PSY202H5 Study Guide - Summer 2018, Comprehensive Midterm Notes - Standard Deviation, Null Hypothesis, Histogram
PSY202H5
MIDTERM EXAM
STUDY GUIDE
Fall 2018
1
Lecture 1
Steps to take
• Identify the experimental design
• Determine the kind of data that are being collected
• Specify the null hypothesis in words
• Specify the research hypothesis in words
• Specify the test statistic
• Specify the statistical null hypothesis
• Specify the statistical research hypothesis
• Determine the distribution of the test statistic assuming that the null hypothesis is true
• Determine the rejection region
• Conduct the experiment and compute the value of the test statistic
• If the test statistic falls into the rejection region then reject the null hypothesis
• If the test statistic falls into the acceptance region then accept the null hypothesis
Example: Graduate Record Exams
• Students going to do post graduate work typically take a graduate record exam (GRE) in
English and in Math. The mean score of Canadian applicants to graduate school on the
math exam is 420, and the standard deviation of these scores is 30. GRE scores are
known to be unimodal and roughly symmetrical. The UTM Public Relations Officer
would like to be able to argue that graduates from our programs are better than those
from other Canadian institutions. She received permission from the 63 students from
UTM who were taking the math GRE to have access to their scores. She plans to use
these 63 scores to determine whether or not UTM students are better than the national
average.
GRE Scores
• What kind of experimental design is this?
o Single group design, one measure per subject
• What kind of data are being collected
o Continuous
• What is the null hypothesis in words?
o Utm student are typical of Canadian applicants
• What’s the research hypothesis in words?
o UTM students are better than the average Canadian applicant
• What test statistic should you use
o Since the measures are continuous, GRE scores are unimodal and roughly
symmetrical, and n is large we use the sample mean (central limit theorem holds)
• What is the statistical null hypothesis ?
o Mean= 420
• What is the statistical research hypothesis
o Mean is greater than 420
• How is the test statistic distributed when the null hypothesis is true?
o If H0 is true, then the sample mean is distributed normally with a mean of 420,
and a standard deviation of 30 / Sqrt(63) (30 divided by the square root of 63)
find more resources at oneclass.com
find more resources at oneclass.com
2
• Determine the rejection region so that the probability of a type 1 error is equal to alpha
Power
• Suppose the true mean for utm students was 425
• How likely is it that we will reject the null hypothesis?
• Assume the same value of standard deviation, standard deviation = 3.77964
• SHR: mean = 425
find more resources at oneclass.com
find more resources at oneclass.com
Document Summary
If the test statistic falls into the rejection region then reject the null hypothesis. If the test statistic falls into the acceptance region then accept the null hypothesis. Example: graduate record exams: students going to do post graduate work typically take a graduate record exam (gre) in. The mean score of canadian applicants to graduate school on the math exam is 420, and the standard deviation of these scores is 30. Gre scores are known to be unimodal and roughly symmetrical. The utm public relations officer would like to be able to argue that graduates from our programs are better than those from other canadian institutions. She received permission from the 63 students from. Utm who were taking the math gre to have access to their scores. She plans to use these 63 scores to determine whether or not utm students are better than the national average.
