 1 1 1 1 1 1 1 2 2 ...
## $ expName : Factor w/ 4 levels "V1","V1_RSI_150_UR",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ age : int [1:88] 20 20 20 20 20 20 20 20 19 19 ...
## $ transition : Factor w/ 2 levels "repeat","switch": 1 1 1 1 2 2 2 2 1 1 ...
## $ task : Factor w/ 2 levels "picture","word": 1 1 2 2 1 1 2 2 1 1 ...
## $ emotionality: Factor w/ 2 levels "negative","neutral": 1 2 1 2 1 2 1 2 1 2 ...
## $ acc : num [1:88] 0.917 1 0.75 0.583 1 ...
## $ rt : num [1:88] 1115 973 1235 1173 2266 ...
# overall accuracy rates per participant
study_long%>%
group_by(participant) %>%
summarise(Macc_overall = mean(acc))
## # A tibble: 11 x 2
## participant Macc_overall
## <fct> <dbl>
## 1 2 0.844
## 2 3 0.958
## 3 4 0.896
## 4 101 0.844
## 5 102 0.698
## 6 103 0.646
## 7 105 0.927
## 8 106 0.917
## 9 107 0.958
## 10 110 0.969
## 11 113 0.865
# subjects 102 and 103 have too low accuracy rates!
study_long %>%
group_by(transition, task, emotionality) %>%
summarise(Macc = mean(acc), Mrt = mean(rt))
## `summarise()` has grouped output by 'transition', 'task'. You can override using the `.groups` argument.
## # A tibble: 8 x 5
## # Groups: transition, task [4]
## transition task emotionality Macc Mrt
## <fct> <fct> <fct> <dbl> <dbl>
## 1 repeat picture negative 0.947 1052.
## 2 repeat picture neutral 0.917 1105.
## 3 repeat word negative 0.795 1344.
## 4 repeat word neutral 0.856 1248.
## 5 switch picture negative 0.917 1674.
## 6 switch picture neutral 0.917 1641.
## 7 switch word negative 0.712 1914.
## 8 switch word neutral 0.864 2003.
se <- function(x) sqrt(var(x)/length(x)) ## function for standard error
ts <- study_long %>%
group_by(transition, task, emotionality) %>%
summarise(m_rt = mean(rt),
sd_rt = round(sd(rt), digits = 0),
se_rt = round(se(rt), digits = 0),
m_acc = mean(acc),
sd_acc = round(sd(acc), digits = 3),
se_acc = round(se(acc), digits = 3),
n = length(acc))
## `summarise()` has grouped output by 'transition', 'task'. You can override using the `.groups` argument.
# plot accuracy
p1 <- ggplot(ts, aes(x=task:emotionality, y= m_acc, fill=transition)) +
geom_bar(stat = "identity", position=position_dodge(), color = "black") +
geom_errorbar(aes(ymin=m_acc-se_acc, ymax=m_acc+se_acc), width=.2, position = position_dodge(.9)) +
scale_y_continuous(expand = c(0,0),
limits = c(0,1.1)) +
scale_fill_manual(values = c("#56B4E9", "#0072B2")) +
labs(title = "Study phase",
x="Task",
y = "Accuracy rate",
fill = "Transition") +
theme_classic(base_size = 16)
p1
ggsave(p1, filename = "study_plot_acc.png", height = 10, width = 15, bg = "transparent")
# plot response times
p2 <- ggplot(ts, aes(x=task:emotionality, y= m_rt, fill=transition)) +
geom_bar(stat = "identity", position=position_dodge(), color = "black") +
geom_errorbar(aes(ymin=m_rt-se_rt, ymax=m_rt+se_rt), width=.2, position = position_dodge(.9)) +
scale_y_continuous(breaks = c(0,100,200,300,400,500,600,700,800,900,1000,
1100,1200,1300,1400,1500,1600,1700,1800,1900,
2000,2100,2200,2300,2400,2500,2600, 2700),
expand = c(0,0),
limits = c(0,2600)) +
scale_fill_manual(values = c("#56B4E9", "#0072B2")) +
labs(title = "Study phase",
x="Task",
y = "Response times in ms",
fill = "Transition") +
theme_classic(base_size = 16)
p2
ggsave(p2, filename = "study_plot_rt.png", height = 10, width = 15, bg = "transparent")
### ANOVAs ####
library(ez)
library(schoRsch)
library(apa)
rm(list=ls())
load("study_long.Rda")
str(study_long)
## tibble [88 x 8] (S3: tbl_df/tbl/data.frame)
## $ participant : Factor w/ 11 levels "2","3","4","101",..: 1 1 1 1 1 1 1 1 2 2 ...
## $ expName : Factor w/ 4 levels "V1","V1_RSI_150_UR",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ age : int [1:88] 20 20 20 20 20 20 20 20 19 19 ...
