This report will explore trends in Biblical baby names in the US.
The data is sourced from the “babynames” data set, an R package created by Hadley Wickham that compiles baby names in the US from 1880 to 2017. The data set is based on US Social Security Administration data, found online at:
Next, I imported this data set into R using the “readr” package. The data set included columns that were not necessary to the project, such as the birth place and surname of the Biblical figures, so I imported only the “Name” column. I named this data set “biblenames”.
Now I needed to merge the “biblenames” and “babynames” data sets.
However, I first had to rename the “Name” column in “biblenames” so that it would match the corresponding “babynames” column. The change was to simply make the “N” in “Name” lowercase using the “colnames” function.
I then merged the data sets using the “inner_join” function. I named this joined data set “merged”.
Now that I had a working data set of the Biblical names that overlapped with the “babynames” data, I decided to narrow down to the most popular Biblical names. I started by finding the top ten most popular boys’ and girls’ names from 2017, the most recent year of data.
I did this by filtering for year and gender, grouping by name, and using the summarize to find the sum of “n” (the number of babies with that name in a year).
# A tibble: 338 × 2
name total
<chr> <int>
1 Michael 138369
2 Joseph 103600
3 Jonathan 71181
4 Benjamin 68665
5 Alexander 49868
6 Jeremiah 46520
7 Nathan 44340
8 James 42696
9 John 37736
10 Ethan 37167
# ℹ 328 more rows
# A tibble: 221 × 2
name total
<chr> <int>
1 Abigail 21102
2 Mary 14286
3 Chloe 6912
4 Azariah 6867
5 Hannah 5872
6 Leah 5159
7 Anna 4520
8 Eden 4164
9 Sarah 3986
10 Naomi 3823
# ℹ 211 more rows
Visualizing Most Popular Names
Now we know the most popular Biblical boys’ and girls’ baby names in 2017. Next, I wanted to display this info on bar charts, depicting the number of babies for each name in 2017.
I started by filtering for year, gender, and the ten names I found in the previous step. I then formed the bar charts using the “geom_col” function of the “ggplot” package.
Now that I had an idea of some of the most popular boys’ and girls’ Biblical names, I wanted to track how these 20 (10 boys’ and 10 girls’ names) changed over time. I decided to track how these sets of names performed as percentage of all names in a given year over time.
I did this by first filtering for gender and the set of names. Then I created a line graph using the “geom_line” function of the “gg_plot” package. I used “year” as an x-value and “prop” (proportion of all babies born in a year) as a y-value.
After visualizing the data, there are mixed patterns in name popularity. Examining the boys’ names, the proportion of names seems to vary more early in the data, while most of the names hover around 0.5% from the start of the 21st century on. “John” stands out as it went from accounting for over 8% of all boys baby names in 1880 to less than 1% in 2017. “Michael” also stands out as the name started out with less than 0.5% of names in 1880 before rapidly increasing in the mid to late 20th century and peaking a bit below 5% around 1970.
Examining the girls’ names, there is a similar pattern where proportions tend to very more early on before leveling out at the end of the data. “Mary” seems to follow a similar pattern as “John”, starting off with over 7% of all girls names in 1880 and declining to less than 0.5% of girls names from the end of the 20th century on.
Tracking the Averages of Biblical Names Over Time
Now I wanted to track how these names as a collective performed over time. I decided to track the average of the ten boys’ and ten girls’ names, as well as an average of all 20 names together.
To do this, I created new data frames for the boys’ and girls’ names. I then took these data frames and further refined them by grouping by year and using the “summarize” function to take the mean values. I named these new data sets “boys_average” and “girls_average”.
Next, I joined the “boys_average” and “girls_average” data frames and used the “mutate” function to get a combined average by adding the two data frames together and dividing by two. I called this data frame “combined_average”.
The next step was to graph the combined averages on a line chart. This line chart depicts the average of the top ten boys’ and top ten girls’ baby names over time, as well as an average of all 20 names.
I graphed this by using the “ggplot” package with three separate “geom_line” values for the boys’ (blue), girls’ (pink), and combined (black) averages. Once again the line chart depicts the names over time with “Year” as the x-value and “Proportion” as the y-value.
ggplot() +geom_line(data = combined_average, aes(x = year, y = combined_average_count), color ="black", linewidth =1.5) +geom_line(data = boys_average, aes(x = year, y = boys_average_count), color ="blue", linewidth =0.75) +geom_line(data = girls_average, aes(x = year, y = girls_average_count), color ="pink", linewidth =0.75) +labs(title ="Biblical Baby Names Over Time (1880-2017)",x ="Year",y ="Proportion")
Visualizing the boys’, girls’, and combined names averages better revealed a general trend of decreasing popularity of Biblical names in the US. In 1880, popular Biblical names accounted for almost 2.5% of all names and have gradually declined until landing at proportion a less than 0.5%.
Additionally, the visualization demonstrates how popular Biblical names have shifted with respect to gender. In 1880, girls’ popular Biblical names made up almost 3.5% of all girls names, while boys’ Biblical names accounted for a little over 1%. Around 1950, the boys’ popularity of Biblical names surpasses the girls’. At the end of the recorded data, the boys Biblical names made up around 0.5% of boys’ names, while the girls’ accounted for around 0.2%.
Conclusion
After examining the data, my findings support the hypothesis that the popularity of Biblical baby names in the US have consistently decreased in the span of 1880 to 2017.