Final Project_AP_V2
2022-11-21
R Markdown
This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
#Began by setting working directory, creating a chunk, and reading in data.
read.csv("Final Project Data.csv")## ID Lhippvol Sex Assocmem Fvol Mvol
## 1 BAD001 3279.872 F 0.05 3279.872 2943.488
## 2 BAD002 2975.744 F 0.50 2975.744 3613.184
## 3 BAD004 3431.936 F 0.15 3431.936 3982.336
## 4 BAD005 3565.568 F 0.45 3565.568 3777.024
## 5 BAD102 4009.984 F 0.70 4009.984 3778.560
## 6 BAD104 4381.696 F 0.50 4381.696 3542.016
## 7 BAD106 3531.264 F 0.75 3531.264 4477.952
## 8 BAD108 4470.272 F 0.10 4470.272 4609.024
## 9 BAD109 4089.856 F 0.90 4089.856 3832.320
## 10 BAD110 3814.912 F 0.85 3814.912 3964.416
## 11 BAD116 3876.864 F 0.55 3876.864 3876.864
## 12 BAD117 3832.320 M 0.70 NA NA
## 13 BAD121 3964.416 M 0.80 NA NA
## 14 BAD122 3876.864 M 0.75 NA NA
## 15 BAD003 2943.488 M 0.00 NA NA
## 16 BAD107 3613.184 M 0.65 NA NA
## 17 BAD111 3982.336 M 0.20 NA NA
## 18 BAD112 3777.024 M 0.80 NA NA
## 19 BAD115 3778.560 M 0.15 NA NA
## 20 BAD118 3542.016 M 0.20 NA NA
## 21 BAD120 4477.952 M 0.30 NA NA
## 22 BAD123 4609.024 M 0.65 NA NA#Loaded libraries
library("stats")
library("naniar")
library("dplyr") ##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary("psych")
library("ggplot2") ##
## Attaching package: 'ggplot2'## The following objects are masked from 'package:psych':
##
## %+%, alphalibrary("ggeffects")
library("tidyr")
library("Rmisc") ## Loading required package: lattice## Loading required package: plyr## ------------------------------------------------------------------------------## You have loaded plyr after dplyr - this is likely to cause problems.
## If you need functions from both plyr and dplyr, please load plyr first, then dplyr:
## library(plyr); library(dplyr)## ------------------------------------------------------------------------------##
## Attaching package: 'plyr'## The following objects are masked from 'package:dplyr':
##
## arrange, count, desc, failwith, id, mutate, rename, summarise,
## summarizelibrary("lsr")
library("easystats")## # Attaching packages: easystats 0.5.2 (red = needs update)
## ✖ insight 0.18.6 ✖ datawizard 0.6.3
## ✔ bayestestR 0.13.0 ✖ performance 0.10.0
## ✖ parameters 0.19.0 ✔ effectsize 0.8.2
## ✔ modelbased 0.8.5 ✔ correlation 0.8.3
## ✖ see 0.7.3 ✔ report 0.5.5
##
## Restart the R-Session and update packages in red with `easystats::easystats_update()`.#Viewed data to ensure it was correct and renamed it
data<- read.csv("Final Project Data.csv")
View(data) #Checking for missing data
vis_miss(data)## Warning: `gather_()` was deprecated in tidyr 1.2.0.
## Please use `gather()` instead.
#Calculating some descriptive stats just to see them
#Finding the volume mean
mean(data$Lhippvol) ## [1] 3810.234#Finding the volume median
median(data$Lhippvol) ## [1] 3823.616#Finding range
range(data$Lhippvol) ## [1] 2943.488 4609.024#Finding standard deviation
sd(data$Lhippvol) ## [1] 444.521#Running an independent t-test to assess male hippocampal volume vs female vol
sexcomparison<-t.test(data$Mvol,data$Fvol ,var.equal=T)
report(sexcomparison) ## Warning: Missing values detected. NAs dropped.## Effect sizes were labelled following Cohen's (1988) recommendations.
