figure 5 trial
Katherine Wong
05/07/2021
Load packages and read data first.
#load packages
library(readspss) #package to read the original datafile from OFS
library(tidyverse)## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──## ✓ ggplot2 3.3.4 ✓ purrr 0.3.4
## ✓ tibble 3.1.2 ✓ dplyr 1.0.6
## ✓ tidyr 1.1.3 ✓ stringr 1.4.0
## ✓ readr 1.4.0 ✓ forcats 0.5.1## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()#read data
data <- read.sav("Humiston & Wamsley 2019 data.sav")
#remove excluded
cleandata <- data %>% #remove excluded participants
filter(exclude=="no")Figuring out what to put into the figure
First, we’ll have a look at the graph we want to replicate. This is a screenshot from the original report:
We need to figure out how to calculate the differential bias change (for the y axis). However, luckily for us we don’t need to calculate the x axis since that is already done.
Calculating y-axis: differential bias change
According to the paper, differential bias change is calculated by “baseline minus delayed score for uncued bias subtracted from the baseline minus delayed score for cued bias”.
So the equation would look something like this:
(baseline_cued - delayed_cued) - (baseline_uncued - delayed_uncued)
We would then have to apply this to each participant’s scores.
Firstly, we have to mutate a bunch of extra columns to get what we want for the y-axis. So we mutate to get one set of brackets, again for the other set, and once again to get the final differential bias change.
differential <- cleandata %>%
select(ParticipantID, baseIATcued, weekIATcued, baseIATuncued, weekIATuncued, SWSxREM) %>%
mutate(cued_differential = baseIATcued - weekIATcued,
uncued_differential = baseIATuncued - weekIATuncued,
diff_bias_change = cued_differential - uncued_differential) #this is the y-axis
print(differential)## ParticipantID baseIATcued weekIATcued baseIATuncued weekIATuncued SWSxREM
## 1 ub6 0.57544182 0.20377367 0.60953653 0.68277422 276
## 2 ub7 0.09911241 0.45873715 0.64396538 -0.01070460 0
## 3 ub8 0.20577365 0.39859469 1.52435622 0.71187286 408
## 4 ub9 0.35314196 0.92341592 0.13108478 0.20212832 408
## 5 ub11 0.57200207 -0.01869151 0.04879409 0.13071184 32
## 6 ub13 0.31025514 0.56073473 0.90121486 1.11629844 648
## 7 ub14 0.23241080 -0.06857532 1.50094682 -0.27687601 333
## 8 ub15 0.67870908 0.25359928 0.61393136 0.03100248 36
## 9 ub18 1.08814254 0.77816500 0.52245709 -0.31888702 552
## 10 ub24 0.55318776 0.08084087 0.28256540 0.03038869 275
## 11 ub25 0.91751740 0.28109140 0.41293602 0.58451878 70
## 12 ub27 0.68424700 0.51216459 0.44334149 0.98690632 496
## 13 ub28 1.08844176 0.55663600 0.77617187 0.93836953 0
## 14 ub29 0.94430311 0.21879167 0.76616645 0.40828505 476
## 15 ub31 -0.15051656 0.64307684 1.20427060 0.88612653 363
## 16 ub32 -0.01583277 0.90497541 0.89984149 0.99438842 0
## 17 ub34 0.53679315 0.57458515 0.26553538 0.00799229 198
## 18 ub35 0.89884164 -0.12045279 0.94869928 1.19622739 0
## 19 ub36 0.63866504 0.64107173 0.36672662 0.62092800 216
## 20 ub38 -0.23209723 0.13055599 -0.20514602 -0.07578923 240
## 21 ub40 0.35954000 0.30356801 0.51371306 0.50089370 450
## 22 ub41 0.26726994 -0.24029660 0.35867739 0.02753136 684
## 23 ub42 0.84482587 -0.37601343 0.63582486 -0.55788997 836
## 24 ub43 0.63319883 0.99021393 0.56643958 0.38961081 