PSY 3000 Exam 2
Which of the following is the correct equation for calculating z-scores for a sample?
(Y - M) / SD
Consider the following data and calculate their z-scores based on M = 5 and SD = .5. What is the largest z-score in these data? Y = 1 Y = 3 Y = 5 Y = 6
-8
A group of researchers is studying the use of specific therapeutic modalities when working with children who experience anxiety. After conducting a randomized control trial testing a new modality, the researchers share their results but do not include an effect size. Which of the following is true? Select all that apply.
-If researchers do not present enough other specific statistics about their data, other researchers will be unable to compare their results to the new results presented by the researchers. -Other researchers can compute effect sizes if other specific statistics are also reported.
Which of the following will increase the power of the experiment?
-Increasing the effect of the independent variable -Decrease variability within groupss -Increase the sample size (n)
A group of researchers is conducting an experiment. Which of the following choices would be sufficient justification for using a one-tailed test instead of a two-tailed test?
-Some previous, similar, experiment found that M1 < M2 -You are testing a theory which specifically predicts that M1 should be less than M2
Consider the following information: μ = 40 and σ² = 16. Compute the standardized score for Y = 45. Remember, this score should keep the score of Y = 45 relative to the other scores in the population.
1.25
For this question, think about the area under the curve. What value of z gives a one-tail p-value of .05 on the upper tail? z = ?
1.65
For this question, think about the area under the curve. What values of z give a two-tail p-value of .05 (.025 on each tail). z = ± ___?
1.96
You sample 15 scores from a population that is normally distributed with μ = 230 and σ = 50. State the value of the standard error of the SDM. σM = ?
12.91
About what percentage of scores would you expect to find at least 2 standard deviations greater than the mean of the population?
2.15%
You repeatedly draw samples (n = 500) from a population that is normally distributed with μ = 230 and σ = 50. What will be the standard deviation of the sample means (assuming you draw an infinite number of samples)?
2.24
How large does n need to be to count on the SDM being normally distributed? n ≥ ____
30
Given a normal distribution, about what percentage of sample means would you expect to be +/- 2 SE from the mean of the sampling distribution?
4.70
Which of the following situations would occur, if in reality H0 is true and your analysis of your data leads you to reject H0?
A type 1 error
Which of the following situations would occur, if in reality H0 is false and your analysis of your data leads you to not reject H0?
A type 2 error
What is the probability of getting Y = 5, when M = 3 and SD = .75?
Between 0.003 and 0.01 0 ( p=0.077 )
Consider the following information for a study participant: Happiness = 90, z = 3.5 Depression = 5, z = .5 Empathy = 3.5, z = 2 Compared to other study participants, for which measure is the current participant most similar to the mean of the measure? Hint: Think about how to compare participants to one another.
Depression
Using the Oak Software, determine if the probability of obtaining a z-score of 1.98 (using a two-tailed test) is below p = .05.
It depends on rounding.
Let's say a population has a large amount of variability. How might a large amount of variability in the population impact the probability of getting a nonrepresentative sample?
Makes is more likely
What type of significance test would you use if you do not have a specific theory, previous research, or a rationale to base your hypothesis on and you simply want to know if there is a difference between population values from two groups?
Nondirectional hypothesis; two-tailed test
Given the following information, which set of data has the largest standard error? Set 1 M = 5, SD = 1.5, n = 150 Set 2 M = 5, SD = .75, n =75 Set 3 M = 5, SD = 1.25, n = 500
Set 1
What happens to the probability of getting Y = 5 when M = 3 and SD decreases (e.g., .75 to .5 or .25)?
The probability gets smaller (p becomes smaller).
A researcher wants to conduct a study to determine if there are differences in average social awareness based on children's primary out-of-school-time activity. Which of the following is a potential alternative hypothesis?
There are differences in average social awareness based on children's primary out-of-school-time activity.
Which hypothesis is the alternative?
There are differences in depression scores based on treatment modality.
Which hypothesis is the null hypothesis?
There are not differences in depression scores based on treatment modality.
A group of researchers concludes that because they did not find a significant result in their experiment there is not a difference between the treatment and control group. They have asked you to advise them about what could be going on. Which of the following statements would be an accurate statement to share with them?
They did not have enough power to detect the size difference they thought may have existed, if in fact, the difference existed in the population.
One study measured the ages of infants in weeks and another study of the very same infants used months. Would the two studies arrive at different values for the standard deviation?
Yes
Consider the following: A researcher conducts an experiment to understand if repeating back sentences after hearing them improves a person's memory of the sentence content. Given an alpha = .05, do results with an associated p = .01 suggest that the researcher had sufficient power to make a conclusion about the null hypothesis (H0 = Repeating back sentences after hearing them does not improve a person's memory of the sentence content)? Choose the answer below that correct answers this question.
Yes. A significance test with a p = .01 and an alpha = .05 suggests that the test was sufficiently powered to detect the effect because p < .05 would be considered statistically significant, thus leading to the decision to reject the null hypothesis.
'Power' is the probability that...
You will be able to reject the null hypothesis when the null hypothesis is actually false.
