Skip to main content

Hofstede's Long-term Orientation and Individuality: Obesity Relationships (using R)

Hofstede extended his original four dimensions, adding measures Long-Term Orientation (LTO) and Indulgence (Ind) in response to other researchers studies. While reading Hofstede's Cultures and Organizations: Software of the Mind, Third Edition I was struck by the lackluster reporting of the correlation between obesity and indulgence. It seemed obvious one would delve a bit further, maybe looking at a compound relationship between both indulgence and LTO, e.g., does short-sightedness and indulgence lead to obesity. Although I limit my analysis to OECD countries, that is what I present here.

An explanation of dimensions can be found on Hofstede's site.

Hofstede's Dimensions and Obesity

A first step would be to see what relationships exist between obesity and the dimensions:


1:  # LM - Multiple Regression - New Hofstede, LTO and Ind  
2:  # Load the data into a matrix  
3:  rm(list = ls())  
4:  setwd("../Data")  
5:  oecdData <- read.table("OECD - Quality of Life.csv", header = TRUE, sep = ",")  
6:  print(names(oecdData))  
7:    
8:  # Access the vectors  
9:  v1 <- oecdData$IQ  
10:  v2 <- oecdData$HofstederPowerDx  
11:  v3 <- oecdData$HofstederMasculinity  
12:  v4 <- oecdData$HofstederIndividuality  
13:  v5 <- oecdData$HofstederUncertaintyAvoidance  
14:  v6 <- oecdData$HofstederLongtermOrientation  
15:  v7 <- oecdData$HofstederIndulgence  
16:    
17:  v9 <- oecdData$Gini  
18:  v10 <- oecdData$Obesity  
19:  v26 <- oecdData$Assaultsandthreats  
20:    
21:  # Conclusion, both high individuality and low LTO contribute to obesity  
22:  #  but inversely correlated with each other  
23:  # Obesity ~ Hofstede  
24:  relation1 <- lm(v10 ~ v2 + v3 + v4 + v5 + v6 + v7)  
25:  print(relation1)  
26:  print(summary(relation1))  
27:  print(anova(relation1))  


Results - Regression and ANOVA

Both linear multiple regression and ANOVA would indicate that both individuality and LTO have, or at least one has, a relationship to obesity.

1:  Call:  
2:  lm(formula = v10 ~ v2 + v3 + v4 + v5 + v6 + v7)  
3:    
4:  Coefficients:  
5:  (Intercept)      v2      v3      v4      v5      v6      v7   
6:    1.09265   0.12813   0.07237   0.10560   -0.01969   -0.14108   0.08111   
7:    
8:  Call:  
9:  lm(formula = v10 ~ v2 + v3 + v4 + v5 + v6 + v7)  
10:    
11:  Residuals:  
12:    Min   1Q Median   3Q   Max   
13:  -5.3248 -3.1639 -0.1943 1.3526 9.3436   
14:    
15:  Coefficients:  
16:        Estimate Std. Error t value Pr(>|t|)   
17:  (Intercept) 1.09265  11.38472  0.096  0.9247   
18:  v2      0.12813  0.12105  1.059  0.3055   
19:  v3      0.07237  0.04969  1.456  0.1646   
20:  v4      0.10560  0.09187  1.150  0.2672   
21:  v5     -0.01969  0.10441 -0.189  0.8528   
22:  v6     -0.14108  0.05303 -2.660  0.0171 *  
23:  v7      0.08111  0.12755  0.636  0.5338   
24:    
25:  Signif. codes: 0 `***' 0.001 `**' 0.01 `*' 0.05 `.' 0.1 ` ' 1  
26:    
27:  Residual standard error: 4.715 on 16 degrees of freedom  
28:   (1 observation deleted due to missingness)  
29:  Multiple R-squared: 0.5731,     Adjusted R-squared: 0.4131   
30:  F-statistic: 3.581 on 6 and 16 DF, p-value: 0.01919  
31:    
32:  Analysis of Variance Table  
33:    
34:  Response: v10  
35:       Df Sum Sq Mean Sq F value  Pr(>F)    
36:  v2     1 26.81 26.814 1.2059 0.288389    
37:  v3     1 17.73 17.731 0.7974 0.385093    
38:  v4     1 253.50 253.495 11.4008 0.003846 **  
39:  v5     1  5.22  5.217 0.2346 0.634672    
40:  v6     1 165.43 165.431 7.4402 0.014902 *   
41:  v7     1  8.99  8.990 0.4043 0.533847    
42:  Residuals 16 355.76 22.235            
43:    
44:  Signif. codes: 0 `***' 0.001 `**' 0.01 `*' 0.05 `.' 0.1 ` ' 1  


Correlations and Graphs - LTO and Obesity


1:  # Corr - Obesity ~ LTO  
2:  cor.test(v6, v10)  
3:  plot(v10, v6, col = "blue", main = "Obesity ~ LTO", abline(lm(v6 ~ v10)), cex = 1.3, pch = 16, xlab = "Obesity", ylab = "LTO")  
    

The results seem significant, with a correlation of -.56.


