The next step in your research project is analyzing the data you collected. In previous courses, you wrote statistical results for several of your assignments. For this assignment, you will do the same for the data you collected and analyzed. Analyzing the data will help you determine the success of your study and help you make meaning of your information.
In a 2–3 page paper, using the required Data Analysis and Interpretation Template [DOCX], address the following points:
Describe your participants using demographic statistics.
Explain the statistical measures you used to analyze your data.
Be sure that you report your findings in APA style.
Describe your statistical findings, including statistical significance and influence of effect size.
Be sure to format your data in APA style.
Interpret your statistical findings using common language.
Attach a screen shot of your data analysis results from Excel or SPSS.
Submission Requirements
Submit your paper as your deliverable for assessment.
[Enter Paper Title]
The Role of Familiarity in Misinformation
Effects of Misinformation
Chan et al. (2017) argued that information that appears or is thought to have been true but later turns out incorrect can affect how people think or make decisions even after this misinformation has been corrected by credible sources when people remember and understand this correction. According to Chan and his colleagues, the overall effects of misinformation have been an area of key interest to psychologists because of the concerns that it can affect individual voting decisions and health behaviours. Chan gives the example of the rumour that the Zika Virus outbreak across Brazil resulted from genetically modified mosquitoes was a claim that was any scientific evidence did not support that. Given that misinformation can result in poor decision-making regarding consequential matters and difficult to correct, Chan et al. (2017) argued that understanding it is a crucial public policy and scientific goal.
In another study, Berinsky (2015) argues that refuting rumors through relying on statements emerging from unlikely sources has the potential to increase a society’s willingness to reject the rumours regardless of the political predictions made. The study further suggests that a given rumor’s source credibility can be a highly effective tool for dispelling political rumours. Leveraging on research from psychology, particularly regarding fluency, Berinsky’s (2015) study suggests that rumours tend to acquire more power through the concept of familiarity. In other words, any attempt to quash any rumors through the act of direct refutation has the potential to facilitate the diffusion of these rumours by increasing fluency. Based on Berinsky (2015) study, we can conclude that simply repeating a specific rumor has the potential to increase its power,
Continued acts of misinformation can undermine well-functioning democracies. For instance, Cook, Lewandowsky, and Ecker (2017) suggest that public misconceptions regarding climate change can lower acceptance of climatic changes’ reality and effects and lower the support of potential mitigation policies. Cook, Lewandowsky, and Ecker (2017) study explored the overall impact of information on climate change to establish the measures that can be adopted to reduce the influence that this misinformation can have on efforts to remedy climate change. The study managed to establish that biased media coverage and misinformation lowered perceived consensus, with the impact being more among free-market supporters. The study established that inoculating messages explaining flawed argumentation techniques applied in misinformation effectively neutralized the adverse effects associated with misinformation. This study recommends that appropriate climate communication messages consider the approach to distort scientific content and engage preemptive inoculation messages.
Familiarity’s Role in Misinformation
People tend to believe or rely on certain information even when it has already been retracted from a phenomenon. Ecker, Hogan, and Lewandowsky (2017) describe it as a continued influence miscommunication effect. Retractions tend to be defective due to several factors: repeating information, especially during corrections, can inadvertently strengthen, leading to the misinformation being strengthened by ensuring that it becomes more familiar. As such, practitioners should design corrections that can avoid misinformation repetition. Ecker, Hogan, and Lewandowsky’s (2017) study aimed to investigate this approach by establishing whether retractions are effective when repetitions and reminders of the original misinformation are included. The study’s findings were that retractions tend to vary in the extent or how they serve as misinformation reminders. On the other hand, retractions that repeated the misinformation appeared to be more effective in minimizing the effects of the misinformation than retractions that were avoidant of the repetition to enhance salience. Based on this understanding, debunking effective myths must be revised to minimize misinformation effects.
