100a quiz prep

Lakukan tugas rumah & ujian kamu dengan baik sekarang menggunakan Quizwiz!

We need to know the distribution of random variables chiefly:

all of these

A correlation coefficient is...

all of these an indicator of strength and direction of linear relation essentially a standardized covariance the average product of Z-scores

Random assignment:

all of these enhances internal validity is only relevant for experiments and not observational studies helps to be sure that treatment groups differ only on the independent variable

Psychological research always contains at least one:

all of these, just different ways of describing the same thing

In an independent group t-test, the ____ is signal and the _____ is noise:

(xbar 1-xbar2); S(xbar 1-xbar2)

Use DistrACTION (normal distribution) in Jamovi: In a Z-score distribution, what Z-scores would correspond to the lower and upper 2.5%?

+ and - 1.96

In the population the average IQ is 100 with a standard deviation of 15 (assume normal distribution). A group of researchers believe that exposures to toxins in the environment early in life can depress adult IQ. They collect a sample of 300 individuals who were exposed to environmental toxins at an early age. The mean IQ in that sample was 97. Test the hypothesis. 25. What is Cohen's D effect size?

-.20

Use the Survey Data. Conduct an ANOVA (use ANOVA command, not one-way) on PULSE as theDV and EXER as the IV. What is the effect size for the largest mean difference?

-.42

From conducting the t-test in question 19 (previous question),what is the effect size?

-.532

Use theMindsetMatters dataset, test the null that weight at time 1 (wt) is 150 in the population (two sided). What is the t-test and p-value?

-1.49, 0.140

Use DistrACTION (normal distribution) in Jamovi: In a Z-score distribution, what Z-score would correspond to the lower 5%?

-1.645

A psychologist is interested in determining whether a new treatment for depression improves (decreases) depression scores. She randomly assigns 30 subjects to the treatment and 30 subjects to the control. At the conclusion of the study she uses a t-test to evaluate whether the groups differ on a widely used depression scale that ranges between 0 and 30. The treatment group (group 1) mean is 18, the control group (group 2) mean is 22, and the standard error is 2. What is the value for the t-statistic?

-2

What is the t-test. value for this problem?

-2.66

What is the mean difference on Salary for men and women?

-21.8

In the population the average IQ is 100 with a standard deviation of 15 (assume normal distribution). A group of researchers believe that exposures to toxins in the environment early in life can depress adult IQ. They collect a sample of 300 individuals who were exposed to environmental toxins at an early age. The mean IQ in that sample was 97. Test the hypothesis. 21. What is the Z scoreof the sample mean?

-3.46

Use DistrACTION (normal distribution) in Jamovi: A normally distributed variable has a mean of 35 and a variance of 4. What percent of scores are above a score of 41.5?

.001

What is Cramer's v for this chi-square test?

.123

************* Assume you have three groups (k = 3), and the overall test F test is significant indicating that at least one group is different than another group in the population. You want to follow up by looking at all possible pairwise comparisons and there are (k * (k-1)) / 2 of them = 3. If you conducted ordinary t-tests, what would the overall family wise error rate be if each test were done at alpha = .05?

.14

Use DistrACTION (normal distribution) in Jamovi: A normally distributed variable has a mean of 35 and a variance of 4. What percent of scores are below a score of 33?

.159

To explore possible confounding variables (third variable problem), correlate Gender, Salary, andAge. What the correlation of Age withGender and Salary?

.161 (ns), .477** not significant with Gender but correlated with Salary

Use theMindsetMatters dataset, test the null that weight at BMI at time 1 and 2 are significantly different (two sided). What was the mean difference score?

.207

What is the Cramer'sv for this problem?

.239

What is the critical value for theF-test, alpha = .05, for this problem?

.323 (f test in descriptives)

A group of farmers are considering a new type of fertilizer for potatoes. We know that the standard yield in the population is µ = 20, with σ=3 (bushels per plot), and normal in the population. The farmers test the new fertilize on N = 16 plots of land, and find the mean is 21.4. They are interested in knowing whether the fertilizer "makes any difference." 12. What is Cohen's D effect size?

.46

A researcher is studying a new treatment for depression using a design involving a treatment and a control group. The treatment group depression mean is 20 and the control group's mean is 23 (lower scores are better). The standard deviation is 6. What is the numeric value of Cohen's d effect size?