## $ transition : Factor w/ 2 levels "repeat","switch": 1 1 1 1 2 2 2 2 1 1 ...
## $ task : Factor w/ 2 levels "picture","word": 1 1 2 2 1 1 2 2 1 1 ...
## $ emotionality: Factor w/ 2 levels "negative","neutral": 1 2 1 2 1 2 1 2 1 2 ...
## $ acc : num [1:88] 0.917 1 0.75 0.583 1 ...
## $ rt : num [1:88] 1115 973 1235 1173 2266 ...
# ANOVA on accuracy:
aov_acc <- ezANOVA(
study_long
, dv = .(acc)
, wid = .(participant)
, within = .(transition, task, emotionality)
, type = 3
, detailed = TRUE
)
anova_out(aov_acc) # print results
## $`--- ANOVA RESULTS ------------------------------------`
## Effect MSE df1 df2 F p petasq getasq
## 1 (Intercept) 0.090009470 1 10 732.42 0.000 0.99 0.97
## 2 transition 0.009043561 1 10 1.71 0.220 0.15 0.01
## 3 task 0.083727904 1 10 3.62 0.086 0.27 0.13
## 4 emotionality 0.003267045 1 10 13.91 0.004 0.58 0.02
## 5 transition:task 0.004403409 1 10 0.65 0.441 0.06 0.00
## 6 transition:emotionality 0.004056187 1 10 4.98 0.050 0.33 0.01
## 7 task:emotionality 0.004940025 1 10 16.36 0.002 0.62 0.04
## 8 transition:task:emotionality 0.003835227 1 10 1.32 0.278 0.12 0.00
##
## $`--- SPHERICITY TESTS ------------------------------------`
## [1] "N/A"
##
## $`--- FORMATTED RESULTS ------------------------------------`
## Effect Text
## 1 (Intercept) F(1, 10) = 732.42, p < .001, np2 = .99
## 2 transition F(1, 10) = 1.71, p = .220, np2 = .15
## 3 task F(1, 10) = 3.62, p = .086, np2 = .27
## 4 emotionality F(1, 10) = 13.91, p = .004, np2 = .58
## 5 transition:task F(1, 10) = 0.65, p = .441, np2 = .06
## 6 transition:emotionality F(1, 10) = 4.98, p = .050, np2 = .33
## 7 task:emotionality F(1, 10) = 16.36, p = .002, np2 = .62
## 8 transition:task:emotionality F(1, 10) = 1.32, p = .278, np2 = .12
##
## $`NOTE:`
## [1] "Reporting unadjusted p-values."
# ANOVA on response times:
aov_acc <- ezANOVA(
study_long
, dv = .(rt)
, wid = .(participant)
, within = .(transition, task, emotionality)
, type = 3
, detailed = TRUE
)
anova_out(aov_acc) # print results
## $`--- ANOVA RESULTS ------------------------------------`
## Effect MSE df1 df2 F p petasq getasq
## 1 (Intercept) 1172649.01 1 10 168.33 0.000 0.94 0.92
## 2 transition 270550.72 1 10 31.37 0.000 0.76 0.32
## 3 task 82121.23 1 10 18.06 0.002 0.64 0.08
## 4 emotionality 29162.99 1 10 0.01 0.931 0.00 0.00
## 5 transition:task 87181.90 1 10 0.44 0.524 0.04 0.00
## 6 transition:emotionality 48697.81 1 10 0.27 0.614 0.03 0.00
## 7 task:emotionality 70245.38 1 10 0.01 0.908 0.00 0.00
## 8 transition:task:emotionality 48282.21 1 10 2.09 0.178 0.17 0.01
##
## $`--- SPHERICITY TESTS ------------------------------------`
## [1] "N/A"
##
## $`--- FORMATTED RESULTS ------------------------------------`
## Effect Text
## 1 (Intercept) F(1, 10) = 168.33, p < .001, np2 = .94
## 2 transition F(1, 10) = 31.37, p < .001, np2 = .76
## 3 task F(1, 10) = 18.06, p = .002, np2 = .64
## 4 emotionality F(1, 10) = 0.01, p = .931, np2 < .01
## 5 transition:task F(1, 10) = 0.44, p = .524, np2 = .04
## 6 transition:emotionality F(1, 10) = 0.27, p = .614, np2 = .03
## 7 task:emotionality F(1, 10) = 0.01, p = .908, np2 < .01
## 8 transition:task:emotionality F(1, 10) = 2.09, p = .178, np2 = .17
##
## $`NOTE:`
## [1] "Reporting unadjusted p-values."
Testphase
# libraries
library(tidyverse)
## prepare workspace
cat('\014') # clear console
rm(list=ls()) # clear workspace
## import data
# "full.names=T" ist wie ein passport, der path wird auch angehängt
temp = list.files(pattern="*.csv", path = "./data_re", full.names = T)
myfiles = lapply(temp, read.csv)
myfiles2 = bind_rows(myfiles)
str(myfiles2)
