Is Friday the 13th a Particularly Unlucky Day: A Data Analysis Report

Photo courtesy of Getty Images

Florida Gulf Coast University, Department of Psychology

Introduction

From the five scenarios provided, I chose to analyze the social psychology data set because I found it the most compelling. I have always been interested in social psychology and I think the Friday the 13th phenomenon is a particularly fascinating topic to study.

The data provided researchers with the number of 911 calls for household and traffic accidents on two given Fridays, the 6th and the 13th. Involved parties include the individuals who made the calls, the 911 operators who recorded the data, as well as the researchers and the confederates involved in this study. The question that researchers are trying to answer through this data is if Friday the 13th is a particularly unlucky day or whether this idea is just superstition.

This study agrees with the APA’s Ethical Principles of Psychologists and Code of Conduct because the study is simply observing the rate of 911 phone calls. There is minimal risk involved and it is important to note that nobody is being put in direct danger due to this study. Researchers are simply analyzing the outcomes of the two Fridays.

The potential ethical issue this study faces is the fact that participants are not aware that they are in a study and therefore cannot give informed consent prior to the phone call. This can be found in the APA’s Ethical Principles of Psychologists and Code of Conduct 3.10 Informed Consent. To combat this, at the end of the call participants will be debriefed about the study and will have the opportunity to give informed consent. Both this and the fact that their information is kept anonymous assures the participants’ rights.

To ensure this report aligns with the APA’s Ethical Principles of Psychologists and Code of Conduct, researchers will respect the privacy of the individuals who participated in this study and will not release or share any of their personal information. It is critical not to breach Respect for People's Rights and Dignity.

Hypothesis and Descriptive Data Analysis

H0: There is not a statistically significant difference between the number of 911 calls for household and traffic accidents on Friday the 6th and the number of 911 calls for household and traffic accidents on Friday the 13th.

H1: There is a statistically significant difference between the number of 911 calls for household and traffic accidents on Friday the 6th and the number of 911 calls for household and traffic accidents on Friday the 13th.

This study has a large sample size, n= 2,800,573, which is positive when developing statistics. A large amount of data points means more accurate information. Because this study has a sample size of over 2 million phone calls, researchers can be more confident when making generalizations and applying key concepts from their findings to the total population.

The statistical procedure chosen to be implemented in this analysis is an independent 2-sample t-test. A t-test was selected because researchers want to see if there is a correlation between the two Fridays. Comparing the mean number of 911 calls on both Friday the 6th and Friday the 13th is an appropriate first step in answering this study’s research question.

In order to determine if the data is statistically significant and not just due to chance, it will be run through a p-value test with the set alpha as .05. As long as the p-value is less than or equal to .05, researchers can be confident that the data is accurate and not attributable to chance factors.

911 calls on Friday the 6th: Mean= 121,657       SD= 9672.38783

911 calls on Friday the 13th:   Mean= 132,940       SD= 9932.41125

The shape of the Friday the 6th histogram appears to be left-skewed while the Friday the 13th histogram appears to be more normally distributed (maybe slightly right-skewed). Most of the data points on the Friday the 6th histogram are on the right side of the chart, meaning 911 operators tend to see higher call volumes on these days more regularly. The Friday the 6th histogram also indicates that operators expect between 120,194-125,884 calls on these days. As for the Friday the 13th histogram, the data is more evenly spaced out and consistent. Because it has more regular points, the histogram reflects the classic bell curve shape.

Results and Inferential Data Analysis

The average 911 call rate On Friday the 13th was 132,940. This is higher than the average 911 call rate on Friday the 6th, which was 121,657. This determination was made by calculating the mean of each data set using Microsoft Excel.

The results from the independent, two-tailed, two-sample t-test rejected the null hypothesis. This is because the test statistic’s calculated value of 2.7 is greater than the critical value of 2.086. To determine whether or not these results were statistically significant, that data underwent an additional p-value test. The p-value=.0138 which is less than the set p-value of .05. This means that the results found were statistically significant and the data provide evidence for a valid effect. Based on these results, researchers can conclude that the number of 911 calls for household and traffic accidents on Friday the 6th is not equal to the number of 911 calls for household and traffic accidents on Friday the 13th. 

Conclusion

Based on the results from the data, we are able to determine that there is indeed a statistically significant difference between the average number of 911 calls on Friday the 6th and Friday the 13th. There are more 911 calls about household and traffic accidents on Friday the 13th than on Friday the 6th. One can infer that accidents occur more frequently on Friday the 13th than on any other randomly selected Friday. Taking this a step further, one could even argue that this is evidence that Friday the 13th is an inherently unlucky day, and it is not just superstition.

The data analysis procedure I used to reach my interpretation was an independent two-sample t-test. I chose this procedure because I was comparing the means of two independent groups and determining whether or not there was a correlation between them. I chose the p-value’s set alpha as .05 because I wanted a simple, standard test. Visual aids such as histograms and charts are crucial for fully understanding the research. Without these, the key findings of the study risk being misinterpreted or lost.

Other studies have developed similar results. The article Traffic Deaths and Superstition on Friday the 13th by Simo Näyhä reported, “82 men and 41 women died on Friday the 13ths, and 2,423 and 789 died, respectively, on other Fridays. Men’s deaths were not significantly higher on Friday the 13th than on other Fridays, but women’s deaths increased by a factor of 1.61, with the confidence interval well above baseline… For the deaths of men that occurred on Friday the 13th, only an estimated 5.0% (0.05 deaths per million person-days) were attributable to the day itself, while the figure was 38.0% (0.18 deaths per million person-days) for women.” (Näyhä 2110.) This study shows how there are multiple examples of Friday the 13th being an inherently unlucky day and the data can prove it. Instead of looking at 911 call patterns, this research study specifically focuses on death.

In my professional opinion, I think there is still more research to be conducted for this study. Although there is a statistically significant difference between the averages of the two Fridays, it is not enough to determine causation, only correlation. There could be a number of other variables at play that were not considered in this study but are impacting the data. The mere fact that it is Friday the 13th could be why there is an increased volume of 911 calls. People could be actively seeking out reasons to call 911 because the date is already at the forefront of their minds. 

It is my recommendation that further research must be conducted for this study before drawing an explicit conclusion. Similarly, in “Found experiments” in accident research: Report of a study of accident rates and implications for future research author A.J. Boyle explains his recommendations for future research, saying, “I would like to make it explicit that 1 can see the findings from the present research being useful only in the context of further research. I can see no immediate way of applying these findings in the industry, except in those cases where replication is possible to ensure that the findings are appropriate to particular circumstances.” (Boyle 59.) With the information I have now, I am not confident in applying this study’s findings to a real-world context just yet. Despite the studies' statistically significant findings, the only clear application of this I would be confident in would be informing emergency responders to expect a high volume of accidents and calls on any Friday the 13th. The results of this data analysis could potentially help police departments with scheduling employees, dispatchers, and even tech support.

References

American Psychological Association. (2017). Ethical principles of psychologists and code of conduct (2002, amended effective June 1, 2010, and January 1, 2017). https://www.apa.org/ethics/code/

Boyle, A. J. (1980). “Found experiments” in accident research: Report of a study of accident rates and implications for future research. Journal of Occupational Psychology, 53(1), 53–64. https://doi.org/10.1111/j.2044-8325.1980.tb00006.x 

Näyhä, S. (2002). Traffic Deaths and Superstition on Friday the 13th. American Journal of Psychiatry, 159(12), 2110–2111. https://doi.org/10.1176/appi.ajp.159.12.2110