.5

Use DistrACTION (normal distribution) in Jamovi: In a standard normally distributed variable, what percentage of the distribution is within + and - 1 standard deviation?

.683

For these problems use the HappyPlanetdata. What is the correlation between GDPperCapita and Happiness?

.698

Use DistrACTION (normal distribution) in Jamovi: A normally distributed variable has a mean of 35 and a variance of 4. What percent of scores are between 31 and 39?

.954

Use the MindsetMatters dataset, test the null that weight(wt) is significantly different between the two conditions (Cond). What was the effect size?

0.063

A psychologist is interested in determining whether a new online pain management program improves (reduces) pain scores for its participants. He assigns 20 subjects to the treatment condition and 20 to the control, and he measures pain intensity on a 1-10 scale. The treatment and control means are 7 and 5, respectively. Which of the following standard deviation values would produce the largest standardized mean difference (i.e., Cohen's d effect size)?

1

According to the Ptukey, how many post-hoc comparisons are significant (p <= .05)?

1

An industrial organizational psychologist uses a 7-point rating scale to estimate the mean job satisfaction in a particular industry (1 = very dissatisfied, 4 = neutral, 7 = very satisfied). Suppose the researcher wants to test the hypothesis that true mean is 4 (neutral). Which of the following sample means is most "absurd" or "rare" if the hypothesis is true? Check all that apply.

1, 7

A group of farmers are considering a new type of fertilizer for potatoes. We know that the standard yield in the population is µ = 20, with σ=3 (bushels per plot), and normal in the population. The farmers test the new fertilize on N = 16 plots of land, and find the mean is 21.4. They are interested in knowing whether the fertilizer "makes any difference." 8. What is the Z scoreof the sample mean?

1.86

In a sample, the mean is 30 and standard deviation is6. Given a sample of size 10, what is the standard error? Round your answer to 2 decimal points.

1.90

Assume there are five groups (k = 5) being compared in ANOVA and the overall F is significant. If you wanted to do all pairwise comparisons, how many would there be?

10

See the survey data below. Which number is a marginal frequency?

11

Under the null hypothesis, what is the expected frequency for Low Achieving and NoAssistance?

121.8

For these problems use the SalaryGender data. For the Gender variable, 0 = men and 1 = women. What is the varianceof Salary overall?

1783

Use the Math Achievement Data. Conduct a chi-square test of independence and associated analyses for AchieveGroup and LunchAsst. How many degrees of freedom are in that chi-square test?

2

Which of the following is based on a within-subjects analysis?

2 sample dependent t

If instead there were five groups and 10 rats per group, the critical value, alpha= .05, would be?

2.57

A group of farmers are considering a new type of fertilizer for potatoes. We know that the standard yield in the population is µ = 20, with σ=3 (bushels per plot), and normal in the population. The farmers test the new fertilize on N = 16 plots of land, and find the mean is 21.4. They are interested in knowing whether the fertilizer "makes any difference." 95% CI:

21.4 + and - 1.96 (.75)

Math Achievement dataset: Add 15 and divide by 2 from each Standardized Reading score what is the new mean, variance and standard deviation? Verify by hand that its right.

272, 51.9

Accordingto Tukey, how many pairwise comparisons are significant, p < .05?

3

How many levels of exercise (EXER) are there?

3

How many pairwise comparisons are there?

6. (k * (k-1)) / 2

Use DistrACTION (normal distribution) in Jamovi: A normally distributed variable has a mean of 35 and a variance of 4. What scores cuts off the lower and upper 5%?

31.71, 38.29

Use DistrACTION (normal distribution) in Jamovi: A normally distributed variable has a mean of 35 and a variance of 4. What scores cuts off the upper 1%?

39.653

For these problems use the USStates data. This is an examination of the differences between states that voted for McCain versus Obama. The grouping variable is ObamaMcCain. The researcher is interested in whether the Household Income dependent variable is different across states that voted for McCain versus Obama. What is the overall mean and standard deviation of Household Income?

48,051, 7,502

What is the expected frequency for female heavy smokersunder the null:

5.52

Match Achievement dataset: Subtract 23 from each Standardized Reading score what is the new mean, variance and standard deviation? Verify by hand that its right.

