In: Statistics and Probability
A researcher tested a research hypothesis that people with diagnosed depression will have REDUCED level of depressive symptoms after a cognitive therapy treatment, as compared to the pre-treatment level of depressive symptoms. The cutoff t value is -1.746 for this one-tailed test. The data analysis yielded a mean change score (post-treatment minus pre-treatment) of -3. If the standard error is 2.0, what is the t statistic and what is the conclusion of the hypothesis test?
-1.50; fail to reject the null hypothesis |
-1.50; reject the null hypothesis |
-1.25; fail to reject the null hypothesis |
-1.25; reject the null hypothesis |
Flag this Question
Question 122 pts
Which of the following is an essential step in conducting a paired -samples t test?
calculating each subject's "change" (difference) score |
calculating the mean of the pre-test scores and the mean of the post-test scores |
estimating the standard deviation for the pre-test scores and the standard deviation for the post-test scores |
obtaining a national mean score on the same test |
Flag this Question
Question 132 pts
What can be said about the relationship between the significance and the effect size of a hypothesis test?
The significance of a test is not determined by the effect size alone. |
A significant test result leads to a large effect size while a non-significant test result leads to a small effect size. |
The effect size is determined by the alpha level while the significance of a test is not. |
The effect size is always the same as the test statistic, which determines the significance of a test result. |
Flag this Question
Question 142 pts
Which of the following datasets cannot be examined with a paired-samples t test?
People's annual income and the number of years of schooling they have. |
Students' SAT math scores and their siblings' SAT math scores. |
People's job satisfaction score before a promotion and their job satisfaction score after the promotion. |
People's amount of sleep and their significant others' amount of sleep, if living in the same household. |
Flag this Question
Question 152 pts
A one-sample t test is conducted with an alpha level of .05 to compare the sample mean to a general population mean of 10.
The population standard deviation is estimated to be 7.
The sample mean is 8.
The sample size is 25.
What is the t statistic?
-1.43 |
-.29 |
-7.14 |
-2 |
Flag this Question
Question 162 pts
Which of the following describes a repeated-measure design?
More than one measure is taken from each subject. |
There are usually two groups of subjects to be compared. |
The appropriate hypothesis test is typically independent-samples t-test. |
The test requires a larger sample size compared to a between-subjects design. |
Flag this Question
Question 172 pts
If I want to reduce the variance in the sampling distribution when conducting a t test, what should I do?
Increasing sample size. |
Raising the alpha level for hypothesis testing. |
Measuring the true population variances. |
Ensuring that the two samples have the same variance. |
Flag this Question
Question 182 pts
A researcher conducts a t test for dependent means (paired-samples t test) with 25 participants. The estimated population variance of the change scores is 4. What is the standard error?
.75 |
.40 |
.16 |
.80 |
Flag this Question
Question 192 pts
The estimated standard deviation of the population ______________________________.
is larger than the sample standard deviation |
is smaller than the sample standard deviation |
is the same as the sample standard deviation |
can be either larger or smaller than the calculated sample standard deviation, depending on the sample size |
Flag this Question
Question 202 pts
A researcher conducted a study on mindfulness and body mass index (BMI). She collected BMI scores from a large group of participants who had completed a mindfulness training program and then compared their scores to the national average BMI scores from the general population. What type of test should be used to see if taking the mindfulness program was beneficial for BMI scores not?
One-sample t test |
Dependent-means (paired-samples) t test |
Independent-means (Independent-samples) t test |
Pearson's correlation |
Answer to question# 1)
The T value = mean change / standard deviation
T value = -3 /2 = -1.5
.
Decision rule says: if T statistic < Critical value, we fail to reject the null hypothesis
We got T statistic -1.5 < -1.746
thus we fail to reject the null hypothesis
The first answer choice is correct
.
Answer to question# 2)
In paired difference test , the same subject is used in two different samples. The values of the same subject in the two samples is compared the difference is noted. The test statistic is calculated based on this difference value d
Hence the important step is to : calculate each subjects change score
.
Answer to questioN# 3)
Significance of the test and effect size are related terms
the significant test is bound to have large effect size as compared to the insignificant test
hence the second answer choice is correct
.
Answer to question# 4)
In this case: the annual income of a person is purely related to his number of years of eductaion, and cannot be compared to any other person, but the two variables: number of years and income do not allow to form a pair here. In case of paired test both the observations relate to the same variable
SAT score of person and his sibling can form a pair so paired test is applicable to it
Job satisfaction of one person before and after pormotion gives a paired set of data
Amount of sleep of one person and another living in same place is related
Thus answer choice A is the one for which paired dataset test cannot be used