Some studies have suggested that people’s inability to refresh or update their memories, particularly where collective information is involved, leads to significant public health consequences. Pluviano, Watt, and Della Sala’s (2017) study attempt to investigate this fact by comparing three strategies that could potentially promote a vaccine, with one approach being a myth and another one a fact. The study sought to investigate the beliefs in the autisms and vaccine link, its side effects, and the intentions to ensure that future children are vaccinated. This research demonstrated that the existing strategies used to correct vaccine misinformation often backfire and are ineffective, leading to unintended opposite effects and reducing specific vaccines’ intentions. From Pluviano, Watt, and Della Sala’s (2017) study, we can conclude that misinformation can lead to significant public health consequences.
The Role of Technology in Promoting Familiarity in Misinformation
With the advent of information technology, particularly social media, people routinely encounter inaccurate information emanating from various fake news sources that confuse their target audiences or fake stories designed to entertain readers. Under such circumstances, the hope would be that these tendencies or inaccuracies are ignored, leading to very little influence on our actions or thoughts. Unfortunately, Rapp and Salovich (2018) explain that exposure to such inaccuracies can lead to very problematic outcomes and consequences. Reading inaccurate statements often results in readers exhibiting clear effects of such contents, particularly their problem-solving skills or decision-making process. Such occurrences tend to happen even when the audience already has the right prior knowledge to reject or evaluate the existing inaccuracies. Exposure to these misinformation types tends to confuse what is true while also doubting any accurate understandings or subsequent reliance on manufactured falsehoods. As such, the study recommends that technologies and interventions designed to address such effects should encourage critical Assessment that can support effective learning and comprehension.
Finally, piecemeal reporting of occurring news events can lead to misinformation about such events that would later have to be corrected. Rich and Zaragoza (2016) argue that studies on continued influence demonstrate that corrections aren’t effective in reversing the effects of misinformation. In most cases, participants usually continue to leverage information that is already discredited when seeking to make judgments or draw inferences about a specific news item. To establish this fact, Rich and Zaragoza (2016) studied two experiments where the first one established that corrections often reduce reliance on misinformation in both implied and explicit conditions. However, the correction tends to be less effective where implied misinformation is involved. The second experiment demonstrated that misinformation tends to be more resistant to any form of correction compared to explicit misinformation. Based on these findings, we can conclude that corrections aren’t effective in reversing misinformation effects. Participants usually continue to leverage information that is already discredited when seeking to make judgments or draw inferences about a specific news item.
Limitations
The limitation to the current research study is that there is little prior research on the role of familiarity in misinformation, which means that the study has had to develop a new research topology leveraging the few research studies. Another limitation is that the current study is affected by the conflict from cultural and personal biases. The study relies on individuals from different cultural perspectives or backgrounds to understand the role of familiarity in misinformation. It is an issue that affects the overall legitimacy of this study.
Hypothesis
Researchers have indicated that uncertainty tends to gain more power via the familiarity concept; hence, it becomes difficult for a person to replace it with factual information even when verified. According to Berinsky (2015), any trial to quash the rumors through direct refutation actions will potentially make the rumors gain more power. The hypothesis for this study will be familiar to any information or knowledge doesn’t help in demystifying the misinformation. The independent variable will be familiarity with information, defined as the quality or state of knowing about something. The dependent variable will be misinformation.
Method
Sampling
I will use the systematic sampling method because it will allow the researcher to zero down the whole population to the desired population (Schonlau et al., 2002). The researcher will recruit the sample from his colleague students in their online class. The online class is a closed population considering there is a list to know the class members.
Data will be collected from this sample, which will subsequently be measured and analyzed accurately using standard validated techniques. The main objective of data collection will be to ensure that the information is rich and reliable for accurate analyses such that data-driven decisions could be made from the research (The Open University, 2014). In this case, the research is primarily quantitative research meaning that the researcher is looking for the causality or link between the identified variables in the study. Questionnaires will be administered to each member of the sample population. The questionnaire will have carefully constructed questions with ranking options so that the respondent will tick off their answer.
After the data collection process and the researcher receives the answered questionnaires, statistical analysis will be incorporated to turn the quantitative data into useful information for decision-making purposes. Statistics will be used to summarize the data, describe the patterns, relationships, and connections. This will be a form of descriptive statistics as the aim is to summarize the information and to gain insights based on the analysis.
