Exploring Dietary Habits and Demographic Factors

Reliability Statistics

Fats

The fats subscale consisted of 8 items (α = 0.769), showing that it is highly reliable. Further, the inter-item correlation matrix shows that there is no high correlation between any of the items, meaning that the data is free from multicollinearity. Moreover, item-total statistics show that even if any of the items are deleted, the dataset will remain highly reliable, making it ideal for data analysis dissertation help.

Carbs

The carbs subscale consisted of 8 items (α = 0.768), showing that it is highly reliable. Further, the inter-item correlation matrix shows that there is no high correlation between any of the items, meaning that the data is free from multicollinearity. Moreover, item-total statistics show that even if any of the items are deleted, the dataset will remain highly reliable.

Sweets

The sweets subscale consisted of 8 items (α = 0.798), showing that it is highly reliable. Further, the inter-item correlation matrix shows that there is no high correlation between any of the items, meaning that the data is free from multicollinearity. Moreover, item-total statistics show that even if any of the items are deleted, the dataset will remain highly reliable.

Fast Foods

The fast foods subscale consisted of 4 items (α = 0.685), showing that it is not reliable as the alpha value is less than 0.70. Further, the inter-item correlation matrix shows that there is no high correlation between any of the items, meaning that the data is free from multicollinearity. Moreover, item-total statistics show that even if any of the items are deleted, the dataset will remain non-reliable.

FCI

The FCI subscale consisted of 37 items (α = 0.905), showing that it is reliable. Further, the inter-item correlation matrix shows that there is no high correlation between any of the items, meaning that the data is free from multicollinearity. Moreover, item-total statistics show that even if any of the items are deleted, the dataset will remain highly reliable.

Descriptive Statistics

As per the descriptive statistics; the average income the respondent is between $60000 and $70000. Further, the mean for fats was 14.38, carbs was 17.46, sweets was 20.32, fast food was 10.24, total carving was 80.61 and BMI was 32.24.

Frequency Analysis

As per the frequency analysis, 19.3% (n = 58) respondents were unemployed, 7.7% (n = 23) respondents were students, and 73.0% (n = 219) respondents were employed.

Further, 10.1% (n = 30) of respondents are divorced, 12.2% (n = 36) of respondents are in relationship, 52.4% (n = 155) of respondents are married, 3.4% (n = 10) of respondents are separated, 21.3% (n = 63) of respondents are single, and 0.7% (n = 2) of respondents are widowed.

Further, 18.1% (n = 53) of the respondents had attended high school, 24.9% (n = 73) of the respondents had attended technical college, 41.6% (n = 122) of the respondents were undergraduate, and 15.4% (n = 45) of the respondents were post graduate.

As per the frequency analysis of income, 24.6% (n = 72) were belonging to low-income group, 29.4% (n = 86) were belonging to middle-income group, and 46.1% (n = 135) were belonging to high-income group.

Finally, the frequency analysis of BMI shows that 10.4% (n = 31) of the respondents had healthy weight, 24.5% (n = 73) of the respondents were overweight, 27.5% (n = 82) of the respondents were in class 1 category, 16.1% (n = 48) of the respondents were in class 2 category, and 21.5% (n = 64) of the respondents were in class 3 category.

Correlation Analysis

As per the correlation analysis of demographic variables with food categories it was found that age was significantly negatively correlated with sweets (r = -0.123; p = 0.046) and fast food (r = -0.172; p = 0.005), whereas significantly positively correlated with BMI (r = 0.230; p = 0.000). Further, there was no statistically significant correlation between Income and any of the food categories.

One-way ANOVA by Education Categories

Income

As per One-way ANOVA, F(3, 282) = 1.633; p = 0.182. Since the p-value is greater than the critical alpha value of 0.05, it can be said that there is no statistically significant difference in Income of the respondents between different education categories.

Fats

As per One-way ANOVA, F(3, 271) = 0.990; p = 0.398. Since the p-value is greater than the critical alpha value of 0.05, it can be said that there is no statistically significant difference in fats between different education categories.

Carbs

As per One-way ANOVA, F(3, 271) = 1.643; p = 0.180. Since the p-value is greater than the critical alpha value of 0.05, it can be said that there is no statistically significant difference in Carbs between different education categories.

Sweets

As per One-way ANOVA, F(3, 271) = 0.200; p = 0.896. Since the p-value is greater than the critical alpha value of 0.05, it can be said that there is no statistically significant difference in sweets between different education categories.