## 'data.frame': 2664 obs. of 43 variables:
## $ ï..stimulus : chr "DEDUCTION" "PLANT" "AGE" "EXERCISE" ...
## $ condition : chr "new" "S2" "R2" "R1" ...
## $ transition : chr "new" "switch" "repeat" "repeat" ...
## $ task : chr "new" "word" "word" "picture" ...
## $ corr_respTS : chr "new" "c" "x" "m" ...
## $ category : chr "x" "c" "x" "x" ...
## $ attention : chr "new" "target" "target" "distractor" ...
## $ old_new : chr "new" "old" "old" "old" ...
## $ corr_resp : chr "n" "v" "v" "v" ...
## $ emotionality : chr "0" "0" "0" "0" ...
## $ phase : chr "practice" "practice" "practice" "practice" ...
## $ practWord_loop.thisRepN : int 0 0 0 0 NA NA NA NA NA NA ...
## $ practWord_loop.thisTrialN: int 0 1 2 3 NA NA NA NA NA NA ...
## $ practWord_loop.thisN : int 0 1 2 3 NA NA NA NA NA NA ...
## $ practWord_loop.thisIndex : int 3 1 2 0 NA NA NA NA NA NA ...
## $ practPict_loop.thisRepN : int NA NA NA NA 0 0 0 0 NA NA ...
## $ practPict_loop.thisTrialN: int NA NA NA NA 0 1 2 3 NA NA ...
## $ practPict_loop.thisN : int NA NA NA NA 0 1 2 3 NA NA ...
## $ practPict_loop.thisIndex : int NA NA NA NA 3 1 0 2 NA NA ...
## $ Word_loop.thisRepN : int NA NA NA NA NA NA NA NA 0 0 ...
## $ Word_loop.thisTrialN : int NA NA NA NA NA NA NA NA 0 1 ...
## $ Word_loop.thisN : int NA NA NA NA NA NA NA NA 0 1 ...
## $ Word_loop.thisIndex : int NA NA NA NA NA NA NA NA 80 98 ...
## $ Pict_loop.thisRepN : int NA NA NA NA NA NA NA NA NA NA ...
## $ Pict_loop.thisTrialN : int NA NA NA NA NA NA NA NA NA NA ...
## $ Pict_loop.thisN : int NA NA NA NA NA NA NA NA NA NA ...
## $ Pict_loop.thisIndex : int NA NA NA NA NA NA NA NA NA NA ...
## $ old_new_word_resp.keys : chr "n" "n" "n" "v" ...
## $ old_new_word_resp.corr : int 1 0 0 1 NA NA NA NA 1 1 ...
## $ old_new_word_resp.rt : num 2.93 4.2 1.71 5.56 NA ...
## $ r_k_word_resp.keys : chr "None" "None" "None" "2" ...
## $ r_k_word_resp.rt : num NA NA NA 5.02 NA ...
## $ old_new_pict_resp.keys : chr "" "" "" "" ...
## $ old_new_pict_resp.corr : int NA NA NA NA 1 1 1 1 NA NA ...
## $ old_new_pict_resp.rt : num NA NA NA NA 3.33 ...
## $ r_k_pict_resp.keys : chr "" "" "" "" ...
## $ r_k_pict_resp.rt : num NA NA NA NA NA ...
## $ participant : int 102 102 102 102 102 102 102 102 102 102 ...
## $ date : chr "2021_Dec_06_1316" "2021_Dec_06_1316" "2021_Dec_06_1316" "2021_Dec_06_1316" ...
## $ expName : chr "V2_rec" "V2_rec" "V2_rec" "V2_rec" ...
## $ psychopyVersion : chr "2021.2.3" "2021.2.3" "2021.2.3" "2021.2.3" ...
## $ frameRate : num 59.9 59.9 59.9 59.9 59.9 ...
## $ X : logi NA NA NA NA NA NA ...
#### Rows ####
unique(myfiles2$phase)
## [1] "practice" "exp"
# relevant rows
# exclude practice trials and warmup trials
myfiles3 <- myfiles2[myfiles2$phase != 'practice', ]
myfiles3$phase <- factor(myfiles3$phase) # refactor data frame (in order to drop cleared levels completely)
unique(myfiles3$phase) # now there won't be a error message when renaming levels
## [1] exp
## Levels: exp
## remove columns with all NAs
not_all_na <- function(x) any(!is.na(x))
myfiles4 <- myfiles3 %>% select(where(not_all_na))
## when you want remove columns with only some na's
# not_any_na <- function(x) all(!is.na(x))
# myfiles5 <- myfiles3 %>%
# select(where(not_any_na))
## relevant columns
colnames(myfiles4)
## [1] "ï..stimulus" "condition" "transition"
## [4] "task" "corr_respTS" "category"
## [7] "attention" "old_new" "corr_resp"
## [10] "emotionality" "phase" "Word_loop.thisRepN"
## [13] "Word_loop.thisTrialN" "Word_loop.thisN" "Word_loop.thisIndex"
## [16] "Pict_loop.thisRepN" "Pict_loop.thisTrialN" "Pict_loop.thisN"
## [19] "Pict_loop.thisIndex" "old_new_word_resp.keys" "old_new_word_resp.corr"
## [22] "old_new_word_resp.rt" "r_k_word_resp.keys" "r_k_word_resp.rt"
## [25] "old_new_pict_resp.keys" "old_new_pict_resp.corr" "old_new_pict_resp.rt"
## [28] "r_k_pict_resp.keys" "r_k_pict_resp.rt" "participant"
## [31] "date" "expName" "psychopyVersion"
## [34] "frameRate"
keep <- c("participant","expName", "phase", "ï..stimulus",
"condition", "transition", "task", "emotionality","category", "attention",
"old_new_word_resp.corr",
"old_new_pict_resp.corr",
"r_k_word_resp.keys",
"r_k_pict_resp.keys")
data_raw <- subset(myfiles4, select = keep)
colnames(data_raw)
## [1] "participant" "expName" "phase"
## [4] "ï..stimulus" "condition" "transition"
## [7] "task" "emotionality" "category"
## [10] "attention" "old_new_word_resp.corr" "old_new_pict_resp.corr"
## [13] "r_k_word_resp.keys" "r_k_pict_resp.keys"
# rename column
colnames(data_raw)[colnames(data_raw)=="ï..stimulus"] <- "stimulus"
colnames(data_raw)
## [1] "participant" "expName" "phase"
## [4] "stimulus" "condition" "transition"
## [7] "task" "emotionality" "category"
## [10] "attention" "old_new_word_resp.corr" "old_new_pict_resp.corr"
## [13] "r_k_word_resp.keys" "r_k_pict_resp.keys"
str(data_raw)