Measures
I will use a debunking myth fact sheet describing the myths and then debunking them in a two-column format. Also, I will use a one-question test measuring the amount of misinformation retained.
Procedures
The cross-sectional study design will be used for this study. This design method entails collecting data from several different individuals at a single point in time. The cross-sectional research will have the variables in the study observed without them being influenced. The study is normally observational and is common within descriptive research. The researcher will record the population’s information without manipulating any of the variables (Sacred Heart University Library, 2020). This study design will enable the researcher to gather preliminary data to support the experimentation to be undertaken. I will have one group.
I will use a one-shot case study design. All participants will be volunteers. The participants will complete a demographic questionnaire to get information on age, gender, family income level, and employment status. All participants will be in one group. The participants will be exposed to the misinformation through debunking the myth pamphlet. They will receive the misinformation.
One variable that has a potential impact on the study outcomes is mainly the respondent’s identity. The salience of race, ethnicity, culture, religion, and other aspects of an individual’s identity, especially since the respondents do not have a similar background or beliefs, raises concerns about their responses to the questionnaire (Nyhan, 2012). One example is when a respondent comes from a minority group whose entire life has been characterized by taking second place. There is a higher possibility for this individual to feel the lack of control over different matters. These individuals could choose to select perceptions that they believe to be accepted by the majority group even if they knew and believed differently. To control this issue, the researcher will present all respondents with a technical issue, specifically a scientific matter. The researcher assumes that technical matters will rarely have strong beliefs attached to them. The respondent will rarely need to look into their beliefs and support particular issues in responding to the fact sheet.
This research incorporates the one-shot case study design where all responses will be gained during the experiment without a control group. Notably, the pretest-posttest-only with control design where one group receives the fact and another receives the myth could be considered quasi-experimental. The treatment and control groups would have provided an adequate comparison to a baseline. Nonetheless, the study outcomes’ validity and reliability depend on how accurate the responses are given in the first instance they receive a myth. The beliefs needed to be obtained during the experiment such that any external factors do not influence the responses. Asking for an explicit expression of belief during the experiment would strongly impact how the myth is processed and how the correction is later achieved.
Results
Participant Demographics
A total of 15 respondents were systematically selected to participate in the survey. The selection was made from the researcher’s online class. The ages of the respondents ranged from 18 to above 46. notably, the researcher divided the respondents into four age categories, namely 18-25, 26-35, 36-45, and above 46. the table below demonstrates the number of respondents for each age group:
Age Ranges Number of respondents
18-25 1
26-35 2
36-45 2
46 and above 9
Not Specified 1
TOTAL 15
The respondents’ level of education is that they have completed their A levels and have completed a graduate diploma or degree as per the requirements of being enrolled in the online class.
Statistical Tests
Inferential statistics were incorporated for the data analysis purposes. This entailed making inferences and predictions on the extensive information collected (Lund Research Ltd, 2018). The sample data from the original data is considered then the probability is utilized to reach the research’s solutions.
Table
The Table of the data was constructed as follows;
Table 1: Group data and Frequency from the research.
Mean, Median and Mode Solution for the data;
Table 2; Mean
The Median was calculated as follows;
Descriptive Statistics was as follows;
Findings
As deduced from the data above, the mode of the data is 46 years and above. This is an implication that many of the respondents were 46 years and above.
Note: The research was only conducted on people 18 years and above. Unspecified respondent was not included in the calculation as this would affect the analysis of the data.
The P-value of the data is 0.016, meaning that the correlation is statistically significant. This is an implication that there is strong evidence for the Alternative hypothesis. Thus, the relationship between age and believing in facts or myths.
Moreover, Pearson’s R of 0.968 means a robust correlation between age and believing in facts and myths. Normally, a correlation between 0.5 and 0.7 shows a moderate correlation between the variables, while 0.3 and 0.5 show a low correlation.