##
## The Two Sample t-test testing the difference between data$Mvol and data$Fvol
## (mean of x = 3854.29, mean of y = 3766.18) suggests that the effect is
## positive, statistically not significant, and very small (difference = 88.11,
## 95% CI [-314.95, 491.17], t(20) = 0.46, p = 0.653; Cohen's d = 0.19, 95% CI
## [-0.65, 1.03])#Running cohens d to check effect size
Mvol <-c(data$Mvol)
Fvol <-c(data$Fvol)
cohensD(Mvol,Fvol) ## [1] 0.1944409#Running SD
sd(data$Mvol, na.rm=T) ## [1] 445.5341sd(data$Fvol, na.rm=T)## [1] 460.6377#Graphing the t-test
read.csv("FD_Graph.csv")## Volume Sex
## 1 3279.872 F
## 2 2975.744 F
## 3 3431.936 F
## 4 3565.568 F
## 5 4009.984 F
## 6 4381.696 F
## 7 3531.264 F
## 8 4470.272 F
## 9 4089.856 F
## 10 3814.912 F
## 11 3876.864 F
## 12 2943.488 M
## 13 3613.184 M
## 14 3982.336 M
## 15 3777.024 M
## 16 3778.560 M
## 17 3542.016 M
## 18 4477.952 M
## 19 4609.024 M
## 20 3832.320 M
## 21 3964.416 Mdata2<- read.csv("FD_Graph.csv")
ggplot(data2, aes(fill=Sex, y=Volume, x=Sex)) +
geom_bar(position="dodge", stat="identity")+
xlab("Sex")+
ylab("Left Hippocampal Volume") 
#Adding in standard error
dfSumm <- data2 %>%
group_by(Sex) %>%
dplyr::summarise(
n=n(), #Tells it what n is for SE calculation later
sd = sd(Volume, na.rm=T), #Finds SD for SE calculation
Volume = mean(Volume,na.rm=T) #Mean for later
)%>%
mutate( se=sd/sqrt(n)) %>% #Calculates SE
mutate( ci=se) #Calculates confidence interval.
ggplot(dfSumm, aes(Sex, Volume)) +
geom_col(fill=c("pink", "blue")) +
geom_errorbar(aes(ymin = Volume-ci, ymax = Volume+ci),width=0.3)+
xlab("Sex")+
ylab("Left Hippocampal Volume")
#Running a correlation between Volume and Associative Memory Scores
r <- corr.test(data$Lhippvol,data$Assocmem)
print(r,short=F) ## Call:corr.test(x = data$Lhippvol, y = data$Assocmem)
## Correlation matrix
## [1] 0.25
## Sample Size
## [1] 22
## These are the unadjusted probability values.
## The probability values adjusted for multiple tests are in the p.adj object.
## [1] 0.25
##
## Confidence intervals based upon normal theory. To get bootstrapped values, try cor.ci
## raw.lower raw.r raw.upper raw.p lower.adj upper.adj
## NA-NA -0.19 0.25 0.61 0.25 -0.19 0.61#Saving function as an object and running a regression
reg <- lm(Assocmem~Lhippvol, data=data)
summary(reg) ##
## Call:
## lm(formula = Assocmem ~ Lhippvol, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.4967 -0.2918 0.0413 0.2419 0.3669
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.1505959 0.5448012 -0.276 0.785
## Lhippvol 0.0001672 0.0001421 1.177 0.253
##
## Residual standard error: 0.2894 on 20 degrees of freedom
## Multiple R-squared: 0.06475, Adjusted R-squared: 0.01799
## F-statistic: 1.385 on 1 and 20 DF, p-value: 0.2531report(reg)## We fitted a linear model (estimated using OLS) to predict Assocmem with
## Lhippvol (formula: Assocmem ~ Lhippvol). The model explains a statistically not
## significant and weak proportion of variance (R2 = 0.06, F(1, 20) = 1.38, p =
## 0.253, adj. R2 = 0.02). The model's intercept, corresponding to Lhippvol = 0,
## is at -0.15 (95% CI [-1.29, 0.99], t(20) = -0.28, p = 0.785). Within this
## model:
##
## - The effect of Lhippvol is statistically non-significant and positive (beta =
## 1.67e-04, 95% CI [-1.29e-04, 4.64e-04], t(20) = 1.18, p = 0.253; Std. beta =
## 0.25, 95% CI [-0.20, 0.71])
##
## Standardized parameters were obtained by fitting the model on a standardized
## version of the dataset. 95% Confidence Intervals (CIs) and p-values were
## computed using a Wald t-distribution approximation.#Mean centering data because this data doesn't have a meaningful zero
data$Lhippvol <- scale(data$Lhippvol,center=T,scale=F)#Running the updated regression
reg2 <- lm(Assocmem~Lhippvol,data=data)
summary(reg2) ##
## Call:
## lm(formula = Assocmem ~ Lhippvol, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.4967 -0.2918 0.0413 0.2419 0.3669
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.4863636 0.0616984 7.883 1.46e-07 ***
## Lhippvol 0.0001672 0.0001421 1.177 0.253
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.2894 on 20 degrees of freedom
## Multiple R-squared: 0.06475, Adjusted R-squared: 0.01799
## F-statistic: 1.385 on 1 and 20 DF, p-value: 0.2531report(reg2)## We fitted a linear model (estimated using OLS) to predict Assocmem with
## Lhippvol (formula: Assocmem ~ Lhippvol). The model explains a statistically not
## significant and weak proportion of variance (R2 = 0.06, F(1, 20) = 1.38, p =
## 0.253, adj. R2 = 0.02). The model's intercept, corresponding to Lhippvol = 0,
## is at 0.49 (95% CI [0.36, 0.62], t(20) = 7.88, p < .001). Within this model:
##
## - The effect of Lhippvol is statistically non-significant and positive (beta =
## 1.67e-04, 95% CI [-1.29e-04, 4.64e-04], t(20) = 1.18, p = 0.253; Std. beta =
## 0.25, 95% CI [-0.20, 0.71])
##
## Standardized parameters were obtained by fitting the model on a standardized
## version of the dataset. 95% Confidence Intervals (CIs) and p-values were
## computed using a Wald t-distribution approximation.#Plotting the regression
g <- ggpredict(reg,terms=c("Lhippvol"))
plot(g)+labs(x="Left Hippocampal Volume", y="Associative Memory",title="Associative Memory Scores and Left Hippocampal Volume")
