Introduction
Research methods are useful for either generating or testing a hypothesis. Specifically, studies that are observational, such as those where data is reviewed to establish a relationship, create hypotheses. For the current study, the objective is to determine if obesity causes dyslipidemia. Performing a statistical test to analyze the data will decide whether or not it is sensible to accept the hypothesis. Thus, inferences about the strength of association between the variables lead to rejection or acceptance of the null hypothesis.
Data Set Description
The main types of variables in research are dependent, which is the presumed effect, and independent, which is the cause. There are also confounding /extraneous variables that may have an unwanted impact on the dependent variable and may make the researcher draw a wrong conclusion (Suresh, 2018). In the current study, obesity is the independent variable, whereas dyslipidemia is the dependent variable. There are also covariate or control variables that are not central to the study but may affect the outcome, such as age, sex, and the number of treated people (Nelson, 2020). Using the Statistical Package for the Social Sciences (SPSS) allows researchers to label both string and numeric variables. In this case, the values include feminine/masculine (sex), percentile (treated), and normal (lipids), while others, like age and BMI, do not have a value.
Data is considered discrete if it is whole and continuous if it can be divided and measured in decimal points. Variables without quantitative values are nominal and include sex, lipids, and treatment (Nakar, 2017). The age of the sample population can be classified into a scale since the data is easily categorized with meaningful metrics (Rennemeyer, 2021). At the same time, data on BMI is an example of ordinal as it has a specific order. The sample size or the number of observations for the current study is fifty people whose BMI was measured while collecting other relevant information. The research may fail to have complete information for some data sets, which may negatively impact quality (Tute et al., 2021). However, in the current study, there is no missing value; hence, the data set is complete.
The research question and the hypothesis serve as a strong guide to the type of variables that are important for analysis. In the current study, the BMI is of relevance because it is the independent variable. The data on lipids are dependent variables which makes them significant during data analysis. However, there are also other covariant variables, such as treatment, age, and sex, all of which may serve as extraneous variables (Denis, 2018). Thus, when doing an analysis, the researcher will control their effect to ensure accurate findings on correlation and causation.
Filling in raw data from the field to the SPSS can be an exhausting process, and some people opt to use excel sheets first before importing the data. There is a seven-step process that researchers can use to transfer their data from excel to SPSS without necessarily retyping the information (Glen, 2022). However, for the current study, there is no challenge anticipated for using the SPSS. A model summary, ANOVA, and coefficient results for analyzing the independent and dependent variables are provided below. Notably, the dataset provided is for regression to determine whether there is a cause and effect between the BMI and the lipids.
Conclusion
Planning for the data analysis process is significant as it helps the researcher assess the available data. The interest of the research is to show if there is a significant association between obesity and dyslipidemia. In turn, the researcher took their BMI for a sample size of fifty respondents. One of the inclusion criteria was for the BMI to be above 30. The student also took the lipids of the selected individuals to serve as the dependent variable during data analysis. Additionally, the researcher gathered interesting data, including age, sex, and treatment, because they can influence the relationship between the predictor and the outcome variable.
There was no missing data for any variable subset, implying that the analysis would use the entire sample. The selected tool for analyzing the data is SPSS which can produce a regression analysis to show causation and relationship. For mapping purposes, the information is organized according to values and the type of variable. Thus, reports on the effects of the extraneous variables will be provided when discussing the findings. The mapped result shows that the value of R-square is 0.004, which indicates a weak prediction. Further analysis and interpretation will be made in the consecutive chapter.
References
Denis, D. J. (2018). SPSS data analysis for univariate, bivariate, and multivariate statistics. John Wiley & Sons.
Glen, S. (2022). Excel to SPSS: How to import data. Statistics How To. Web.
Nakar, M. (2017). Nominal, ordinal and scale- Levels of measurement in SPSS. Market Research. Web.
Nelson, M. (2020). Statistics in nutrition and dietetics. John Wiley & Sons.
Rennemeyer, A. (2021). Types of data in statistics – Nominal, ordinal, interval, and ratio data types explained with examples. freeCodeCamp.org. Web.
Suresh, S. (2018). Nursing research and statistics. Elsevier Health Sciences.
Tute, E., Scheffner, I., & Marschollek, M. (2021). A method for interoperable knowledge-based data quality assessment. BMC Medical Informatics and Decision Making, 21, 1-14. Web.