Question

The paper "Short-Term Sleep Loss Decreases Physical Activity Under Free-Living Conditions but Does Not Increase Food Intake Under Time-Deprived Laboratory Conditions in Healthy Men" (American Journal of Clinical Nutrition [2009]: \(1476-1483\) ) describes an experiment in which 30 male volunteers were assigned at random to one of two sleep conditions. Men in the 4 -hour group slept 4 hours per night for two nights. Men in the 8-hour group slept 8 hours per night for two nights. On the day following these two nights, the men recorded food intake. The researchers reported that there was no significant difference in mean calorie intake for the two groups. In the context of this experiment, explain what it means to say that there is no significant difference in the group means. (Hint: See discussion on page 578 )

Short answer

Saying that there 'is no significant difference in the group means' in the context of this experiment means that the difference in the average calorie intake between the men who slept for 4 hours and those who slept for 8 hours was not statistically significant. This implies that the researchers could not find enough evidence to conclude that a change in sleep duration causes a change in calorie intake based on this study.

Step-by-step solution

Understanding statistical significance

Statistical significance is used to measure the certainty with which we can accept or reject the null hypothesis (which in this case would likely be that sleep deprivation has no effect on food intake). More technically, statistical significance is often measured by the p-value. If p < 0.05, we conventionally say that the difference between the groups is statistically significant. If p >= 0.05 , we say that the difference isn't significant.

Applying significance to our context

In the case of the study mentioned, saying there was 'no significant difference in the group means' means that the difference in mean calorie intake between the 4-hour sleep group and the 8-hour sleep group was not statistically significant. Understanding the context, it is concluded that the researchers could not find enough evidence to conclude that reduced sleep (4-hour sleep group) changes calorie intake compared to regular sleep (8-hour sleep group) over the period of the study.

Interpreting the implications

With this result, it's important to note that 'not significant' does not mean 'no difference'. There might be a real difference between the two conditions, but the experiment did not have enough power (usually referring to size of experiment, in this case the number of volunteers) to detect it. In other words, the data does not provide strong evidence to confidently reject the null hypothesis, even though it may not be true.