Sleep and Bed Times Correlate

¶ … sleep and bed times correlate with GPA? Form a hypothesis about the nature of the relationship between these sleep habits and GPA. Note that this hypothesis may require recoding variables to consider what is a healthy or unhealthy pattern of sleep. Students who, on average, sleep a greater number of hours during the week will have a higher GPA. Students who go to bed after midnight will have a lower GPA. The variables in question are Amount of Sleep, GPA and Bedtime.

Both Amount of Sleep and GPA are scale (interval) variables, which are continuous in nature. The Bedtime variable is a categorical, ordinal, discrete variable. This variable was broken into 4 categories, with the majority of participants selecting category 2. On average, participants in this sample received 7.2 hours of sleep each night, with a standard deviation of 2.3 hours and with responses ranging from a minimum of 4 hours to a maximum of 35 hours. The sample reported an average GPA of 3.56 with a standard deviation of .43. Overall, GPAs in this sample ranged from 1 to 4.7.

GPA has a negatively skewed distribution, while Amount of Sleep shows a somewhat negatively skewed distribution. The bedtime had a relatively even distribution between the 4 categories, with slightly more selecting the two inner categories of 2 and 3. Histogram of GPA Histogram for Hours of Sleep Hypothesis 1 was examined using a one-tailed correlation test with the two scale variables of amount of sleep and GPA. The results of the analysis indicate that there is not a significant correlation between these two variables (r = .097, p = .101).

The analysis was run as a one-tailed test due to the directionality built into the hypothesis (i.e. that greater sleep would predict a higher GPA). To double check for potential alternate directions a two-tailed correlation was also run, which was also not significant (r = .097, p = .202). The significance level used for these tests was .05. A correlation tells us how one variable functions in relation to another variable.

A positive correlation exists when one variable goes up in relation to another and a negative correlation exists when one variable goes down when another variable goes up. Correlations can be measured on a scale of 0 to 1, with 1 being a perfect correlation and 0 representing no relationship whatsoever. We then check the significance of our correlation to determine what the chances are that we would find a correlation this strong due to chance.

If we are satisfied that we would not find such a correlation solely due to chance then we conclude that the correlation is significant. The graph below demonstrates that there is no linear relationship between these two variables. Hypothesis 2 was tested using an independent samples t-test to determine whether individuals who went to bed after midnight had lower GPAs than individuals who went to bed before midnight.

The graph below shows the number of respondents who selected each of the four bedtime categories (1, 2, 3, 4), and clearly shows the mode to be category 2. In order to test this hypothesis, data was re-coded such that categories 1 and 2 became category 1 (representing those who went to bed before midnight) and categories 3 and 4 became category 2 (representing those who went to bed after midnight). An independent samples t-test was run to determine whether or not these two groups differed in their average GPA.

The results indicated that there is no significant difference between group 1 and group 2 with respect to their GPA, t (172) = .623, p =.534. Part 3 The results of the analysis for hypothesis one did not support the hypothesis. It was predicted that individuals who received greater amounts of sleep would have correspondingly higher GPAs. The results of the correlation analysis were not significant, nor did they approach significance in any way. This means that, for individuals in this sample, the amount of sleep one gets is not related to one's GPA.

Whether one sleeps for 4 hours during a week or for 30, there appears to be no relation to one's GPA. These results are surprising, as one would generally believe that receiving an adequate amount of sleep would contribute to an individual's ability to function well, and thereby get good grades. There are a few factors, which could have influenced the results of this study. It could be that the relationship between these two variables is not linear, which would therefore not allow a significant correlation to be found.

What this might mean is that if one gets either too little sleep or too much sleep, their GPA may suffer, and that what truly predicts a good GPA would be getting a specific amount of sleep, such as 8 hours per night. This would create a U. shaped curve in which performance is reduced at each end of the U. But optimized in the centre of the U. The inability of the correlation analysis to detect this kind of a relationship represents one of the limitations of this study.

Future analyses could address this issue by conducting separate analyses that allow for curvilinear relationships to be identified. To conduct the analyses in a more simple fashion, the data could be divided into separate categories, those who received less than 6 hours of sleep per night,.