Evaluation Plan: Effect of Tobacco and Alcohol on High Blood Pressure

Developing an Evaluation Plan
Name:
Subject
Date of Submission
Developing an Evaluation Plan
An evaluation plan could be defined as a written manuscript, which describes how to evaluate, monitor, and how the evaluation results of a program will be used in evidence-based decision-making (Bowen, 2012). It includes a describing the program and how activities from the program are associated with its desired effects. In simple terms, it clarifies the purpose and expected results of the program. It is critical that an evaluation plan also describes how the entire process of the program will be implemented by including a study design (Parreco et al., 2012). Ultimately, an evaluation plan must provide the rationale and significance of a program to a specific profession. It follows that an evaluation plan does not only help the researcher in conducting the study but also fosters transparency to decision makers and stakeholders (Lombard et al., 2015). Thus, this paper discusses all sections of an evaluation plan that will be used by the researcher to examine the effect of tobacco and alcohol use on patients with high blood pressure.
The Centers for Disease Control and Prevention (2011) defines a cross-sectional study design as a study design where outcomes and exposures are measured instantaneously within a population. Such a study design allows the researcher to deduce a relationship between the outcome and exposure (Blankenship, 2010). However, the study cannot be used for a causal-end-effect study. Another characteristic for a cross-sectional study design is that it is used for single observations or studies that take a short time. As a result, they are mostly used to examine the prevalence of diseases or disorders within a population. It is known that the researcher intends to identify the effect of tobacco and alcohol consumption on hypertension. Further, the researcher intends to conduct the study for only three months, which is a short time. Considering that the characteristics of a cross-sectional study design fits the intentions of this study, the researcher is justified to use a cross-sectional study design.
In order to complete the study successfully, the researcher intends to divide the study population into two groups. One group will contain people who are suffering from hypertension while another group will comprise of healthy study participants. Each of the groups will further subdivided into teetotalers, drunkards, smokers, non-smokers, and ex-smokers. They will also be categorized based on different age groups, which will be defined after obtaining the ages for the study participants. Additional categories for the study will include the number of beers taken every week and the number of cigarettes smoked every week. All the aforementioned categories will be independent variables while blood pressure (BP) recorded from the study participants will be the dependent variable. Further, the researcher will examine whether the effect of the independent variables is different for diastolic and systolic BP. Simply, put the diastolic and systolic BP will also be considered as dependent variable differently.
Zanazzi (2014) argues that it is useful to consider relevant responsibilities and interactions of people who contribute to the study directly. Such people include data collectors, study participants, and the researcher. It follows that the researcher has a duty of educating the data collectors and study participants on their roles and responsibilities. It is undeniable that a researcher cannot educate data collectors and study participants devoid of using appropriate tools (Fraser Health, 2009). Consequently, the researcher designed a data collection checklist, which was used to educate both data collectors and the study participants. The researcher also created a database with email addresses from the study participants and sent them instructions on how to fill the data collection checklist. Moreover, the researcher used their email addresses to remind them of their weekly visits to the Kings County Hospital. Samples of the data collection checklists are shown in Appendix 1 below.
It is also critical for researchers to develop tools that can help them to evaluate outcomes of a study because such tools enable them to make conclusions (Diem and Moyer, 2005). Consequently, the researcher is equipped with statistical software, which will be used for data analysis. This owes to the reality that the researcher is ready to use statistical software such as the Statistical Package for Social Sciences (SPSS) and R for data analysis. It is also critical to mention that the researcher will use Microsoft Excel to clean and code the data in preparation for data analysis. It is also notable that statistical tools such as analysis of variance (ANOVA), the t-test, Kruskal-Wallis test, or the Wilcoxon tests will be used depending on the nature of the data. Specifically, the t-test and ANOVA will be used for normal data while the Kruskal-Wallis and the Wilcoxon tests will be applied for non-normal data (Hall, 2008). Moreover descriptive statistics, incidence rates, and prevalence rates will be used to evaluate the outcome of the study.
In conclusion, it is clear that an evaluation plan is an important section when conducting research (Levin, 2006). As a result, this paper discusses all sections of an evaluation plan that will be used by the researcher to examine the effect of tobacco and alcohol use on patients with high blood pressure. For instance, it is clear that the prospective study design will be used to describe the effectiveness of the proposed solution. Moreover, the blood pressure will be the only dependent variable while the study will include independent variables such as age, status of smoking, and amount of alcohol consumed. It is also critical to highlight that the data collection checklist and an email database are the main tools the researcher intends to use for training data collectors and the study participants. Ultimately, the researcher will use statistical software in additional to statistical tools such as ANOVA a...