506, 104

What is the mean Household Income for Obama and McCain states, respectively?

51,786; 43,298

Use DistrACTION (normal distribution) in Jamovi: A normally distributed variable has a mean of 58 and a variance of 16. A person has a Z-score of -1.63, what is their raw score?

51.48

Match Achievement dataset: What is the mean and standard deviation of Standardized Reading (StanRead)?

529, 104

Use DistrACTION (normal distribution) in Jamovi: A normally distributed variable has a mean of 58 and a variance of 16. A person has a Z-score of 0.50, what is their raw score?

60

Use the Survey Data. What range of PULSE values cut off the middle 50%?

66 to 80

A chi-square problemwith three levels of the row variable and four levels of the column variable willhave:

6df

An industrial organizational psychologist uses a 7-point rating scale to estimate the mean job satisfaction in a particular industry (1 = very dissatisfied ... 4 = neutral ... 7 = very satisfied). She has reason to believe that the particular industry she is studying has better satisfaction than most. To test this prediction, she uses a null hypothesis that says the true satisfaction mean is 4 (neutral). Which of the following sample means would be most likely to discredit the null hypothesis?

7

Use the Survey Data. What is the 50th percentile for PULSE?

72.5

In the plot (Happiness on X axis), what data point appears to be the largest outlier?

8, 60,000

Conduct an ANOVA of the RATS data. What was the estimated variance within groups?

8.47

which of the following are joint frequencies

89, 5, 9

For these problems use the LDLbeforeafterdata. Conduct a dependent samplest-test and what is the t-statistic and df?

9.67, 11

In the population the average IQ is 100 with a standard deviation of 15 (assume normal distribution). A group of researchers believe that exposures to toxins in the environment early in life can depress adult IQ. They collect a sample of 300 individuals who were exposed to environmental toxins at an early age. The mean IQ in that sample was 97. Test the hypothesis. 26. What is the 95%confidence interval?

97 + and - 1.96 (.866)

Use the MindsetMatters dataset, test the null that weight atBMI at time 1 and 2 are significantly different (two sided). What is the t-test value?

< .001

Which of the following best describes the construction of the F statistic?

A fraction reflecting variation explained by the independent variable relative to unexplained (error) variation

Which of the following best describes the p-value?

A measure of how rare the data (the sample estimate) are if the null hypothesis is true

Which of the following variables is measured on a nominal scale?

A psychological diagnosis (antisocial personality disorder, schizophrenia, bipolar disorder)

In histograms, the height of the bars reflects __________ frequency could be any of these density probability of score occurring in sample

frequency, density, probability of score occurring in sample

Which of the following best characterizes the difference between an independent t-test and an ANOVA analysis?

ANOVA can accommodate 2 or more independent variable groups, the t-test can compare only 2 groups

A social psychology study administers questionnaires to 150 students from a large public university that ask about behaviors and social norms around texting. What is the likely population for the study?

All possible college-age individuals in the US

Suppose a researcher conducts an ANOVA analysis that compares three different treatments for depression: medication, cognitive, behavioral therapy, and a control condition. What is the null hypothesis for the ANOVA analysis?

All three groups have identical mean depression levels

Suppose a researcher conducts an ANOVA analysis that compares three different treatments for depression: medication, cognitive behavioral therapy, and a control condition. The p-value for the F statistic is .25. Which of the following statements is true?

All three groups have identical means, within sampling error

Perform the t-test on heavy drinkers and non white dependent variables, alpha .05, two tailed.

heavy drinking significant, non-white not significant

Which of the following is NOT an example of a within-subjects design?

An educational researcher compares the change in test scores for a sample of students between 7th and 8th grade c.Students in a social psychology experiment rate the competency of female professors dressed in business attire, then they rate the competency of female professors dressed in casual attire d.Husband and wife pairs are compared to see which gender reports the highest level of marital satisfaction **********To examine test bias, an educational researcher compares test scores between Hispanics and Caucasians

A clinical psychologist is evaluating a new treatment for depression. Which of the following is consistent with the procedure for null hypothesis significance testing?

