4_calculating_zscores
Jenny Richmond
23/06/2020
https://rpubs.com/jenrichmond/emgz
load packages
library(tidyverse)
library(here)
library(skimr)
options(scipen = 999) #set no scientific notationThe process
- first, make data wide using pivot_wider so that brow and cheek are in columns
- use scale() to transform RMS scores into z scores for each participant.
- then make bin wide so that each row represents a single trial and bins 1-6 are in different columns
- make new column for each bin, calculating the difference between that binZ and baselineZ.
- make z diff scores long again
how to: calculate zscores
Normally, to center a variable, you would subtract the mean of all data points from each individual data point. With scale(), this can be accomplished in one simple call.
Center variable A using the scale() function
scale(A, center = TRUE, scale = FALSE)
You can generate z-scores for variable A using the scale() function
scale(A, center = TRUE, scale = TRUE)
read in data
data <- read_csv(here("data", "combined", "2_clean_no_bl_outliers.csv"))Try it out on one pp first
pp403 <- data %>%
filter(pp_no == "pp403")
# make it wide
widepp403 <- pp403 %>%
pivot_wider(names_from = muscle, values_from = rms)
# create new variables called zbrow and zcheek using the scale function and specifying center = TRUE and scale = TRUE
widepp403$zbrow = scale(widepp403$brow, center = TRUE, scale = TRUE)
widepp403$zcheek = scale(widepp403$cheek, center = TRUE, scale = TRUE)
# Check that the mean of the new zbrow and zcheek columns is 0 - this is what we want...
summary(widepp403)## pp_no condition emotion bin
## Length:210 Length:210 Min. :626.0 Length:210
## Class :character Class :character 1st Qu.:626.0 Class :character
## Mode :character Mode :character Median :727.0 Mode :character
## Mean :770.8
## 3rd Qu.:828.0
## Max. :929.0
##
## bin_no trial brow cheek
## Min. :0 Length:210 Min. : 3.382 Min. : 2.934
## 1st Qu.:1 Class :character 1st Qu.: 5.577 1st Qu.: 3.673
## Median :3 Mode :character Median : 7.280 Median : 4.241
## Mean :3 Mean : 8.506 Mean : 6.801
## 3rd Qu.:5 3rd Qu.: 9.325 3rd Qu.: 5.708
## Max. :6 Max. :66.192 Max. :120.989
## NA's :7 NA's :7
## zbrow.V1 zcheek.V1
## Min. :-0.818495 Min. :-0.380274
## 1st Qu.:-0.467962 1st Qu.:-0.307551
## Median :-0.195849 Median :-0.251692
## Mean : 0.000000 Mean : 0.000000
## 3rd Qu.: 0.130802 3rd Qu.:-0.107447
## Max. : 9.215078 Max. :11.227675
## NA's :7 NA's :7Now do all the data
make data wide, use mutate to make new z variables
data_zscore <- data %>%
pivot_wider(names_from = muscle,
values_from = rms) %>%
group_by(pp_no) %>%
mutate(Zbrow = scale(brow, center = TRUE, scale = TRUE)) %>%
mutate(Zcheek = scale(cheek, center = TRUE, scale = TRUE))
summary(data_zscore)## pp_no condition emotion bin
## Length:10836 Length:10836 Min. :626.0 Length:10836
## Class :character Class :character 1st Qu.:701.8 Class :character
## Mode :character Mode :character Median :727.0 Mode :character
## Mean :776.7
## 3rd Qu.:828.0
## Max. :929.0
##
## bin_no trial brow cheek
## Min. :0 Length:10836 Min. : 0.7779 Min. : 1.504
## 1st Qu.:1 Class :character 1st Qu.: 4.4947 1st Qu.: 3.621
## Median :3 Mode :character Median : 7.2542 Median : 5.139
## Mean :3 Mean : 9.6268 Mean : 10.168
## 3rd Qu.:5 3rd Qu.: 11.0048 3rd Qu.: 9.662
## Max. :6 Max. :220.8444 Max. :176.645
## NA's :700 NA's :924
## Zbrow Zcheek
## Min. :-2.9500 Min. :-1.3829
## 1st Qu.:-0.5080 1st Qu.:-0.5146
## Median :-0.2471 Median :-0.2893
## Mean : 0.0000 Mean : 0.0000
## 3rd Qu.: 0.2121 3rd Qu.: 0.1066
## Max. :13.5634 Max. :11.2277
## NA's :700 NA's :924note: can also make new z-variables manually:
data_z_manual <- data_wide %>% group_by(pp_no) %>% mutate(Zbrow = (brow - mean(brow))/sd(brow)) %>% mutate(Zcheek = (cheek - mean(cheek))/sd(cheek))
Calculating Difference Scores
Need to calculate difference scores from baseline. Need to make BIN wide to allow for calculations across columns. Its a bit difficult to do that for both muscles at the same time, so lets separate and work out the difference scores for brow and cheek separately.