506
## 25 ub44 0.43954561 0.62261116 0.93824426 0.98645892 0
## 26 ub45 0.73144877 0.16658792 1.08670619 0.86611864 418
## 27 ub46 -0.07735156 0.05022121 0.08362815 -0.10227978 480
## 28 ub47 1.08893601 1.22970000 -0.18741515 0.16271922 50
## 29 ub48 0.79863715 0.89204287 1.32229673 0.62636312 0
## 30 ub49 0.44411896 0.16209957 0.33019024 0.33564519 336
## 31 ub50 0.53631389 0.68478850 0.15458906 0.28350526 224
## cued_differential uncued_differential diff_bias_change
## 1 0.371668148 -0.07323769 0.44490584
## 2 -0.359624732 0.65466998 -1.01429471
## 3 -0.192821041 0.81248335 -1.00530440
## 4 -0.570273967 -0.07104354 -0.49923043
## 5 0.590693579 -0.08191775 0.67261133
## 6 -0.250479588 -0.21508358 -0.03539601
## 7 0.300986111 1.77782283 -1.47683672
## 8 0.425109806 0.58292888 -0.15781907
## 9 0.309977544 0.84134411 -0.53136657
## 10 0.472346888 0.25217670 0.22017019
## 11 0.636426002 -0.17158276 0.80800876
## 12 0.172082405 -0.54356483 0.71564723
## 13 0.531805761 -0.16219766 0.69400342
## 14 0.725511445 0.35788139 0.36763005
## 15 -0.793593406 0.31814407 -1.11173748
## 16 -0.920808186 -0.09454693 -0.82626125
## 17 -0.037791997 0.25754309 -0.29533509
## 18 1.019294435 -0.24752811 1.26682255
## 19 -0.002406687 -0.25420138 0.25179469
## 20 -0.362653222 -0.12935678 -0.23329644
## 21 0.055971988 0.01281936 0.04315263
## 22 0.507566544 0.33114603 0.17642051
## 23 1.220839300 1.19371483 0.02712447
## 24 -0.357015106 0.17682877 -0.53384387
## 25 -0.183065550 -0.04821467 -0.13485088
## 26 0.564860845 0.22058754 0.34427330
## 27 -0.127572774 0.18590793 -0.31348070
## 28 -0.140763994 -0.35013437 0.20937037
## 29 -0.093405722 0.69593361 -0.78933933
## 30 0.282019388 -0.00545494 0.28747433
## 31 -0.148474613 -0.12891620 -0.01955842Now that we have the values for the axes, I’m going to plot the graph.
Plot the graph
We select the data to be what we used before, then we specify the y and x axes. We then use geom_point to create a scatter plot. After that, we add geom_smooth to add a regression line. Within geom_smooth we have to add method = lm to make it a straight line, and we get rid of the confidence interval with se = F.
ggplot(data = differential, aes(
x = SWSxREM,
y = diff_bias_change
))+
geom_point()+
geom_smooth(method = lm, #lm stands for linear model, so it makes the line straight
se = F)+ #removes confidence interval shading
xlim(0,1000) #for some reason the x axis isn't starting at 0 with this## `geom_smooth()` using formula 'y ~ x'
An attempt to get the x-axis to start at 0. I found this solution on Google which adds the scale_x_continuous function to centre the graph at the origin. At the same time, the `limits = c(0,1000) allows us to expand the axis to 1000, the same length as the original graph.
Final graph:
ggplot(data = differential, aes(
x = SWSxREM,
y = diff_bias_change
))+
geom_point()+
geom_smooth(method = lm, #lm stands for linear model, so it makes the line straight
se = F)+ #removes confidence interval shading
scale_x_continuous(expand = c(0,0),limits = c(0,1000))+
scale_y_continuous(expand = c(0,0),limits = c(-2,1.5))+
labs(title = "Fig 5. No association between minutes in SWS x minutes in REM and differential bias change",
x = "SWS x REM sleep duration (min)",
y = "Differential bias change")+
theme_bw()## `geom_smooth()` using formula 'y ~ x'