## 'data.frame': 2592 obs. of 14 variables:
## $ participant : int 102 102 102 102 102 102 102 102 102 102 ...
## $ expName : chr "V2_rec" "V2_rec" "V2_rec" "V2_rec" ...
## $ phase : Factor w/ 1 level "exp": 1 1 1 1 1 1 1 1 1 1 ...
## $ stimulus : chr "APPROACH" "MISERY" "MOBILITY" "ALCOHOLIC" ...
## $ condition : chr "S1" "new" "S1" "R1" ...
## $ transition : chr "switch" "new" "switch" "repeat" ...
## $ task : chr "picture" "new" "picture" "picture" ...
## $ emotionality : chr "neutral" "negative" "neutral" "negative" ...
## $ category : chr "x" "x" "x" "c" ...
## $ attention : chr "distractor" "new" "distractor" "distractor" ...
## $ old_new_word_resp.corr: int 1 1 0 1 1 1 1 1 0 1 ...
## $ old_new_pict_resp.corr: int NA NA NA NA NA NA NA NA NA NA ...
## $ r_k_word_resp.keys : chr "2" "None" "None" "1" ...
## $ r_k_pict_resp.keys : chr "" "" "" "" ...
data_raw$participant <- factor(data_raw$participant)
data_raw$expName <- factor(data_raw$expName)
data_raw$condition <- factor(data_raw$condition)
data_raw$transition <- factor(data_raw$transition)
data_raw$task <- factor(data_raw$task)
data_raw$emotionality <- factor(data_raw$emotionality)
data_raw$category <- factor(data_raw$category)
data_raw$attention <- factor(data_raw$attention)
str(data_raw)
