Plan for Data Analysis of Demographic Variables
To identify associations between the demographic variables, correlational descriptive statistics tests will be used. The correlation coefficient will be the key focus to show how closely the two or more variables are related. The regression equation and the correlation coefficient will be calculated based on the dependence between the variables if they at least approximately can be regarded as linear.
Otherwise, the results may be completely incorrect. In particular, the correlation coefficient may be close to zero in the presence of a strong relationship. This is typical for cases when the dependence is nonlinear, for example, the dependence between variables is approximately described by a sinusoid or parabola (Sullivan & Verhoosel, 2017). In many cases, this problem can be circumvented by transforming the original variables. However, to guess the need for such a transformation and find out that data can contain complex forms of dependence, it is essential to detect them. That is why the study of the interrelationships between quantitative variables will also include viewing scattering diagrams.
In other words, the correlation coefficients will help to establish whether it is possible to predict the possible values of one indicator knowing the value of the other or not. Meanwhile, it will be interesting to check whether there is a connection between the responses of parents and children to restricted access to sugary and fatty foods and their age and gender. This is likely to allow asserting that, for example, the older the person, the more critical will be his or her views and vice versa. At the same time, to strengthen the analysis of variables, Spearman correlation will also be used.
Plan for Data Analysis of Study Variables
Descriptive and inferential statistical tests will be applied to analyze study variables, both dependent and independent as well as extraneous ones. The use of inferential statistics will allow a researcher to understand if the pattern is actual or occurs by chance. Since inferential statistics is a branch of analysis that deals with concluding a population-based on measurements obtained from a representative sample of this population, the key to determining whether it affects is measuring the statistical value, as noted by Mertler and Reinhart (2016).
The latter will show the connections between the variables that are probably not due to the usual chance, and that the real dependency between the two variables is most likely. In this connection, the Analysis of Variance (ANOVA) test will be used. It implies that the average populations from which the samples were extracted are equal, in other words, they all belong to the same population, and the differences are random. To test hypotheses in the case of variance analysis, the F distribution will be used. F-statistics takes only positive or zero values.
The procedure of the variance analysis will consist of determining the ratio of systematic (intergroup) dispersion to random (intra-group) variance in the measured data (Mertler & Reinhart, 2016). It seems also essential to point out that as a measure of variability, the sum of the squares of deviation of the parameter values from the mean is used Sum of Squares (SS). Ultimately, the generalization of data from sample studies will be made based on techniques determining to what extent the relationships identified in the sample describe the characteristics of the general population along with their importance.
Mertler, C. A., & Reinhart, R. V. (2016). Advanced and multivariate statistical methods: Practical application and interpretation. New York, NY: Routledge.
Sullivan, M., & Verhoosel, J. C. M. (2017). Statistics: Informed decisions using data (5th ed.) Upper Saddle River, NJ: Pearson.