BROW FIRST
Add a muscle column
Just to make things easier to join back together later
brow_z <- data_zscore %>%
mutate(muscle = "brow") %>%
select(pp_no, condition, emotion, bin, trial, muscle, Zbrow) Make the bin column wide
… and rename bin_0 as BL (i.e. baseline)
brow_z_wide <- brow_z %>%
pivot_wider(names_from = bin,
values_from = Zbrow) %>%
rename(BL = bin_0)mutate() diff scores
Use wide columns to calcuate the difference between each bin column and BL, creating a new set of columns starting with “diff”, drop BL column and all columns starting with bin (i.e. raw z scores).
note - This df contains for each bin the difference between stimulus and basline, so POSITIVE difference scores = greater activity during STIM than BL and NEGATIVE difference scores = greater activity during BL than STIM
brow_z_diff <- brow_z_wide %>%
mutate(diff_bin1 = bin_1 - BL,
diff_bin2 = bin_2 - BL,
diff_bin3 = bin_3- BL,
diff_bin4 = bin_4 - BL,
diff_bin5 = bin_5 - BL,
diff_bin6 = bin_6 - BL) %>%
select(-BL, - starts_with("bin"))Make data long again
brow_z_diff_long <- brow_z_diff %>%
pivot_longer(names_to = "bin",
values_to = "Zdiff",
diff_bin1:diff_bin6)checking on missingness
library(naniar)##
## Attaching package: 'naniar'## The following object is masked from 'package:skimr':
##
## n_completevis_miss(brow_z_diff_long)
NOW CHEEK
add a muscle column
…to make things easier to join back together later
cheek_z <- data_zscore %>%
mutate(muscle = "cheek") %>%
select(pp_no, condition, emotion, bin, trial, muscle, Zcheek) Make the bin column wide
…and rename bin_0 as BL (i.e. baseline)
cheek_z_wide <- cheek_z %>%
pivot_wider(names_from = bin,
values_from = Zcheek) %>%
rename(BL = bin_0)mutate() diff scores
- Use wide columns to calcuate the difference between each bin column and BL, creating a new set of columns starting with “diff”, drop BL column and all columns starting with bin (i.e. raw z scores).
note - This df contains for each bin the difference between stimulus and basline, so POSITIVE difference scores = greater activity during STIM than BL and NEGATIVE difference scores = greater activity during BL than STIM
cheek_z_diff <- cheek_z_wide %>%
mutate(diff_bin1 = bin_1 - BL,
diff_bin2 = bin_2 - BL,
diff_bin3 = bin_3- BL,
diff_bin4 = bin_4 - BL,
diff_bin5 = bin_5 - BL,
diff_bin6 = bin_6 - BL) %>%
select(-BL, - starts_with("bin"))make data long again
cheek_z_diff_long <- cheek_z_diff %>%
pivot_longer(names_to = "bin",
values_to = "Zdiff",
diff_bin1:diff_bin6)BIND CHEEK AND BROW TOGETHER
zdiff_cheek_brow <- bind_rows(cheek_z_diff_long, brow_z_diff_long) %>%
arrange(pp_no, emotion, trial, muscle, bin)write to csv
zdiff_cheek_brow %>%
write_csv(here("data", "combined", "4_zdiff_clean.csv"))