Type of Sampling Strategy

Running head: OBESITY AND DIABETES RISK 1

OBESITY AND DIABETES RISK 6

Obesity and Diabetes Risk

Module 3 SLP Assignment

RES500 (2020JUN01FT-1)

July 12, 2020

Sampling

Type of Sampling Strategy

Simple random sampling is the most appropriate sampling strategy for the research study. Under this sampling strategy, people with obesity and aged between 35 to 45 years will have an equal probability of being chosen to form the sample size. The population, individuals living with and without obesity, will be divided into smaller subgroups, strata within the two cohorts – exposed and nonexposed. Strata are a homogenous group. Since the population shares the same characteristics, obese, the formation of strata becomes easy (Wrench, 2017). The researcher will get and obtain a sample population that best represents the whole population of obese people under the study. Simple random sampling will require a researcher to obtain a sample of obese volunteers aged between 35 and 45 years who are eligible based on inclusion and exclusion criteria. Any individual living with and without obesity but not under the age brackets listed will not be a study. The sample becomes a subset of the population. This approach is different because it divides the target population into smaller groups depending on shared features, unlike sampling that represents the whole data population. Many secondary independent variables (IVs) between study participants and the two cohorts include weight, body mass index, sex, marital status, race, education, occupation, income, medical history, family history, and age. The exclusion criteria include ages younger than 35 to more than 45 years of age to subjects with a prior history of T2DM.

Target Population, Sampling Frame, and Sample Size

Target population. The target population is Americans aged between 35 to 45 years. Any person living with and without obesity is part of the target population and will be part of the inclusion criteria. The population comprises all items of interest to the research study including specific characteristics. These features are individuals who have a medical condition of obesity and are young adults, ages 35 to 45 years old. This target population is the one in which research has interest when it comes to the generalization of the research conclusions.

Sampling frame. The selection of the sampling frame is based on different factors. It is not recommended to use any list you encounter when determining a sampling frame. In creating a research sample frame, the first step is to include every person in the target population (Wrench, 2017) for the study’s two cohorts that will include obese and nonobese participants. The second step is excluding all individuals, not in the target population. Then the third step is including accurate information that can help in contacting the selected individuals.

Sample size. A variety of variables must be taken into consideration when deciding the sample size. Because research is a costly undertaking, taking on a high number of participants may not be feasible due to a limited budget (Gentles et al., 2015). Ethically, the researcher must be responsible to the participants for not putting them through any unnecessary procedures or pain and for considering that smaller sample size may be capable of delivering the objective results (Murphy et al., 2018). Two tools can help to determine the number of sample sizes for multiple variables, Rule of 30 and application, G*Power (Gentles et al., 2015). The Rule of 30 generates numbers by using a minimum of 30 elements for each variable. If subcategories are compared, that is an additional 30. Therefore, the calculation is 30 per variable and 30 per group. Due to the possible dropouts during research, the researcher may include 30 additional participants (Gentles et al., 2015). The other tool, G*Power3, is a computer application that allows the user to plug in numerical values based on the variables, then the program calculates the sample size (Gentles et al., 2015).

Merits and Shortcomings of Simple Random Sampling

Merits. The critical merit of simple random sampling is that it encapsulates the essential features of the population in the sample. For populations with a variety of characteristics, such as weight, body mass index, sex, marital status, race, education, occupation, income, medical history, family history, and age, works well but is otherwise useless if subgroups cannot be established.

Demerits. Multiple conditions must be met for it to work properly. A researcher needs to identify every population member being researched and categorize each member into one, and only one, subgroup. Consequently, simple random sampling becomes a significant loss in case a researcher is unable to categorize every member of the population into a stratum (Wrench, 2017). Also, it becomes difficult to get an all-inclusive and final list of the whole population.

Ways of Avoiding Threats to Internal and External Validity

Strict guidelines should be used during the research to prevent misleading findings. All participants need to come from the same general population. This approach helps in avoiding selection bias. Also, a flawed study design threatens both internal and external study validity.

Using simple random sampling accurately represents the surveyed population due to common features, the categories are precise, leaving minimal space for bias (Palinkas et al., 2015). Once the specific variables of the individuals who qualify for the study have been identified, determine who is relevant within the group and how many participants are required to be effective in the program at a minimum. Stratified sampling performs strata representation within a population but is limited in cases where subgroups are not formed (Palinkas et al., 2015). The goal is to lower the chances of bias. Finally, if the sample size required is incorrect, internal, and external validity can be threatened. A small sample can undermine findings by failing to display real effects and a too-large sample is less likely to be affected by chance variability (Peffers et al., 2007). Effective sample size will result in results being reliable.

.

References

Gentles, S. J., Charles, C., Ploeg, J., & McKibbon, K. A. (2015). Sampling in qualitative research: Insights from an overview of the methods literature. The Qualitative Report, 20(11), 1772.

Murphy, M. P., Staffileno, B. A., & Foreman, M. D. (2018). Research for advanced practice nurses: From evidence to practice, 3rd edition (3rd ed.) Springer Publishing Company.

Palinkas, L. A., Horwitz, S. M., Green, C. A., Wisdom, J. P., Duan, N., & Hoagwood, K. (2015). Purposeful Sampling for Qualitative Data Collection and Analysis in Mixed Method Implementation Research. Administration and policy in mental health, 42(5), 533–544. https://doi.org/10.1007/s10488-013-0528-y

Peffers, K., Tuunanen, T., Rothenberger, M. A., & Chatterjee, S. (2002). A design science research methodology for information systems research. Journal of management information systems, 24(3), 45-77.

Wrench, J. S. (2017). Quantitative methodology. The International Communication Research Methods, 1-10.

"Is this question part of your assignment? We can help"

ORDER NOW