The descriptive and inferential statistics obtained in plain language show significance between age and believing in factual or myth information. It implies that being familiar with any information or knowledge does not help one in demystifying the misinformation. Thus the younger generation may focus on little information or knowledge, but that does not make them knowledgeable.
Effect Size
Myth Busting 1
Mean: 54.93
Median: 52.38
Mode: 46 and Above
Standard deviation σ=21.4766128139
Corrected sample standard deviation s=23.1973931212
Myth Busting Part Two:
Mean: 55.33
Median: 51
Mode:
The standard deviation of the data
Statistical file:
{21.5, 30.5, 40.5, 40.5, 73, 73, 73, 73, 73}
Standard deviation σ=20.4450483003
Corrected sample standard deviation s=21.6852484422
Effects size of the data Calculation
Mean of Myth Bursting 1 minus Mean of Myth Bursting two / Standard deviation
Let x1 be the mean of Bursting 1
Let X2 be mean of Myth Bursting 2
So X2-X1/ standard deviation
55.33-54.93/ 20.45
Ans 0.01955
This implies that an effect size of 0.01955 of the adult person in the experimental group (Myth Busting 1) is a 0.01955 standard deviation above the person in the adult person in the control group (Myth Busting two). This implies that it is lower than 79%, which is the standard of Effect hence implying that the two groups of 15 in both Experiment and Control would not accurately tell between myths and facts even though they have facts and knowledge about the subject.
References
Berinsky, A. J. (2015). Rumors and health care reform: Experiments in political
misinformation. British Journal of Political Science, 47(2), 241-262. doi:10.1017/s0007123415000186
Chan, M. S., Jones, C. R., Hall Jamieson, K., & Albarracín, D. (2017). Debunking: A meta-
analysis of the psychological efficacy of messages countering misinformation. Psychological Science, 28(11), 1531-1546. doi:10.1177/0956797617714579
Cook, J., Lewandowsky, S., & Ecker, U. K. (2017). Neutralizing misinformation through
inoculation: Exposing misleading argumentation techniques reduces their influence. PLOS ONE, 12(5), e0175799. doi:10.1371/journal.pone.0175799
Ecker, U. K., Hogan, J. L., & Lewandowsky, S. (2017). Reminders and repetition of
misinformation: Helping or hindering its retraction? Journal of Applied Research in Memory and Cognition, 6(2), 185-192. doi:10.1016/j.jarmac.2017.01.014
Lund Research Ltd. (2018). FAQs about descriptive and inferential statistics. SPSS Statistics Tutorials and Statistical Guides | Laerd Statistics. https://statistics.laerd.com/statistical-guides/descriptive-inferential-statistics-faqs.php
Nyhan, B. (2012). Misinformation and fact-checking: Research findings from social science.
New America Foundation.
Pluviano, S., Watt, C., & Della Sala, S. (2017). Misinformation lingers in memory: Failure of
three pro-vaccination strategies. PLOS ONE, 12(7), e0181640. doi:10.1371/journal.pone.0181640
Rapp, D. N., & Salovich, N. A. (2018). Can’t we just disregard fake news? The consequences of
exposure to inaccurate information. Policy Insights from the Behavioral and Brain Sciences, 5(2), 232-239. doi:10.1177/2372732218785193
Rich, P. R., & Zaragoza, M. S. (2016). The continued influence of implied and explicitly stated
misinformation in news reports. Journal of Experimental Psychology: Learning, Memory, and Cognition, 42(1), 62-74. doi:10.1037/xlm0000155
Sacred Heart University Library. (2020, September 10). Research guides: Organizing academic research papers: Types of research designs. SHU Library – Research Guides at Sacred Heart University. https://library.sacredheart.edu/c.php?g=29803&p=185902#s-lg-box-wrapper-626726
Schonlau, M., Ronald Jr, D., & Elliott, M. N. (2002). Conducting research surveys via e-mail and the web. Rand Corporation.
The Open University. (2014). 6 Methods of data collection and analysis. Monitoring, Assessment,
Accountability and Learning (MEAL)