If H0 is true, what is the probability that your analysis of the data will lead you to incorrectly decide to reject H0?
alpha
A variable (something other than random error and the independent variable) that could account for why you get a certain result is called a _________ variable.
confounding
All statistically significant results are meaningful.
false
Raw effect sizes can be compared across studies using different measures of the same construct.
false
___-______ should be used when you have a specific theory, previous research, or a rationale to base your hypothesis on that a specific group will have a larger/smaller population value than another group.
one-tailed
If you have sufficient power to conduct a specific statistic test, you can ...
only commit a Type 1 error.
The standard deviation of the SDM is also known as the
standard error
Choose the answer that best completes the following sentence: Null hypothesis testing allows researchers...
to be unsure about making claims that a relationship between variables does not exist.
Effect sizes are important to advancing scientific knowledge.
true
Standardized effect sizes provide researchers the ability to compare the magnitude of effects across variables and across studies.
true
The size of an effect can be related to whether or not the results of an analysis are statistically signficant.
true
When a p-value is smaller than the established alpha, the only error that can be committed is a Type 1 error, which means the test did have enough power to detect an effect.
type 1 error, did have
Rejecting the null hypothesis when you have a confounding variable means...
you do not know whether the independent variable, the confounding variable or both caused the result.
When expressed as a proportion probability, will always be a value between ___ and ____.
0 and 1.00
Consider the following description of majors at a university with 40,000 students. There are 15,000 students who have not yet decided their major. There are 5,000 students who have a major in the social and behavioral sciences; 9,000 students who have a health-related major; 2,000 students who have a major in the arts; 6,000 students in a business-related major; and, 3,000 students in a physical science major. You are conducting a study at this university and want to draw a representative sample of majors. If each major has an equal chance of being selected, what is the probability you will draw a student with a social and behavioral sciences major?
0.125
Effect sizes provide a measure of _________.
magnitude
Consider the following situation: A group of researchers conducted a quasi-experimental study examining the effects of spending time outside on people's mental health. After collecting and analyzing their data, they stated they found a statistically significant small effect suggesting that spending time outside was related to mental health. The standardized effect size was very small and the associated significance test resulted in p = .053. Prior to conducting the study, the researchers set 𝛼 = .05. Based on these results, which of the following are true?
-The researchers did not have enough power to detect the size of relationship they thought they could between mental health and spending time outside if there was a relationship in the population. -The researchers committed a type 2 error -There is less than a 10% chance they incorrectly concluded that there was a relationship between spending time outside and mental health when, in fact, their was not a relationship between mental health and spending time outside.
Consider the following scenario: A group of researchers conducted a randomized control trial to determine if providing families with weekly distributions of information about recreation activities influenced average childhood psychosocial functioning during the month of December. The primary outcome variable was emotion regulation. The primary independent variable was the treatment group assignment (receive information or not receive information). The researchers hypothesized that the children of parents who received information would have higher emotion regulation scores than children of parents who did not receive information. After using a t-test to determine if there were differences in average emotion regulation scores based on the treatment assignment group. The results were t(25) = 1.64, p = .057. Based on what you have learned in this course so far, which of the following is correct?
-The researchers failed to reject the null hypothesis that there were not differences in groups because the p-value was larger than alpha = .05. -Based on an alpha = .1, the researchers concluded there was a statistically significant difference between groups.
You are conducting a study about young adult perspective-taking. You are using a measure of perspective-taking that provides scores indicating the depth of perspective-taking. The score has possible values of 1-100. You draw a sample from a population of young adults that is normally distributed with μ = 65 and σ = 9. If you sample one score from the population, what is the probability that it will have a score of at least 4 below the population mean? Consider drawing a curve while working this out.
0.33
Consider the following: You are conducting a study about social awareness development among children. Social awareness scores in a population of scores is normally distributed with a mean of μ = 350 and a standard deviation of σ = 20. What proportion of the scores are within ±17 of the mean (i.e., 333 ≤ Y ≤ 367)? Consider drawing the population and shading in the regions. Please provide your answer to four decimal places.
0.6046
Which of the following situations would occur, if in reality H0 is false and your analysis of the data leads you to reject H0?
A correct decision
Consider the following information. M1 = 50, M2 = 61, 𝛼 = .05, p = .06. If using a two-tailed test, what would you decide about the null hypothesis?
Do not reject the null hypothesis
Statistical analyses can account for poorly designed studies, biased data, and low response rates from potential study participants.
false
Which of the following statements is true about one-tailed compared to two-tailed significance tests?
increased power
Complete the sentence: One-tailed tests provide ______ two-tailed tests.
more power than
Which of the following options correctly completes the sentence: The two hypotheses (H0 and Ha) are...
mutually exclusive and exhaustive
Increasing the power in an experiment will increase the likelihood of correctly rejecting the null hypothesis...
only if the null hypothesis is actually false.
Probability is necessary in statistics to make generalizations about populationsusing data from samples .
populations, samples
Z-scores related to the sampling distribution of the mean...
provide information about how likely a sample value is to have occurred if a sample value was recalculated from a new sample drawn from the same population an infinite number of times.
Effect size is directly related to null hypothesis testing, such that smaller effects are generally more difficult to detect than larger effects.
smaller, larger
The standard deviation of the sample means is the ___________.
standard error
Consider the following situations: A two-tailed test: t(6) = 2.04, p = .0874 A one-tailed test: t(6) = 2.04, p = .0437 Which approach had more power (assuming alpha = .05 and the IV really did have an effect)?
the one-tailed test