Assume that the treatment has no effect, then refute or contradict that assumption with a sample that shows a marked reduction in depression scores

Suppose a researcher conducts an ANOVA analysis that compares three different treatments for depression: medication, cognitive behavioral therapy, and a control condition. What evidence is needed from the data in order to refute the null hypothesis (i.e., make the null look "absurd").

At least one of the three groups has a different mean depression level than the others

Suppose a researcher conducts an ANOVA analysis that compares three different treatments for depression: medication, cognitive behavioral therapy, and a control condition. The p-value for the F statistic is .04. Which of the following statements is true?

At least one pair of treatment conditions has different means

Why is the average of the sum of squared differences between each score and the mean such a poor indicator of spread of scores?

Because its always zero

If people tend to score above the mean on X, tend to score below the mean on Y, then the correlation will

Both be negative AND have a large negative covariance

In a chi-square test:

Both the chi-square distribution under the null is usually positively skewed and as degrees of freedom increases, larger values of chi-square are needed to reject

A psychologist is interested in determining whether a new online pain management program improves (reduces) pain scores for its participants. A group of pain patients are randomly assigned to participate in either the online program or a control group. At the end of the study the researcher administered a widely used pain level scale ranging from 1-10. The standard error for the analysis is .50. Which of the following interpretations is correct regarding the standard error?

Due to estimation error (random chance) alone, we would expect a .50 mean difference on a 10-point scale

A clinical psychologist is studying the association between education level and smoking. She collects a measure of smoking frequency from a group of participants with a high school or lower education, and she collects the same measure from a group of college graduates. Because the two measurements are obtained from different samples or people, she uses an independent-samples t test to analyze the data. College students smoked three fewer cigarettes, on average, and the t test gave a probability value of .01 (1%). Which of the following interpretations is correct regarding these results?

College educated individuals smoke less than individuals with less education

Suppose a researcher conducts an ANOVA analysis that compares three different treatments for depression: medication, cognitive behavioral therapy, and a control condition. The probability value for the F statistic is p = .01, which is statistically significant. Which of the following steps should the researcher take next?

Conduct t-tests that compare whether every possible pair of groups differs in their mean depression level

Which of the following is true

Converting all scores to Z scores makes the mean be 0 and variance be 1 always

A social psychology study administers questionnaires to 150 students from a large public university that ask about behaviors and social norms around texting. One of the questions asks whether it is appropriate to carry on a text conversation while on a date. The question uses a Likert scale with options 1 = "strongly disagree", 2 = "disagree", 3= "neither agree nor disagree", 4 = "agree", and 5 = "strongly agree". Which of the following is true of this variable? Check all that apply.

For this to be an interval scale, the amount of agreement between "strongly disagree" and "disagree" must be the same amount between "agree" and "strongly agree" In practice, this type of scale is often close enough to interval that researchers treat it like any other numeric scale

An appropriate null hypothesis for an independent group t-test is:

H0: μ1 = μ2 H0: μ1 ≤ μ2 H0: μ1≥ μ2 All of these

Which of the following variables is measured on an ordinal scale?

Highest level of education (high school, some college, college, post BA)

A clinical psychologist is evaluating a new treatment for depression. The null hypothesis is that the mean is 18 (the mean of a national norm group with mild depression). Following two months of treatment, his sample of 50 participants has a mean of 17 (an improvement of one point), the p-value for which is .10. Which of the following interpretations is true concerning the p-value?

If he took samples of 50 participants over and over again, he would expect about 1 out of 10 to give an estimate that is a point or more below the hypothesized mean of 18

A psychologist is interested in determining whether a new online pain management program improves (reduces) pain scores for its participants. A group of pain patients are randomly assigned to participate in either the online program or a control group. At the end of the study the researcher administered a widely used pain level scale ranging from 1-10. What is the null hypothesis for the study?

If the experiment were conducted on the entire population, the difference in the treatment and control group means would be zero

A group of farmers are considering a new type of fertilizer for potatoes. We know that the standard yield in the population is µ = 20, with σ=3 (bushels per plot), and normal in the population. The farmers test the new fertilize on N = 16 plots of land, and find the mean is 21.4. They are interested in knowing whether the fertilizer "makes any difference." 5. The alpha rate is set at .05, thus:

If the null hypothesis is correct, then 5% of the time you will reject the null by chance you need to find critical values of Z that cut off 2.5% in each tail the Type 1 error rate is 5% all of these

An exercise physiologist is studying energy exertion from playing video games. Participants first play Wii bowling for 15 minutes, during which researchers measure calories burned. After a period of rest, participants then play Will tennis. The average change in energy expenditure scores was 12 points, and a paired-samples t test gave a two-tailed probability value of .09 (9%). Which of the following interpretations is correct regarding these results?