## 'data.frame': 2592 obs. of 14 variables:
## $ participant : Factor w/ 9 levels "2","3","4","102",..: 4 4 4 4 4 4 4 4 4 4 ...
## $ expName : Factor w/ 3 levels "V1_recog","V2_rec",..: 2 2 2 2 2 2 2 2 2 2 ...
## $ phase : Factor w/ 1 level "exp": 1 1 1 1 1 1 1 1 1 1 ...
## $ stimulus : chr "APPROACH" "MISERY" "MOBILITY" "ALCOHOLIC" ...
## $ condition : Factor w/ 5 levels "new","R1","R2",..: 4 1 4 2 4 2 4 1 5 2 ...
## $ transition : Factor w/ 3 levels "new","repeat",..: 3 1 3 2 3 2 3 1 3 2 ...
## $ task : Factor w/ 3 levels "new","picture",..: 2 1 2 2 2 2 2 1 3 2 ...
## $ emotionality : Factor w/ 3 levels "0","negative",..: 3 2 3 2 3 2 3 2 3 2 ...
## $ category : Factor w/ 4 levels "c","m","n","x": 4 4 4 1 1 4 1 1 4 4 ...
## $ attention : Factor w/ 3 levels "distractor","new",..: 1 2 1 1 1 1 1 2 3 1 ...
## $ old_new_word_resp.corr: int 1 1 0 1 1 1 1 1 0 1 ...
## $ old_new_pict_resp.corr: int NA NA NA NA NA NA NA NA NA NA ...
## $ r_k_word_resp.keys : chr "2" "None" "None" "1" ...
## $ r_k_pict_resp.keys : chr "" "" "" "" ...
# replace None with 0
data_raw[data_raw==""]<-NA
# combine accuracy of wordlist and picturelist to ACC column
colnames(data_raw)
## [1] "participant" "expName" "phase"
## [4] "stimulus" "condition" "transition"
## [7] "task" "emotionality" "category"
## [10] "attention" "old_new_word_resp.corr" "old_new_pict_resp.corr"
## [13] "r_k_word_resp.keys" "r_k_pict_resp.keys"
testphase <- data_raw %>%
mutate(ACC = coalesce(old_new_word_resp.corr, old_new_pict_resp.corr))
testphase2 <- testphase %>%
mutate(RK = coalesce(r_k_word_resp.keys, r_k_pict_resp.keys))
# create new Column "running" indicating which Block was running (word or picture)
testphase2$running <- 99
# when character in column "stimulus" starts with "Bilder" write "picture" to column "running"
for (i in 1:length(testphase2$running)) {
if(startsWith(testphase2$stimulus[i],"Bilder")) {testphase2$running[i] <- "picture"}
else{testphase2$running[i] <- "word"}
}
testphase2$running <- factor(testphase2$running)
## relevant columns
colnames(testphase2)
## [1] "participant" "expName" "phase"
## [4] "stimulus" "condition" "transition"
## [7] "task" "emotionality" "category"
## [10] "attention" "old_new_word_resp.corr" "old_new_pict_resp.corr"
## [13] "r_k_word_resp.keys" "r_k_pict_resp.keys" "ACC"
## [16] "RK" "running"
keep <- c("participant","expName", "stimulus", "running",
"condition", "transition", "task", "emotionality","category", "attention",
"ACC", "RK")
testphase3 <- subset(testphase2, select = keep)
colnames(testphase3)
## [1] "participant" "expName" "stimulus" "running" "condition"
## [6] "transition" "task" "emotionality" "category" "attention"
## [11] "ACC" "RK"
# aggregate to means of condiitons
testphase_long <- testphase3 %>%
group_by(participant, expName, running, condition, attention, transition, emotionality) %>%
summarise(acc = mean(ACC), items = length(ACC)) %>%
ungroup()
## `summarise()` has grouped output by 'participant', 'expName', 'running', 'condition', 'attention', 'transition'. You can override using the `.groups` argument.
judgements <- testphase3[testphase3$condition != "new",] %>% # only old items
group_by(participant, attention, transition, emotionality, running, RK) %>%
summarise(count_judgements = length(RK)) %>%
complete(RK) %>%
ungroup()
## `summarise()` has grouped output by 'participant', 'attention', 'transition', 'emotionality', 'running'. You can override using the `.groups` argument.
# "None" = "incorrect" response = miss
judgements <- judgements %>%
spread(key = RK, value = count_judgements)
# replace NAs with 0
unique(judgements$`1`)
## [1] 4 1 NA 7 5 9 2 11 3 6 8 10
judgements$`1`[is.na(judgements$`1`)] <- 0
unique(judgements$`1`)
## [1] 4 1 0 7 5 9 2 11 3 6 8 10
unique(judgements$`2`)
## [1] NA 3 1 4 10 2 9 8 6 7 5 12 11
judgements$`2`[is.na(judgements$`2`)] <- 0
unique(judgements$`2`)
## [1] 0 3 1 4 10 2 9 8 6 7 5 12 11
# calculate proportion of remember and know responses for hits
judgements$p_remember <- 1/(12/judgements$`1`) # we have 12 items per subject and per condition
judgements$p_know <- 1/(12/judgements$`2`) # we have 12 items per subject and per condition
# proportion remember responses + proportion know responses = hit rate
# merge two dataframes
str(testphase_long)
## tibble [171 x 9] (S3: tbl_df/tbl/data.frame)
## $ participant : Factor w/ 9 levels "2","3","4","102",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ expName : Factor w/ 3 levels "V1_recog","V2_rec",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ running : Factor w/ 2 levels "picture","word": 1 1 1 1 1 1 1 1 1 2 ...
## $ condition : Factor w/ 5 levels "new","R1","R2",..: 1 2 2 3 3 4 4 5 5 1 ...
## $ attention : Factor w/ 3 levels "distractor","new",..: 2 3 3 1 1 3 3 1 1 2 ...
## $ transition : Factor w/ 3 levels "new","repeat",..: 1 2 2 2 2 3 3 3 3 1 ...
## $ emotionality: Factor w/ 3 levels "0","negative",..: 1 2 3 2 3 2 3 2 3 2 ...
## $ acc : num [1:171] 0.917 0.917 0.583 0.333 0.333 ...
## $ items : int [1:171] 48 12 12 12 12 12 12 12 12 24 ...
levels(testphase_long$transition)
## [1] "new" "repeat" "switch"
str(judgements)
## tibble [144 x 10] (S3: tbl_df/tbl/data.frame)
## $ participant : Factor w/ 9 levels "2","3","4","102",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ attention : Factor w/ 3 levels "distractor","new",..: 1 1 1 1 1 1 1 1 3 3 ...