1:  Pearson's product-moment correlation  
2:    
3:  data: v6 and v10  
4:  t = -3.1025, df = 21, p-value = 0.005392  
5:  alternative hypothesis: true correlation is not equal to 0  
6:  95 percent confidence interval:  
7:   -0.7902136 -0.1930253  
8:  sample estimates:  
9:      cor   
10:  -0.5606214   
    

Correlations and Graphs - Individuality and Obesity


1:  # Corr - Obesity ~ Idv  
2:  cor.test(v4, v10)  
3:  plot(v10, v4, col = "blue", main = "Obesity ~ Idv", abline(lm(v4 ~ v10)), cex = 1.3, pch = 16, xlab = "Obesity", ylab = "Idv")  

These results seem equally significant, with a correlation of .59.


1: Pearson's product-moment correlation  
2:    
3:  data: v4 and v10  
4:  t = 3.351, df = 21, p-value = 0.003027  
5:  alternative hypothesis: true correlation is not equal to 0  
6:  95 percent confidence interval:  
7:   0.2353225 0.8062918  
8:  sample estimates:  
9:     cor   
10:  0.5902683   



Concern - Correlation between Individuality and LTO

Although the two qualities are not linearly related, they have a significant degree of correlation, -.33.


Sample Data

Popular posts from this blog

Decision Tree in R, with Graphs: Predicting State Politics from Big Five Traits

This was a continuation of prior explorations, logistic regression predicting Red/Blue state dichotomy by income or by personality. This uses the same five personality dimensions, but instead builds a decision tree. Of the Big Five traits, only two were found to useful in the decision tree, conscientiousness and openness.

Links to sample data, as well as to source references, are at the end of this entry.

Example Code

# Decision Tree - Big Five and Politics library("rpart") # grow tree input.dat <- read.table("BigFiveScoresByState.csv", header = TRUE, sep = ",") fit <- rpart(Liberal ~ Openness + Conscientiousness + Neuroticism + Extraversion + Agreeableness, data = input.dat, method="poisson") # display the results printcp(fit) # visualize cross-validation results plotcp(fit) # detailed summary of splits summary(fit) # plot tree plot(fit, uniform = TRUE, main = "Classific…

Chi-Square in R on by State Politics (Red/Blue) and Income (Higher/Lower)

This is a significant result, but instead of a logistic regression looking at the income average per state and the likelihood of being a Democratic state, it uses Chi-Square. Interpreting this is pretty straightforward, in that liberal states typically have cities and people that earn more money. When using adjusted incomes, by cost of living, this difference disappears.

Example Code
# R - Chi Square rm(list = ls()) stateData <- read.table("CostByStateAndSalary.csv", header = TRUE, sep = ",") # Create vectors affluence.median <- median(stateData$Y2014, na.rm = TRUE) affluence.v <- ifelse(stateData$Y2014 > affluence.median, 1, 0) liberal.v <- stateData$Liberal # Solve pol.Data = table(liberal.v, affluence.v) result <- chisq.test(pol.Data) print(result) print(pol.Data)
Example Results
Pearson's Chi-squared test with Yates' continuity correction data: pol.Data X-squared = 12.672, df …

Logistic Regression in R on State Voting in National Elections and Income

This data set - a link is at the bottom - is slightly different, income by state and political group, red or blue. Generally, residents of blue states have higher incomes, although not when adjusted for cost of living:

Example Code
# R - Logistic Regression stateData <- read.table("CostByStateAndSalary.csv", header = TRUE, sep = ",") am.data = glm(formula = Liberal ~ Y2014, data = stateData, family = binomial) print(summary(am.data))
Example Results
Call: glm(formula = Liberal ~ Y2014, family = binomial, data = stateData) Deviance Residuals: Min 1Q Median 3Q Max -2.4347 -0.7297 -0.4880 0.6327 1.8722 Coefficients: Estimate Std. Error z value Pr(>|z|) (Intercept) -9.325e+00 2.671e+00 -3.491 0.000481 *** Y2014 1.752e-04 5.208e-05 3.365 0.000765 *** --- Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1 (Dispersion parameter for bi…