Report summary:

Don’t Drink And Drive is on, as the title suggests, drinking and driving. The data provided for the report were collects from UFHeath Biostatistics Open Learning textbook. The featured data is on the capabilities of drivers before and after two beers, this set specifically has 20 people(samples) who were surveyed before and after the consumption of two beers. The 20 people were each given the chance to drive through an obstacle course where their reaction times were recorded before drinking and after drinking. The purpose of this study was to check whether drivers are impaired after drinking two beers.

Blood Alcohal Concentration Before and After Beer

SubjectID Before After AfterMinusBefore
1 6.25 6.85 0.60
2 2.96 4.78 1.82
3 4.95 5.57 0.62
4 3.94 4.01 0.07
5 4.85 5.91 1.06
6 4.81 5.34 0.53
7 6.60 6.09 -0.51
8 5.33 5.84 0.51
9 5.15 4.19 -0.96
10 4.88 5.75 0.87
11 5.75 6.25 0.50
12 5.26 7.23 1.97
13 3.16 4.55 1.39
14 6.65 6.42 -0.23
15 5.49 5.25 -0.24
16 4.05 5.59 1.54
17 4.42 3.96 -0.46
18 4.99 5.93 0.94
19 5.01 6.03 1.02
20 4.69 3.72 -0.97

The data above is divided into 4 different columns, the first being “SubjectID”. This is just a way to differentiate between each surveyed person. The Before and After column,as suggested, is the blood alcohol concentration(BAC) of each surveyed subject before and after consumption of two beers. The fourth column “AfterMinusBefore” is the calculated difference of the BAC of each subject (After consumption - Before consumption).

Data Plotted

The plot below depicts the range in which participants BAC is measured.

The graph suggests that although not a perfect bell curve the bar-graph shows that the participants BAC lie within a range of one deviation from the center which is 0.5; showing that the data closest to the mean(0.5) is the most likely outcome when performing a similar survey or experiment. As suggested, after two beers the subject is more likely to be in a state of intoxication meaning their recorded reaction times were slower when presented with an obstacle.

As stated above this Quantile-Quantile plot also shows the same thing, all the data is contain within that grey range called the expected variability meaning that the sample distribution is similar to the theoretical distribution.

Hypothesis Testing:

Null Hypothesis: The population mean difference is equal to zero (\(H_0:\mu=0\))

Alternative Hypothesis: The population mean difference is NOT zero, meaning there is a change (\(H_a:\mu > 0\))

In words, the null hypothesis suggests that there is no significant change, while the alternative hypothesis suggests that there is a positive change after participants had two beers, this meaning an increase in Blood Alcohol Concentration.

T-test on Before and After

estimate statistic p.value parameter conf.low conf.high method alternative
0.5035 2.603147 0.0087338 19 0.1690516 Inf Paired t-test greater

Decision and Conclusion:

Decision: At a significance level of 0.05, the P-value is less than the level of significance (0.05 > 0.0174675) so the Null Hypothesis is REJECTED.

Conclusion: At the 0.05 level of significance there is sufficient evidence to conclude that there is a statistically significant difference between the after and before two beers conditions. Additionally, the alternative hypothesis being “greater” suggest that, on average, the measured condition in the after two beers participants tends to be greater than their measured condition before two beers.

Work Cited

UFHealth Biostatistics

https://bolt.mph.ufl.edu/6050-6052/unit-4b/module-13/paired-t-test/ The provided link leads to the webpage where the drunk driving data originated.