## $ transition : Factor w/ 3 levels "new","repeat",..: 2 2 2 2 3 3 3 3 2 2 ...
## $ emotionality: Factor w/ 3 levels "0","negative",..: 2 2 3 3 2 2 3 3 2 2 ...
## $ running : Factor w/ 2 levels "picture","word": 1 2 1 2 1 2 1 2 1 2 ...
## $ 1 : num [1:144] 4 1 4 0 4 1 7 0 7 1 ...
## $ 2 : num [1:144] 0 3 0 0 1 3 0 1 4 10 ...
## $ None : int [1:144] 8 8 8 12 7 8 5 11 1 1 ...
## $ p_remember : num [1:144] 0.3333 0.0833 0.3333 0 0.3333 ...
## $ p_know : num [1:144] 0 0.25 0 0 0.0833 ...
# dfjudgments is shorter than dftestphase_long because "new" items have been excluded
test_long <- merge(testphase_long,judgements,
all = TRUE) # keep all columns and rows to not lose "new" items
# create final file
str(test_long)
## 'data.frame': 171 obs. of 14 variables:
## $ participant : Factor w/ 9 levels "2","3","4","102",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ running : Factor w/ 2 levels "picture","word": 1 1 1 1 1 1 1 1 1 2 ...
## $ attention : Factor w/ 3 levels "distractor","new",..: 1 1 1 1 2 3 3 3 3 1 ...
## $ transition : Factor w/ 3 levels "new","repeat",..: 2 2 3 3 1 2 2 3 3 2 ...
## $ emotionality: Factor w/ 3 levels "0","negative",..: 2 3 2 3 1 2 3 2 3 2 ...
## $ expName : Factor w/ 3 levels "V1_recog","V2_rec",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ condition : Factor w/ 5 levels "new","R1","R2",..: 3 3 5 5 1 2 2 4 4 2 ...
## $ acc : num 0.333 0.333 0.417 0.583 0.917 ...
## $ items : int 12 12 12 12 48 12 12 12 12 12 ...
## $ 1 : num 4 4 4 7 NA 7 7 5 9 1 ...
## $ 2 : num 0 0 1 0 NA 4 0 2 2 3 ...
## $ None : int 8 8 7 5 NA 1 5 5 1 8 ...
## $ p_remember : num 0.333 0.333 0.333 0.583 NA ...
## $ p_know : num 0 0 0.0833 0 NA ...
colnames(test_long)
## [1] "participant" "running" "attention" "transition" "emotionality"
## [6] "expName" "condition" "acc" "items" "1"
## [11] "2" "None" "p_remember" "p_know"
keep <- c("participant", "expName","running", "condition",
"attention", "transition", "emotionality",
"acc", "items", "p_remember", "p_know")
test_long <- subset(test_long, select = keep)
colnames(test_long)
## [1] "participant" "expName" "running" "condition" "attention"
## [6] "transition" "emotionality" "acc" "items" "p_remember"
## [11] "p_know"
# save
save(test_long, file = "test_long.Rda")
#### Check data ####
library(tidyverse)
## prepare workspace
rm(list=ls()) # clear workspace
load("test_long.Rda")
str(test_long)
## 'data.frame': 171 obs. of 11 variables:
## $ participant : Factor w/ 9 levels "2","3","4","102",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ expName : Factor w/ 3 levels "V1_recog","V2_rec",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ running : Factor w/ 2 levels "picture","word": 1 1 1 1 1 1 1 1 1 2 ...
## $ condition : Factor w/ 5 levels "new","R1","R2",..: 3 3 5 5 1 2 2 4 4 2 ...
## $ attention : Factor w/ 3 levels "distractor","new",..: 1 1 1 1 2 3 3 3 3 1 ...
## $ transition : Factor w/ 3 levels "new","repeat",..: 2 2 3 3 1 2 2 3 3 2 ...
## $ emotionality: Factor w/ 3 levels "0","negative",..: 2 3 2 3 1 2 3 2 3 2 ...
## $ acc : num 0.333 0.333 0.417 0.583 0.917 ...
## $ items : int 12 12 12 12 48 12 12 12 12 12 ...
## $ p_remember : num 0.333 0.333 0.333 0.583 NA ...
## $ p_know : num 0 0 0.0833 0 NA ...
load("study_long.Rda")
str(study_long)
## tibble [88 x 8] (S3: tbl_df/tbl/data.frame)
## $ participant : Factor w/ 11 levels "2","3","4","101",..: 1 1 1 1 1 1 1 1 2 2 ...
## $ expName : Factor w/ 4 levels "V1","V1_RSI_150_UR",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ age : int [1:88] 20 20 20 20 20 20 20 20 19 19 ...
