1 Research Basics of Research Assignment Rebekah Reed School of Community Care & Counseling: Liberty University Author Note Rebekah Reed I have no known conflict of interest to disclose. Correspondence concerning this article should be addressed to Rebekah Reed. Email:[email protected]
2 Research Causal Inference Causal inference is that something is, or could be, the cause of something else. It is a cause-and-effect relationship. An example in someone's life could be that they were in college and went to class every day and passed because of perfect attendance. There is a direct correlation that shows that smoke caused diseased lungs. The book, Applied Statistics, gives an example of social stress causing high blood pressure (Warner, 2021). An example in ministry of causal inference is the law of sowing and reaping in the Bible. If a person sows seed, they reap the harvest whether that be literally speaking in terms of farming, or sowing money into a ministerial organization. God gives to those who give the first tenth of their profit because they sowed their seed in the church. In these examples, there is an X and Y variable. They directly relate to each other when researched. X is the attendance, and Y is the person passing the class. X is the stress, and Y is the high blood pressure. X is the sowing, and Y is when the person reaps. There are many subtle examples of causal inference in everyday life, and it could be observed by anyone willing to pay attention. There are many cause-and-effect relationships that happen throughout the day, and it is easy to spot when they make life difficult. For example, stressors can be a cause of depression or anxiety. If someone deals with this in their life, it would be easy to point out the triggers when the person is anxious or depressed. Causal inferences are liked because they are an easy way to explain events or tie them together in science and in everyday life. Causal inference can also help in suggesting we can change the outcome of a possibility (Warner, 2021). P-Value & p-hacking
3 Research The value of p represents the probability of obtaining a result (Warner, 2021). This is saying how likely it is to find out what could have happened in research.Finding the probability of the null, or the alternative hypothesis, is the goal of proving p to be incorrect (Warner, 2021). When a researcher incorrectly interprets statistical analysis or manipulates results for a biased outcome, this is p-hacking. It is a desire to have significant results statistically, so they will rework it until they are satisfied (Warner, 2021). Common practices of p-hacking are reporting large numbers of significant tests, running different analyses, or deleting scores until they obtain the results the researcher wants (Warner, 2021). Studies that are done should be completed several times in order to obtain the most accurate information. Studies can be significantly flawed when p-hacking occurs. This is also called data fishing, data torturing, and questionable research practices (Warner, 2021). P-hacking leads to false positives per the definition. When current researchers start producing their results, p-hacking could be indirectly involved with false positives. Researchers who are implicating p-hacking in today's research will directly affect future research which will produce skewed results. An example of this is the number of deaths from 2020-2022 that resulted from COVID, or not. There have been dishonest numbers, from what has been said, about the actual number of deaths COVID has caused versus another disease or illness. It will be interesting to see p-hacking occurrences in those results in the future.
Why is this page out of focus?
Because this is a Premium document. Subscribe to unlock this document and more.