My group and I designed a survey to learn the texting habits amoung different age groups. We used convenience to survey our friends and acquaintances we know through school, ballgames, work, church, and Facebook or other social medias. We didnt put a boundary on age, surveying all groups from 14 and below to 51 and older.
We asked the following questions:
1. How many text messages did you send yesterday?
2. How many different people did you text yesterday?
3. Did you send a group text yesterday?
4. What is your age group?
Looking at a Categorical Variable:
The responses to the question "How many different people did you text yesterday?" are shown in the pie chart below.
It can be seen that the two age groups, 14 and below and 51 and older, are at 12%. The top age group of texters interviewed is 1520, coming in at 25%.
To see the differences in the age of texters who use group text as a way to communicate, see the bar plot below.
As you can see looking at the bar plot, those that used group text more frequently were those from age 1530 and 4150. Those that used it less were those from ages 14 and below and 3140. Those texters greater than age 51 had the same number of those that grouped texted as those who didnt.
Looking at a Numerical Variable:
The responses to the question "How many text messages did you send yesterday?" are shown in the Histogram, Boxplot, and Summary Statistics below.
Summary statistics:

As you can see in the histogram, the data is skewed to the right with the majority of those surveyed texting between 050 text in one day. An outlier is considered if it is more than 1 1/2 IQR below Q1 or above Q3. With the IQR being 62.5, this would mean anything over 177 would be an outlier, meaning there are 4 texting outliers. The boxplot graph shows a better view of the outliers, showing the two between 200300. I dont feel these are in error due to the possiblity of someone sending this many text in one day. The mean is 65.14 with the median being at 50. The median is a better choice for measuring the center since it's not affectedd by extreme values (or outliers).
Looking for a Relationship between 2 Numerical Variables
The scatterplot below shows the association between text sent in a day versus how many people texted.
As you observe the scatterplot, you see a linear form and loosely scattered. It appears that there are a few outliers, which could dramatically effect the results of the mean, standard deviation, and the nature of the distribution. These outliers have been reviewed and found to be legitimate, as there are times someone may have this many text if using them for work or a teenager who is grounded.
Simple linear regression results:
Dependent Variable: People Independent Variable: Text People = 6.2367186 + 0.020467937 Text Sample size: 100 R (correlation coefficient) = 0.23460935 Rsq = 0.055041545 Estimate of error standard deviation: 6.6123906 Parameter estimates:
Analysis of variance table for regression model:

The correlation coefficient for the paired data is .2346, as shown below. Since the absolute value of r is less than .196, we can conclude that there is not a statistically significant correlation between the number of texts made in one day and the number of people that were texted.
Already a member? Sign in.