Fast Foods

As per One-way ANOVA, F(3, 271) = 0.443; p = 0.723. Since the p-value is greater than the critical alpha value of 0.05, it can be said that there is no statistically significant difference in fast food between different education categories.

Total Craving

As per One-way ANOVA, F(3, 271) = 1.392; p = 0.245. Since the p-value is greater than the critical alpha value of 0.05, it can be said that there is no statistically significant difference in total craving of the respondents between different education categories.

BMI

As per One-way ANOVA, F(3, 282) = 1.301; p = 0.274. Since the p-value is greater than the critical alpha value of 0.05, it can be said that there is no statistically significant difference in BMI of the respondents between different education categories.

Further, the post-hoc test for all the dependent variables shows that the p-value is coming out to be more than the critical alpha value of 0.05 for all the pairs; thus, it shows that there is no statistically significant difference in the independent variables between the individual pairs of dependent variable, that is, education categories.

One-way ANOVA by Marital Categories

Income

As per One-way ANOVA, F(5, 283) = 11.072; p = 0.000. Since the p-value is smaller than the critical alpha value of 0.05, it can be said that there is a statistically significant difference in Income of the respondents between different marital categories. Married respondents have the highest income, and separated individuals have the lowest Income.

Fats

As per One-way ANOVA, F(5, 271) = 1.522; p = 0.183. Since the p-value is greater than the critical alpha value of 0.05, it can be said that there is no statistically significant difference in fats between different marital categories.

Carbs

As per One-way ANOVA, F(5, 271) = 0.913; p = 0.473. Since the p-value is greater than the critical alpha value of 0.05, it can be said that there is no statistically significant difference in carbs between different marital categories.

Sweets

As per One-way ANOVA, F(5, 271) = 0.476; p = 0.794. Since the p-value is greater than the critical alpha value of 0.05, it can be said that there is no statistically significant difference in sweets between different marital categories.

Fast Foods

As per One-way ANOVA, F(5, 271) = 1.275; p = 0.275. Since the p-value is greater than the critical alpha value of 0.05, it can be said that there is no statistically significant difference in fast foods between different marital categories.

Total Craving

As per One-way ANOVA, F(5, 271) = 1.296; p = 0.266. Since the p-value is greater than the critical alpha value of 0.05, it can be said that there is no statistically significant difference in total cravings between different marital categories.

BMI

As per One-way ANOVA, F(5, 288) = 3.020; p = 0.011. Since the p-value is smaller than the critical alpha value of 0.05, it can be said that there is a statistically significant difference in BMI of the respondents between different marital categories. Separated respondents have the highest BMI, and single individuals have the lowest BMI.

As per One-way ANOVA, F(5, 288) = 3.020; p = 0.011. Since the p-value is smaller than the critical alpha value of 0.05, it can be said that there is a statistically significant difference in BMI of the respondents between different marital categories. Separated respondents have the highest BMI, and single individuals have the lowest BMI. Further, the post-hoc test also reveals the same thing that married respondents have the highest income, and separated individuals have the lowest income; and separated respondents have the highest BMI, and single individuals have the lowest BMI. Apart from that, there is no statistically significant difference in the independent variables between the individual pairs of the dependent variable, that is, marital categories.

One-way ANOVA by Employment Categories

Income

As per One-way ANOVA, F(2, 290) = 10.214; p = 0.000. Since the p-value is smaller than the critical alpha value of 0.05, it can be said that there is a statistically significant difference in Income of the respondents between different employment categories. Employed respondents have the highest income and students have the lowest Income.

Fats

As per One-way ANOVA, F(2, 277) = 0.947; p = 0.389. Since the p-value is greater than the critical alpha value of 0.05, it can be said that there is no statistically significant difference in fats between different employment categories.

Carbs

As per One-way ANOVA, F(5, 277) = 0.947; p = 0.389. Since the p-value is greater than the critical alpha value of 0.05, it can be said that there is no statistically significant difference in carbs between different employment categories.

Sweets

As per One-way ANOVA, F(2, 277) = 0.273; p = 0.762. Since the p-value is greater than the critical alpha value of 0.05, it can be said that there is no statistically significant difference in sweets between different employment categories.

Fast Foods

As per One-way ANOVA, F(2, 277) = 0.606; p = 0.546. Since the p-value is greater than the critical alpha value of 0.05, it can be said that there is no statistically significant difference in fast foods between different employment categories.