#Getting package citations
citation("stats") ##
## The 'stats' package is part of R. To cite R in publications use:
##
## R Core Team (2022). R: A language and environment for statistical
## computing. R Foundation for Statistical Computing, Vienna, Austria.
## URL https://www.R-project.org/.
##
## A BibTeX entry for LaTeX users is
##
## @Manual{,
## title = {R: A Language and Environment for Statistical Computing},
## author = {{R Core Team}},
## organization = {R Foundation for Statistical Computing},
## address = {Vienna, Austria},
## year = {2022},
## url = {https://www.R-project.org/},
## }
##
## We have invested a lot of time and effort in creating R, please cite it
## when using it for data analysis. See also 'citation("pkgname")' for
## citing R packages.citation("naniar") ##
## To cite package 'naniar' in publications use:
##
## Tierney N, Cook D, McBain M, Fay C (2021). _naniar: Data Structures,
## Summaries, and Visualisations for Missing Data_. R package version
## 0.6.1, <https://CRAN.R-project.org/package=naniar>.
##
## A BibTeX entry for LaTeX users is
##
## @Manual{,
## title = {naniar: Data Structures, Summaries, and Visualisations for Missing Data},
## author = {Nicholas Tierney and Di Cook and Miles McBain and Colin Fay},
## year = {2021},
## note = {R package version 0.6.1},
## url = {https://CRAN.R-project.org/package=naniar},
## }citation("dplyr") ##
## To cite package 'dplyr' in publications use:
##
## Wickham H, François R, Henry L, Müller K (2022). _dplyr: A Grammar of
## Data Manipulation_. R package version 1.0.10,
## <https://CRAN.R-project.org/package=dplyr>.
##
## A BibTeX entry for LaTeX users is
##
## @Manual{,
## title = {dplyr: A Grammar of Data Manipulation},
## author = {Hadley Wickham and Romain François and Lionel Henry and Kirill Müller},
## year = {2022},
## note = {R package version 1.0.10},
## url = {https://CRAN.R-project.org/package=dplyr},
## }citation("psych") ##
## To cite the psych package in publications use:
##
## Revelle, W. (2022) psych: Procedures for Personality and
## Psychological Research, Northwestern University, Evanston, Illinois,
## USA, https://CRAN.R-project.org/package=psych Version = 2.2.9.
##
## A BibTeX entry for LaTeX users is
##
## @Manual{,
## title = {psych: Procedures for Psychological, Psychometric, and Personality Research},
## author = {William Revelle},
## organization = { Northwestern University},
## address = { Evanston, Illinois},
## year = {2022},
## note = {R package version 2.2.9},
## url = {https://CRAN.R-project.org/package=psych},
## }citation("ggplot2") ##
## To cite ggplot2 in publications, please use:
##
## H. Wickham. ggplot2: Elegant Graphics for Data Analysis.
## Springer-Verlag New York, 2016.
