Page 23 - 2023-ml-lewandowski-stats1e

Step 1: Population and Hypotheses To determine if mindfulness
meditation has an effect, we need to establish our populations and
predictions.
Population of Interest ( µµ 1 ): People who engage in mindfulness
meditation.
Comparison Population ( µµ 2 ): People who do not engage in mindful-
ness meditation.
Sample: Consists of 80 participants, half of whom complete the
mindfulness meditation intervention and half of whom are in the
control condition.
Next, we need to establish our research and null hypotheses. Our
main decision here is whether or not we want to make a directional or
nondirectional research hypothesis. Although we might believe that
mindfulness meditation will reduce stress, it may not. Potentially,
while meditating, people might start to ruminate on their problems,
leading them to experience an increase in stress. Because this outcome
would also be interesting to us, we will set up a nondirectional, two-
tailed research hypothesis.
Research Hypothesis (H 1 ): Participants in the mindfulness meditation
condition will report different stress levels from those of the partici-
pants in the control condition ( µµ ≠ µµ 2 ).
1
Null Hypothesis (H 0 ): Participants in the mindfulness and control
conditions will report the same average stress levels ( µµ = µµ 2 ).
1
Step 2: Build Comparison Distribution What would the com-
parison distribution look like if mindfulness meditation has no
effect on stress? That’s the question we need to answer to construct
our comparison distribution. As we learned in the first half of this
chapter, we need to determine the mean of the distribution of dif-
ferences between means, the pooled estimate of the population’s
variance, and the standard error of the difference (which, remember,
is the standard deviation of our distribution of differences between
means).
Let’s start with the easy one. The mean of the distribution of differ-
ences between means assumes that the null is true. If the null is correct,
then the mean for our two groups will be equal, which means that the
difference between the two means must be zero. So, our comparison
distribution has a mean of zero.
Next, we need to calculate the pooled estimate of the population’s
variance (see Figure 10.10). Because we have a large sample size (over-
all N = 80), we are not going to compute the sum of squares for each
condition. Instead, we already know that the standard deviation for
the mindfulness condition is 1.08 and the standard deviation for the
control condition is 0.93, so we can square these numbers to get their

T -TES T F OR TW O INDEPENDENT/UNRELATED S AMPLES • CHAPTER 10 365

Copyright ©2024 Worth Publishers. Distributed by Worth Publishers. Not for redistribution.

11_statsresandlife1e_24717_ch10_343_389.indd 365 29/06/23 5:17 PM