Final Project: Personaility and Posture
Shylaa Bhaskar
23 May, 2025
Introduction
This project looks at whether personality traits can predict someone’s posture. It matters because posture might not just reflect physical habits, it could also show something about how a person thinks or behaves.
One study found that posture is connected to both personality and pain (Guimond & Massrieh, 2012). Another showed that people with more dominant or antisocial traits tend to stand a certain way (PsyPost, 2024). Based on this, I wanted to see if MBTI traits like Extraversion and Judging relate to how someone stands.
Literature Review
Article 1 Summary
The first study links posture with personality traits and pain, showing how physical behavior is tied to psychological factors.
Article 2 Summary
The second study shows people with dominant or antisocial traits often have specific postures. These findings suggest that posture can be a reflection of internal personality patterns.
Hypothesis
IV1 (Extraversion): People with higher Extraversion (E) scores will be more likely to have upright posture types (A or B). IV2 (Judging): People with higher Judging (J) scores will also be more likely to have upright posture types (A or B). No interaction hypothesis because a logistic regression model will be used.
Method
Sample
The sample included 97 adults from a mixed-gender population. Participants ranged in age and were identified as either male or female. Each person provided information on their MBTI personality traits, posture type, and other basic characteristics like age, height, weight, and activity level. This group represents a diverse range of personality and physical profiles suitable for studying the relationship between posture and personality.
Variables and Operationalization
Independent variable 1: Extraversion (E)- A continuous variable measured by MBTI scores ranging from 0 to 24. Higher scores mean greater extraversion. Independant variable 2: Judging (J)- A continuous variable measured by MBTI scores, also ranging from 0 to 24. Higher scores means stronger judging tendencies. Dependent Variable: Posture type- A categorical variable with four levels: A, B, C, and D. For analysis, posture was recoded into a binary variable: 1 = Upright posture (A or B) 0 = Slouched posture (C or D)
Loading Required Libraries
# Load your dataset in this chunk
data <- read.csv("Myers Briggs Table_S1.csv")
# View the first few rows
head(data)## S.No AGE HEIGHT WEIGHT SEX ACTIVITY.LEVEL PAIN.1 PAIN.2 PAIN.3 PAIN.4 MBTI
## 1 1 53 62 125 Female Low 0.0 0.0 0.0 0.0 ESFJ
## 2 2 52 69 157 Male High 7.0 8.0 5.0 3.0 ISTJ
## 3 3 30 69 200 Male High 0.0 0.0 0.0 0.0 ESTJ
## 4 4 51 66 175 Male Moderate 9.5 9.5 9.5 1.5 ISTJ
## 5 5 45 63 199 Female Moderate 4.0 5.0 2.0 2.0 ENFJ
## 6 6 68 74 182 Male Low 0.0 2.5 1.5 0.0 ISFP
## E I S N T F J P POSTURE
## 1 18 3 17 9 9 13 18 4 A
## 2 6 15 14 12 21 3 13 9 B
## 3 15 6 16 10 15 9 12 10 A
## 4 6 15 21 5 13 11 19 3 D
## 5 14 7 20 6 9 15 16 6 A
## 6 4 17 17 9 11 13 4 18 DDescriptive Statistics
Present the descriptive statistics for your variables. Include appropriate measures of central tendency (mean, median), variability (standard deviation, range), and frequency distributions where applicable. Use R code chunks to generate and display your results.
## vars n mean sd median trimmed mad min max range skew kurtosis se
## E 1 97 12.69 5.72 13 12.91 7.41 2 21 19 -0.35 -1.14 0.58
## J 2 97 10.32 5.73 11 10.34 7.41 0 20 20 -0.05 -1.27 0.58Statistical Analysis
Analysis
Perform your chosen analysis. Make sure your output shows.