If there is truly no difference in the population, a change of 12 points or more would occur in 9% of all random samples from such a population

following is most accurate about a 95% confidence interval:

If we repeated the study many times, 95% of the time the computed confidence interval will contain the population parameter

Perform the Tukey post hoc and Cohen's d, for each pairwise comparison. What is the largest effect?

Impov- Superen

If the null hypothesis is correct, then 5% of the time you will reject the null by chance the Type 1 error rate is 5% you need to find critical values of Z that cut off 2.5% in each tail all of the above

In the population the average IQ is 100 with a standard deviation of 15 (assume normal distribution). A group of researchers believe that exposures to toxins in the environment early in life can depress adult IQ. They collect a sample of 300 individuals who were exposed to environmental toxins at an early age. The mean IQ in that sample was 97. Test the hypothesis. 18. The alpha rate is set at .05, thus:

A national survey of smoking behavior asks respondents to report their family's total household income to the nearest dollar. What is the level of measurement for the income variable?

Interval (i.e., numeric, continuous)

A study examining the use of and engagement with Facebook asked participants to report their exact number of friends. Which level of measurement describes this variable?

Interval (i.e., numeric, continuous)

Math Achievement dataset: What type of variable is math efficacy?

Interval - Ratio

Major league baseball standings are considered:

Interval/ratio if based on win percentage, ordinal if rank standing

A psychologist is interested in determining whether a new online pain management program improves (reduces) pain scores for its participants. At the end of the study the researcher administered a widely used pain level scale to the intervention participants and a control group that received generic reading materials. Which of the following sets of means provides the strongest evidence against the null hypothesis?

Intervention mean = 7, control mean = 8.50

Which of the following is NOT an example of a within-subjects design that would yield data appropriate for a paired-samples t-test?

Males and females are compared to see whether they differ in their depression levels

The degrees of freedom within is?

N- K

The degrees of freedom total is?

N-1

In a one-sample t-test the df are __________ but in a dependent samples t-test the df are:

N-1, # of pairs -1

Which of the following variables is measured on an interval scale?

Number of days per month having at least one alcoholic drink

A psychologist is interested in determining whether a new online pain management program improves (reduces) pain scores for its participants. He assigns 20 subjects to the treatment condition and 20 to the control, and he measures pain intensity on a 1-10 scale. At the end of the study the researcher finds an improvement, the standardized mean difference effect size of which is .30. Which of the following describes the meaning of this effect size value?

Pain scores improved by about a third of a standard deviation

Which of the following is an example of a within-subjects design that would yield data that could be analyzed with a paired-samples t-test?

Pretest and posttest scores are obtained from a group of people prior to and after they participate in a smoking cessation intervention

The eta squared is .705 which is huge;70% of the variance in learning is "explained" by environment. What is eta squared?

SSBetween / SS total

Suppose a researcher conducts an ANOVA analysis that compares three different treatments for depression: medication, cognitive behavioral therapy, and a control condition. The probability value for the F statistic is p = .25, which is non-significant. Which of the following steps should the researcher take next?

Stop, no further analysis is required

A clinical researcher measures depression at the beginning of a study, then she measures it a second time after participants have completed three months of therapy. Which of the following describes a difference or change scores in this context?

The amount by which each person's score changes from the beginning to the end of the study

In a chi-squaregoodness-of-fit test:

The categories are mutually exclusive and exhaustive

An educational psychologist is interested in whether test scores improve between 7th and 8th grade. She recruits a sample of 100 students and finds test score averages of 50 and 52 in 7th and 8th grade, respectively. The standard error for the paired-samples t-statistic is 2.25. Which of the following conclusions is true regarding the change in scores?