## $ transition : Factor w/ 2 levels "repeat","switch": 1 1 1 1 2 2 2 2 1 1 ...
## $ task : Factor w/ 2 levels "picture","word": 1 1 2 2 1 1 2 2 1 1 ...
## $ emotionality: Factor w/ 2 levels "negative","neutral": 1 2 1 2 1 2 1 2 1 2 ...
## $ acc : num [1:88] 0.917 1 0.75 0.583 1 ...
## $ rt : num [1:88] 1115 973 1235 1173 2266 ...
# convert to wide format
study_wide <- study_long %>%
pivot_wider(names_from = c(transition, task, emotionality),
values_from = c(acc, rt))
test_wide <- test_long %>%
pivot_wider(names_from = c(running, condition, attention, transition, emotionality),
values_from = c(items, acc, p_remember, p_know))
# save as csv files
write.csv(test_wide, file = "test_wide.csv")
write.csv(study_wide, file = "study_wide.csv")
## check if the same version was run in study and test phase per subject
controlvers <- left_join(study_wide[,c("participant", "expName")],
test_wide[,c("participant", "expName")], by = "participant")
controlvers$studyVers <- substr(controlvers$expName.x, start = 1, stop = 2)
controlvers$testVers <- substr(controlvers$expName.y, start = 1, stop = 2)
## identify participants with low accuracy in study phase
# overall accuracy rates per participant
study_long%>%
group_by(participant) %>%
summarise(Macc_overall = mean(acc))
## # A tibble: 11 x 2
## participant Macc_overall
## <fct> <dbl>
## 1 2 0.844
## 2 3 0.958
## 3 4 0.896
## 4 101 0.844
## 5 102 0.698
## 6 103 0.646
## 7 105 0.927
## 8 106 0.917
## 9 107 0.958
## 10 110 0.969
## 11 113 0.865
# subjects 102 and 103 have too low accuracy rates!
exclusion <- study_long %>%
group_by(participant) %>%
summarise(Macc_overall = mean(acc))
test_long <- merge(test_long, exclusion, by = "participant") # merge computed columns
excl_part <- test_long[test_long$Macc_overall < 0.7, ] # extract participants with accuracy < 70%
unique(excl_part$participant) # see which participants are excluded: 102, 103
## [1] 102 103
## Levels: 2 3 4 102 103 106 107 110 113
test_long <- test_long[test_long$Macc_overall >= 0.7, ] # delete participant with error rate > 30%
test_long$participant <- factor(test_long$participant)
levels(test_long$participant) # see only included participants
## [1] "2" "3" "4" "106" "107" "110" "113"
## exclude participants with low accuracy in study phase
# 102 and 103
test_long <- test_long[test_long$participant != 102 &
test_long$participant != 103,]
# save
save(test_long, file = "test_long.Rda")
#### Descriptives ####
library(tidyverse)
test_long[test_long$condition != "new",] %>%
group_by(running, attention, transition, emotionality) %>%
summarise(Macc = mean(acc))
## `summarise()` has grouped output by 'running', 'attention', 'transition'. You can override using the `.groups` argument.
## # A tibble: 16 x 5
## # Groups: running, attention, transition [8]
## running attention transition emotionality Macc
## <fct> <fct> <fct> <fct> <dbl>
## 1 picture distractor repeat negative 0.321
## 2 picture distractor repeat neutral 0.345
## 3 picture distractor switch negative 0.417
## 4 picture distractor switch neutral 0.452
## 5 picture target repeat negative 0.75
## 6 picture target repeat neutral 0.690
## 7 picture target switch negative 0.726
## 8 picture target switch neutral 0.762
## 9 word distractor repeat negative 0.310
## 10 word distractor repeat neutral 0.0238
## 11 word distractor switch negative 0.333
## 12 word distractor switch neutral 0.119
## 13 word target repeat negative 0.881
## 14 word target repeat neutral 0.833
## 15 word target switch negative 0.869
## 16 word target switch neutral 0.726
se <- function(x) sqrt(var(x)/length(x)) ## function for standard error
re <- test_long[test_long$condition != "new",] %>%
group_by(running, attention, transition, emotionality) %>%
summarise(m_acc = mean(acc),
sd_acc = round(sd(acc), digits = 3),
se_acc = round(se(acc), digits = 3),
n = length(acc))
## `summarise()` has grouped output by 'running', 'attention', 'transition'. You can override using the `.groups` argument.
# plot recognition performance
p3 <- ggplot(re, aes(x=emotionality:attention, y= m_acc, fill=transition)) +
facet_grid(running ~.) +
geom_bar(stat = "identity", position=position_dodge(), color = "black") +
geom_errorbar(aes(ymin=m_acc-se_acc, ymax=m_acc+se_acc), width=.2, position = position_dodge(.9)) +
scale_y_continuous(expand = c(0,0),
limits = c(0,1.1)) +
scale_fill_manual(values = c("#56B4E9", "#0072B2")) +
labs(title = "Test phase",
x="Emotionality:Attention",
y = "Hits",
fill = "Transition") +
theme_classic(base_size = 16)
p3
ggsave(p3, filename = "test_plot.png", height = 10, width = 15, bg = "transparent")
### ANOVAs ####
library(ez)
library(schoRsch)
library(apa)
rm(list=ls())
load("test_long.Rda")
str(test_long)
