Probability sampling
please respond to each discussion with a reference
discussion 1
Probability sampling, also known as random sampling, is defined as “one in which every sample of a particular size has an equal probability of being selected” (Hebl and Lane, n.d.). The thought process for this is that the opportunity for systemic bias is less when sample/subjects are randomly selected. Using random sampling leaves the subject selection to “chance”, instead of having researchers consciously or unconsciously selects subjects whose conditions or behaviors are consistent with the study hypotheses. In theory, because selection is left to chance, study findings should have increase validity (Burns & Grove, 2007). The four most common probability sampling methods used in nursing research include simple random sampling, stratified random sampling, cluster sampling, and systematic sampling (Burns & Grove, 2007).
One probable problem/limitation that could prevent a truly random sampling would include sample size adequacy. As we can recall, a random sample is a sample in which every member of the population has an equal chance of being selected (Hebl and Lane, n.d.). Random samples, especially small sample size, are not necessarily representative of the entire population (Hebl and Lane, n.d.). Sample sizes that are too small can result in studies that “lack the ability to identify significant relationships among variables or differences among groups” (Grove ,n.d.). These types of studies often lead to the risk of acquiring a type II error. According to this week’s reading in the “ Understanding Nursing Research: Building an Evidence-Based Practice”, important factors to consider in determining sample size for qualitative studies are to include the “scope of the study, nature of the topic, quality of the data collected, and design the study”.
References:
Grove, S., Gray, J., & Burns, N. (2015). Understanding Nursing Research (6th ed.). St. Louis, MO: Elsevier Saunders.
Discussion 2
Random sampling is also called probability sampling, each part of the population undergoing a study has the same chances of being chosen as every other participant in the study. The point of a random sample study is to have more of a representation of the group targeted for the study, to have an equal representation of the group. Random sampling should allow for participants to have representation without prejudice one way or another. There are some problems or imitations to random sampling such as not using a large enough sample size to be representative of the targeted group. Knowing the ages, diagnoses and gender, ethnic background helps gather a sample size to include an even amount of all needed to participate, or it might not be a proper representation of the group to be surveyed. To truly get a random sample there would be a great cost in money needed to be able to obtain the needed individuals to participate and in hoping that all the participants answered all the questions honestly to the best of their ability.
Definition of Random Sampling | What is Random Sampling? Random Sampling Meaning. (n.d.). Retrieved May 7, 2018, from https://economictimes.indiatimes.com/definition/ra…
Grove, S. K., & Cipher, D. J. (2017). Statistics for nursing research: A workbook for evidence-based practice (2nd ed.). St. Louis, MO: Elsevier.
Discussion 3
Random sampling is also called probability sampling. It is important because it ensures that every variable of data set has the same chance of getting chosen. Random sampling allows each member to have a fair chance; no samples are favored over others. This prevents bias and sampling errors by allowing the sample to represent itself equally. The data or people surveyed are not random people, they are from a targeted population. Grove and Cipher (2017) stated, “The purpose of sampling in quantitative research is to obtain study participants who are as representative of the target population as possible. The sample’s representativeness of the study population is increased by probability sampling.” Larger populations have the best results with probability sampling. A computer choosing random samples is the most commonly performed random sampling method. Another way random sampling is conducted by assigning numbers to each member or variable, and randomly selects samples, this method has the same concept as pulling numbers out of a hat. According to the Khan Academy (2018), “Every member and set of members has an equal chance of being included in the sample. Technology, random number generators, or some other sort of chance process is needed to get a simple random sample.” Random sampling (simple random sampling) is one of the four probability sampling methods used in nursing research. Stratified random sampling, cluster sampling, and systematic sampling are the probability sampling methods.
A problem that can prevent a truly random sampling can be the size of the population. For example when conducting a poll in larger groups such as one thousand people or more, random samples are more effective because it takes less people to obtain accurate results or responses. Whereas in a smaller group such as one hundred people or less, random sampling might have some disadvantages because more people may be needed to obtain accurate results or responses. Custom Insight (2018) stated, “As the population size increases, the percentage of people needed to achieve a high level of accuracy decreases rapidly.” A random sampling can be costly because every person in the group must meet certain criteria in order to qualify, which increases accuracy of results. The use of random sampling can be more efficient when saved for larger groups with participants that represent the target population.