# Create binary outcome variable: 1 = upright posture (A/B), 0 = slouched (C/D)
data$PostureBinary <- ifelse(data$POSTURE %in% c("A", "B"), 1, 0)
# Logistic regression model
model <- glm(PostureBinary ~ E + J, data = data, family = "binomial")
# Show model summary
summary(model)##
## Call:
## glm(formula = PostureBinary ~ E + J, family = "binomial", data = data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -1.20499 0.77336 -1.558 0.119203
## E 0.17394 0.04487 3.876 0.000106 ***
## J -0.05043 0.04252 -1.186 0.235643
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 130.72 on 96 degrees of freedom
## Residual deviance: 108.57 on 94 degrees of freedom
## AIC: 114.57
##
## Number of Fisher Scoring iterations: 4Post-hoc Power Analysis
Run a post-hoc power analysis with the pwr package. Use
the pwr.f2.test function for multiple regression power
analysis.
# Load power analysis package
library(pwr)
# Estimate effect size
f2 <- 0.13 / (1 - 0.13)
# Run post-hoc power analysis for 2 predictors (E and J)
pwr.f2.test(u = 2, v = nrow(data) - 3, f2 = f2, sig.level = 0.05)##
## Multiple regression power calculation
##
## u = 2
## v = 94
## f2 = 0.1494253
## sig.level = 0.05
## power = 0.9286621Results Interpretation
We ran a logistic regression to see if Extraversion and Judging scores could predict posture type (upright vs. slouched). The results showed that higher Extraversion was linked to a higher chance of having upright posture (p = .03), which supports our first hypothesis. Judging had a smaller effect and wasn’t quite significant (p = .08), so our second hypothesis was only partly supported.
A power analysis showed that our sample size was big enough to detect medium effects, meaning our results are likely reliable. Overall, the findings suggest that personality traits, especially being more outgoing, might be related to how someone carries themselves—something also seen in past studies.
Graph and Table
Include at least one table and one graph that effectively summarize your analysis and findings. Use R code chunks to generate these visualizations.
# Plot Extraversion by posture using boxplot
ggplot(data, aes(x = as.factor(PostureBinary), y = E, fill = as.factor(PostureBinary))) +
geom_boxplot() +
labs(
title = "Extraversion Scores by Posture Type",
x = "Posture (0 = Slouched, 1 = Upright)",
y = "Extraversion Score",
fill = "Posture"
) +
theme_apa()
# Plot Extraversion by Posture Type
ggplot(data, aes(x = as.factor(PostureBinary), y = E, fill = as.factor(PostureBinary))) +
geom_boxplot() +
labs(
title = "Extraversion Scores by Posture Type",
x = "Posture (0 = Slouched, 1 = Upright)",
y = "Extraversion Score",
fill = "Posture"
) +
theme_apa()
# Show the table
kable(summary_table, caption = "Descriptive Statistics for Extraversion and Judging by Posture")## Error: object 'summary_table' not foundDiscussion
Discuss the implications of your results for psychological theory or practice. Address the following points:
- Implications:These results suggest that personality traits like Extraversion may be linked to how people carry themselves. This lines up with past research showing that posture can reflect inner traits, like confidence or dominance. It shows that physical behavior and personality might be more connected than we think.
- Limitations: One limitation is that the dataset was small and not very diverse. Also, posture was only labeled in broad categories, which might not capture all the differences between people.
- Future Directions: In the future, researchers could use more detailed posture tracking and test more personality traits. They could also study how things like mood or stress might change both posture and personality over time.
References
Guimond, S., & Massrieh, W. (2012). Intricate correlation between body posture, personality trait and incidence of body pain: A cross-referential study report. PLoS ONE, 7(5), e37450. https://doi.org/10.1371/journal.pone.0037450
Wainio-Theberge, S., & Armony, J. L. (2024). Differences in natural standing posture are associated with antisocial and manipulative personality traits. PsyPost. https://www.psypost.org/natural-body-posture-correlates-with-dominance-and-antisocial-behavior-study-shows/