The change in scores from 7th to 8th grade is about what you would expect due to sampling error (random chance) alone

A clinical psychologist is studying the progression of alcohol use in a teenage population. She collects a measure of alcohol use from the same group of teens at ages 16 and 18. Because the two measurements are obtained from the same people, she uses a paired-samples t-test to analyze the data. The null hypothesis predicts no change in alcohol use. The sample data are as follows: age 16 mean = 6, age 18 mean = 6.25, p = .01. Based on the probability value, which is the conclusion about the null hypothesis?

The data refute (i.e., are inconsistent with) the null

The value that is commonly considered as"error", "noise" or "chance variation" in ANOVA is:

The difference between each score and it's group mean squared.

An educational psychologist is interested in whether math test scores improve between 7th and 8th grade. She recruits a sample of 100 students and uses a paired-samples t-test to analyze the data. Which of the following is a valid null hypothesis for the study?

The difference between the average 7th and 8th grade math scores is 0 in the population

A psychologist is interested in determining whether a new treatment for depression improves (decreases) depression scores. She randomly assigns 30 subjects to the treatment and 30 subjects to the control. At the conclusion of the study she uses an independent t-test to evaluate whether the groups differ on a widely used depression scale that ranges between 0 and 30. The treatment group mean is 18 and the control group mean is 22. What is the null hypothesis for the analysis?

The difference between the population means is zero

A psychologist is interested in determining whether a new treatment for depression improves (decreases) depression scores. To evaluate the treatment, she randomly assigns 30 subjects to the treatment and 30 subjects to the control, and she then performs an independent t-test. What population parameter is the target/focus of the hypothesis?

The difference between the treatment and control group means

Fill in the blank with the statement that is true about the p-value. The p-value gets smaller as ______________.

The estimate from the sample data gets farther from the mean predicted by the null hypothesis (i.e., becomes more "absurd")

Linear transformations, such as adding or subtracting a constant, or dividing or multiplying by a constant

all are true

Researchers are interested in determining whether a smoking cessation intervention reduces smoking frequency. They assign 50 subjects to the treatment condition and 50 to the control, and measure smoking frequency on a 1-5 scale. At the end of the study the researcher finds that the treatment subjects improved, with a standardized mean difference effect size of .51. Which of the following interpretations is correct?

The mean difference between the treatment and control group is equivalent to about a half a standard deviation

A clinical psychologist is evaluating a new treatment for depression. The null hypothesis is that the mean is 18 (the mean of a national norm group with mild depression). Following two months of treatment, his sample of 50 participants has a mean of 17 (an improvement of one point), the p-value for which is .10. Which of the following conclusions is warranted?

The new treatment is ineffective at reducing depression (the data are consistent with the null)

The null hypothesis in a goodness-of-fit test is:

The observed frequencies are a random sample from a null hypothesis distribution

When computing the standard deviation or variance from a sample of data, we compute each person's distance from the mean, then we average those distances by dividing by the number of scores MINUS ONE. What is the reason for this operation instead of just averaging by dividing by the number of scores?

The resulting standard deviation or variance from the data is a better guess about the spread in the entire population

A clinical psychologist is trying to estimate the average number of alcoholic drinks per week in the population of college students. She collects data from a sample of 20 participants and finds that the mean is 5 with a standard error of .20. Which of the following is true about the standard error value?

The sample mean based on N = 20 students should differ from the true population mean by .20, on average

An industrial organizational psychologist uses a 7-point rating scale to estimate the mean job satisfaction in a particular industry (1 = very dissatisfied ... 4 = neutral ... 7 = very satisfied). She has reason to believe that the particular industry she is studying could have better or worse satisfaction than most. To test this prediction, she uses a null hypothesis that says the true satisfaction mean is 4 (neutral). The TWO-TAILED p-value for her sample mean is .04 (4%). Which of the following conclusions is true?

The sample mean is much higher OR much lower than 4

An industrial organizational psychologist uses a 7-point rating scale to estimate the mean job satisfaction in a particular industry (1 = very dissatisfied ... 4 = neutral ... 7 = very satisfied). She has reason to believe that the particular industry she is studying has better satisfaction than most. To test this prediction, she uses a null hypothesis that says the true satisfaction mean is 4 (neutral). The ONE-TAILED p-value for her sample mean is .04 (4%). Which of the following conclusions is true?