References
Custom Insight. (2018). Random Samples and Statistical Accuracy. Retrieved from https://www.custominsight.com/articles/random-samp…
Grove, S. K. & Cipher, D. (2017). Statistics for Nursing Research: A Workbook for Evidence-Based Practice, 2nd Edition. St. Louis, MO: Elsevier.
Khan Academy. (2018). Sampling Methods Review. Retrieved from https://www.khanacademy.org/math/statistics-probability/designing-studies/sampling-methods-stats/a/sampling-methods-review
Discussion 4
Random Sampling is a method for obtaining a sample. When obtaining a sample this way will allow for all of the population or possible participants have an equal chance of being selected for obtaining a sample. For example, if a business of 50 people were going to do a survey but only 10 would actually be surveyed, everyones name would be put into the drawing once.
Random sampling has some pros and advantages.. It provides a true random sample and allows everyone with an equal chance to provide their input. This can also be used to get a general idea of what the population is thinking/answering. (Advantages And Disadvantages Of Random Sampling, 2014)
Some cons and disadvantages of Random Sampling can be that there may be a change for some biases results. This can be done by providing only a few opportunities for the survey. A person taking the survey could provide an answer that is biases and unlike the majority of the population. Also, the surveys or participants could be surveyed in an area where the majority has a familiar belief. For example, if a “random sample” were to prefers either Republicans or Democrats could have a bias opinion. The sample/survey could have a large amount of surveys provided to an area that is known to have a high Democratic/Republic supporter area. This could cause a biases and problematic result. (Advantages And Disadvantages Of Random Sampling, 2014)
Some of these disadvantages could be prevented by actually making sure that the sample is random and that everyone throughout the population has an equal chance for being sampled. Some example that should not be done for random sampling would be not selecting people out of a phonebook due to the fact that not everyone is in a phonebook. You should ask for volunteers, random sample should truly be random. This could lead to bias results which will not help the result at all.
References
Advantages And Disadvantages Of Random Sampling. (2014). Retrieved on May 7, 2018 from https://occupytheory.org/advantages-and-disadvanta…
Discussion 5
The importance of random sampling is that it gives a fair chance to the entire population to participate in a study as a study subject Random sampling allows every facet of the study population to be examined without study bias and cuts down on sampling error. This help to make sure that study participants are as representative of the population as possible. This complete randomness helps with the elimination of the possibility of bias. The reason that this is important is that it helps ensure the scientific accuracy of the sample (Grove & Cipher, 2017).
The problems with random sampling would be the implementation of a truly random sample. It requires that everybody participate equally which may not happen. People with the strongest feelings towards a subject or topic may be the most likely to respond to the survey. This builds in bias because of those feelings. Another limitation of a random sample is the scope. To truly have a random sample every member of a population must be given a number and then randomly chosen. If you have a very large population such as the population of the world the time and distance involved would make such a sample prohibitive (Grove & Cipher, 2017).
There have already been solutions to these problems with different sampling techniques such as stratified random sampling and systematic sampling. They include randomness and help make the survey size more manageable (Grove & Cipher, 2017).
Reference:
Grove, S. K., & Cipher, D. J. (2017). Statistics for nursing research: A workbook for evidence-based practice. St. Louis (MO): Elsevier.
Discussion 6
The visual learner presentation gives five examples of sampling technique. The first one is cluster sampling. Cluster breaks populations into groups and then randomly chooses members from that group to be sampled. For example, it would be difficult to judge the amount of education that every person in the State of Utah has achieved. It would easier to break the state into cities and then take your sample from the city cluster to get a representative result.
Simple random is that everybody in the sample size has the same chance of being in the sample. For example, if you wanted to so a survey on nurses; every nurse would be given a number. That number would then be placed into a randomizer. A certain number of nurses would then be chosen to participate.
Stratified sampling breaks a sample population into at least two different groups or strata that share a characteristic. The survey is then given to random people in that strata. An example would be persons that had taken a CPR class and those who had not. Each is a separate group and then random samples are taken from each group.
Systematic is just choosing a sample in the same way from a population. For example, if you had 1000 people together you may choose every fourth person for a sample of 250 people.
Convivence sampling is just getting the data that is easiest to get. For example if I wanted to sample people in my hospital about an issue if I were to convivence sample I would go to the people on my floor and ask then because that is the easiest for me.
Reference
Visual Learner. (n.d.). Retrieved from https://lc.gcumedia.com/hlt362v/the-visual-learner…