##
## A BibTeX entry for LaTeX users is
##
## @Book{,
## author = {Hadley Wickham},
## title = {ggplot2: Elegant Graphics for Data Analysis},
## publisher = {Springer-Verlag New York},
## year = {2016},
## isbn = {978-3-319-24277-4},
## url = {https://ggplot2.tidyverse.org},
## }citation("ggeffects") ##
## To cite package 'ggeffects' in publications use:
##
## Lüdecke D (2018). "ggeffects: Tidy Data Frames of Marginal Effects
## from Regression Models." _Journal of Open Source Software_, *3*(26),
## 772. doi:10.21105/joss.00772 <https://doi.org/10.21105/joss.00772>.
##
## A BibTeX entry for LaTeX users is
##
## @Article{,
## title = {ggeffects: Tidy Data Frames of Marginal Effects from Regression Models.},
## volume = {3},
## doi = {10.21105/joss.00772},
## number = {26},
## journal = {Journal of Open Source Software},
## author = {Daniel Lüdecke},
## year = {2018},
## pages = {772},
## }citation("tidyr") ##
## To cite package 'tidyr' in publications use:
##
## Wickham H, Girlich M (2022). _tidyr: Tidy Messy Data_. R package
## version 1.2.1, <https://CRAN.R-project.org/package=tidyr>.
##
## A BibTeX entry for LaTeX users is
##
## @Manual{,
## title = {tidyr: Tidy Messy Data},
## author = {Hadley Wickham and Maximilian Girlich},
## year = {2022},
## note = {R package version 1.2.1},
## url = {https://CRAN.R-project.org/package=tidyr},
## }citation("Rmisc") ##
## To cite package 'Rmisc' in publications use:
##
## Hope RM (2022). _Rmisc: Ryan Miscellaneous_. R package version 1.5.1,
## <https://CRAN.R-project.org/package=Rmisc>.
##
## A BibTeX entry for LaTeX users is
##
## @Manual{,
## title = {Rmisc: Ryan Miscellaneous},
## author = {Ryan M. Hope},
## year = {2022},
## note = {R package version 1.5.1},
## url = {https://CRAN.R-project.org/package=Rmisc},
## }
##
## ATTENTION: This citation information has been auto-generated from the
## package DESCRIPTION file and may need manual editing, see
## 'help("citation")'.citation("lsr") ##
## To cite the lsr package in publications use:
##
## Navarro, D. J. (2015) Learning statistics with R: A tutorial for
## psychology students and other beginners. (Version 0.6) University of
## New South Wales. Sydney, Australia
##
## A BibTeX entry for LaTeX users is
##
## @Manual{,
## title = {Learning statistics with R: A tutorial for psychology students and other beginners. (Version 0.6)},
## author = {Danielle Navarro},
## organization = {University of New South Wales},
## address = {Sydney, Australia},
## year = {2015},
## note = {R package version 0.5.1},
## url = {https://learningstatisticswithr.com},
## }citation("easystats")##
## To cite datawizard in publications use:
##
## Lüdecke, Patil, Ben-Shachar, Wiernik, & Makowski (2022). easystats:
## Framework for Easy Statistical Modeling, Visualization, and
## Reporting. CRAN. Available from
## https://easystats.github.io/easystats/
##
## A BibTeX entry for LaTeX users is
##
## @Article{,
## title = {easystats: Framework for Easy Statistical Modeling, Visualization, and Reporting},
## author = {Daniel Lüdecke and Mattan S. Ben-Shachar and Indrajeet Patil and Brenton M. Wiernik and Dominique Makowski},
## journal = {CRAN},
## year = {2022},
## note = {R package},
## url = {https://easystats.github.io/easystats/},
## }