Total Craving

As per One-way ANOVA, F(2, 277) = 0.639; p = 0.529. Since the p-value is greater than the critical alpha value of 0.05, it can be said that there is no statistically significant difference in total cravings between different employment categories.

BMI

As per One-way ANOVA, F(2, 294) = 8.453; p = 0.000. Since the p-value is smaller than the critical alpha value of 0.05, it can be said that there is a statistically significant difference in BMI of the respondents between different employment categories. Unemployed respondents have the highest BMI and students have the lowest BMI.

Further, the post-hoc test also reveals the same thing that employed respondents have the highest income and students have the lowest income; and unemployed respondents have the highest BMI and students have the lowest BMI. Apart from that, there is no statistically significant difference in the independent variables between the individual pairs of the dependent variable, that is, employment categories.

One-way ANOVA by Income Categories

Fats

As per One-way ANOVA, F(2, 270) = 0.254; p = 0.776. Since the p-value is greater than the critical alpha value of 0.05, it can be said that there is no statistically significant difference in fats between different income categories.

Carbs

As per One-way ANOVA, F(2, 270) = 0.435; p = 0.648. Since the p-value is greater than the critical alpha value of 0.05, it can be said that there is no statistically significant difference in carbs between different income categories.

Sweets

As per One-way ANOVA, F(2, 270) = 0.273; p = 0.135. Since the p-value is greater than the critical alpha value of 0.05, it can be said that there is no statistically significant difference in sweets between different income categories.

Fast Foods

As per One-way ANOVA, F(2, 270) = 1.254; p = 0.287. Since the p-value is greater than the critical alpha value of 0.05, it can be said that there is no statistically significant difference in fast foods between different income categories.

Total Craving

As per One-way ANOVA, F(2, 270) = 0.493; p = 0.611. Since the p-value is greater than the critical alpha value of 0.05, it can be said that there is no statistically significant difference in total cravings between different income categories.

Further, the post-hoc test for all the dependent variables shows that the p-value is coming out to be more than the critical alpha value of 0.05 for all the pairs; thus, it shows that there is no statistically significant difference in the independent variables between the individual pairs of dependent variable, that is, income categories.

Assumptions for Hierarchical Multiple Regression Analyses (HMR).

G*Power analysis indicated that to detect a medium effect size, the minimum sample size necessary for a regression model with 2 predictors was 107. As the present study had a sample size of 301, the assumption of sample size was met. Further, dependent and independent variables are either continuous or categorical. This fulfils another assumption of HRM. Further, the scatter plot between BMI and income and BMI and Total craving are coming out to be linear as shown below. This confirms the assumption of linearity.

The above scatter plot also shows that there are not much outliers in the dataset. Now, in order to check the assumption of independence of observation or independence of residual, Durbin-Watson test was performed which shows Durbin-Watson statistic comes out to be 1.769, which is between 1.5 and 2.5, showing that there is no autocorrelation, thus, fulfils the assumption of independence of observation. Further, the assumption of multicollinearity can be checked by observing which shows tolerance is greater than 0.1 and VIF is less than 10. This shows that there is no multicollinearity. Finally, the P-P plot shows that the points generally follow the normal (diagonal) line with no strong deviations. In this way, we can say that all the assumptions for HMR are met.

The table below shows the results of HMR:

As per the above table, for model 1, when only income was taken as an independent variable, the regression coefficient R2 comes out to be 0.009. This shows if the income is changed by 100 per cent, only 0.9 per cent variation will be observed in the BMI. Further, when Craving is added to income in model 2, this variation is increased to 1.7%. However, whether the relationship is significant or not can be observed from the ANOVA result blow.

For model 1, as per ANOVA, F(1, 268) = 2.521; p = 0.114. Since the p-value is greater than the critical alpha value of 0.05, it can be said that there is no statistically significant association in model 1. That is, income does not have a statistically significant impact on BMI. Further, for model 2, as per ANOVA, F(2, 267) = 2.334; p = 0.099. Since the p-value is greater than the critical alpha value of 0.05, it can be said that there is no statistically significant association in model 2. That is, income and total craving do not have a statistically significant impact on BMI.

Finally, the coefficient table shows that income is negatively associated with BMI and total craving is positively associated with BMI. However, as the p-value or the significance value of both is coming out to be more than the critical alpha value of 0.05, it can be said that both there is no significant impact of independent variables on the dependent variable in both the model. That is, even after adding total craving, the results remain same.

Continue your journey with our comprehensive guide to Experimental Study on Factors Influencing Tourist Destination Popularity.