## 'data.frame': 133 obs. of 12 variables:
## $ participant : Factor w/ 7 levels "2","3","4","106",..: 4 4 4 4 4 4 4 4 4 4 ...
## $ expName : Factor w/ 3 levels "V1_recog","V2_rec",..: 2 2 2 2 2 2 2 2 2 2 ...
## $ running : Factor w/ 2 levels "picture","word": 1 1 1 1 1 1 1 1 1 2 ...
## $ condition : Factor w/ 5 levels "new","R1","R2",..: 3 3 5 5 1 2 2 4 4 2 ...
## $ attention : Factor w/ 3 levels "distractor","new",..: 1 1 1 1 2 3 3 3 3 1 ...
## $ transition : Factor w/ 3 levels "new","repeat",..: 2 2 3 3 1 2 2 3 3 2 ...
## $ emotionality: Factor w/ 3 levels "0","negative",..: 2 3 2 3 1 2 3 2 3 2 ...
## $ acc : num 0.667 0.333 0.417 0.25 0.854 ...
## $ items : int 12 12 12 12 48 12 12 12 12 12 ...
## $ p_remember : num 0.3333 0.1667 0.1667 0.0833 NA ...
## $ p_know : num 0.333 0.167 0.25 0.167 NA ...
## $ Macc_overall: num 0.917 0.917 0.917 0.917 0.917 ...
# ANOVA on accuracy:
aov_acc <- ezANOVA(
test_long[test_long$condition != "new",]
, dv = .(acc)
, wid = .(participant)
, within = .(running, attention, transition, emotionality)
, type = 3
, detailed = TRUE
)
## Warning: You have removed one or more levels from variable "attention".
## Refactoring for ANOVA.
## Warning: You have removed one or more levels from variable "transition".
## Refactoring for ANOVA.
## Warning: You have removed one or more levels from variable "emotionality".
## Refactoring for ANOVA.
anova_out(aov_acc) # print results
## $`--- ANOVA RESULTS ------------------------------------`
## Effect MSE df1 df2 F p
## 1 (Intercept) 0.085317460 1 6 375.70 0.000
## 2 running 0.068700397 1 6 0.87 0.388
## 3 attention 0.009259259 1 6 724.83 0.000
## 4 transition 0.013020833 1 6 2.10 0.197
## 5 emotionality 0.019593254 1 6 9.57 0.021
## 6 running:attention 0.018353175 1 6 30.49 0.001
## 7 running:transition 0.018229167 1 6 1.50 0.267
## 8 attention:transition 0.019634590 1 6 3.44 0.113
## 9 running:emotionality 0.007771164 1 6 29.69 0.002
## 10 attention:emotionality 0.010664683 1 6 2.10 0.198
## 11 transition:emotionality 0.030960648 1 6 0.10 0.765
## 12 running:attention:transition 0.004918981 1 6 0.62 0.462
## 13 running:attention:emotionality 0.008349868 1 6 8.09 0.029
## 14 running:transition:emotionality 0.025586971 1 6 0.29 0.608
## 15 attention:transition:emotionality 0.013599537 1 6 0.22 0.653
## 16 running:attention:transition:emotionality 0.007812500 1 6 3.50 0.111
## petasq getasq
## 1 0.98 0.94
## 2 0.13 0.03
## 3 0.99 0.76
## 4 0.26 0.01
## 5 0.61 0.08
## 6 0.84 0.20
## 7 0.20 0.01
## 8 0.36 0.03
## 9 0.83 0.10
## 10 0.26 0.01
## 11 0.02 0.00
## 12 0.09 0.00
## 13 0.57 0.03
## 14 0.05 0.00
## 15 0.04 0.00
## 16 0.37 0.01
##
## $`--- SPHERICITY TESTS ------------------------------------`
## [1] "N/A"
##
## $`--- FORMATTED RESULTS ------------------------------------`
## Effect
## 1 (Intercept)
## 2 running
## 3 attention
## 4 transition
## 5 emotionality
## 6 running:attention
## 7 running:transition
## 8 attention:transition
## 9 running:emotionality
## 10 attention:emotionality
## 11 transition:emotionality
## 12 running:attention:transition
## 13 running:attention:emotionality
## 14 running:transition:emotionality
## 15 attention:transition:emotionality
## 16 running:attention:transition:emotionality
## Text
## 1 F(1, 6) = 375.70, p < .001, np2 = .98
## 2 F(1, 6) = 0.87, p = .388, np2 = .13
## 3 F(1, 6) = 724.83, p < .001, np2 = .99
## 4 F(1, 6) = 2.10, p = .197, np2 = .26
## 5 F(1, 6) = 9.57, p = .021, np2 = .61
## 6 F(1, 6) = 30.49, p = .001, np2 = .84
## 7 F(1, 6) = 1.50, p = .267, np2 = .20
## 8 F(1, 6) = 3.44, p = .113, np2 = .36
## 9 F(1, 6) = 29.69, p = .002, np2 = .83
## 10 F(1, 6) = 2.10, p = .198, np2 = .26
## 11 F(1, 6) = 0.10, p = .765, np2 = .02
## 12 F(1, 6) = 0.62, p = .462, np2 = .09
## 13 F(1, 6) = 8.09, p = .029, np2 = .57
## 14 F(1, 6) = 0.29, p = .608, np2 = .05
## 15 F(1, 6) = 0.22, p = .653, np2 = .04
## 16 F(1, 6) = 3.50, p = .111, np2 = .37
##
## $`NOTE:`
## [1] "Reporting unadjusted p-values."
# Running = stimulus type