The sample mean is much higher than 4

The mean difference and Cohen's D is larger for Freq vs None, than Freq vs Some, yet it's the Freq vs. Some that is significant? Why?

The standard error for the comparison is smaller, thus the relative mean difference larger

A psychologist is interested in determining whether a new online pain management program improves (reduces) pain scores for its participants. He assigns 20 subjects to the treatment condition and 20 to the control, and he measures pain intensity on a 1-10 scale. The treatment and control means are 7 and 5, respectively, and the standard deviation is 1. What happens to the standardized mean difference (Cohen's d effect size) if mean values stay the same but the standard deviation increased to 2?

The standardized mean difference would decrease

The variance is

The sum of squared differences between each score and the mean divided by degrees of freedom

Suppose a researcher conducts an ANOVA analysis that compares three different treatments for depression: medication, cognitive behavioral therapy, and a control condition. The ANOVA analysis indicates that the between-group variability (i.e., variation due to the model, or the independent variable) is exactly zero. Which of the following must be true in this case?

The three groups have identical mean depression scores

A researcher is studying a new treatment for depression using a design involving a treatment and a control group. She reports that the Cohen's d effect size is .50. Which of the following interpretations is consistent with this finding?

The treatment and control group averages differ by an amount equal to one half of a standard deviation unit

A psychologist studying chronic pain reports that his new treatment protocol produced a "non significant" difference between the treatment and control group. Which of the following conclusions is most likely true?

The treatment and control means were very similar

A psychologist is interested in determining whether a new treatment for depression impacts depression scores. She recruits 30 subjects and measures their depression at baseline then again following the intervention. At the conclusion of the study she uses a paired-samples t-test to evaluate whether scores change. The paired-samples t-statistic is 1.80 with a two-tailed probability of .20. Which of the following conclusions is true regarding the treatment?

The treatment changed scores in a manner that is consistent with random chance

A psychologist is interested in determining whether a new online pain management program improves (reduces) pain scores for its participants. She randomly assigns 50 subjects to the online intervention and 50 subjects to a waitlist control. At the conclusion of the study she uses a t-test to evaluate whether the groups differ. The independent t-statistic is 2.50, and its two-tailed probability value is .0141. Which of the following conclusions is true regarding the treatment?

The treatment improves scores beyond what is expected due to random chance (estimation error)

A psychologist is interested in determining whether a new treatment for depression impacts depression scores. She randomly assigns 30 subjects to the treatment and 30 subjects to the control. At the conclusion of the study she uses a t-test to evaluate whether the groups differ. The independent t-statistic is 2.30, and its two-tailed probability is .0251. Which of the following conclusions is true regarding the treatment?

The treatment improves scores beyond what is expected due to random chance (estimation error), The treatment produced a large decrease in depression relative to the control group

What are the meansquares between and within estimation.

The variance of scores on the dependent variable in the population

A psychologist is interested in whether participation in a smoking cessation intervention reduces smoking. She recruits a sample of 50 participants and has them rate their smoking frequency on a 1-10 scale. The pre-test and post-test means are 7 and 5, respectively, for a mean change of -2. The 95% confidence interval for the mean change is -3.5 to -.5. Which of the following is true?

There is a 95% probability that the interval from -3.5 to -.5 contains the true mean change in the population

An educational psychologist is interested in whether test scores improve between 7th and 8th grade. She recruits a sample of 100 students and finds test score averages of 50 and 53 in 7th and 8th grade, respectively, for an average change of 3. The 95% confidence interval for the mean change is -1 to 7. Which of the following is true?

There is a high probability that scores did not change if the study was performed on the entire population

Which of the following research scenarios would require an INDEPENDENT t-test?

To examine test bias, an educational researcher compares test scores between males and females

A psychologist is interested in determining whether a new online pain management program improves (reduces) pain scores for its participants. He assigns 20 subjects to the treatment condition and 20 to the control, and he measures pain intensity on a 1-10 scale (low pain ratings are good, high pain ratings are bad). At the end of the study the researcher finds an improvement, the standardized mean difference (i.e., Cohen's d) effect size of which is 1.00. Which of the following sets of descriptive statistics produced this effect size?

Treatment mean = 4 (SD = 2), control mean = 6 (SD = 2)

Which of the following describes the relationship between a sample and a population?

We analyze data from a sample of participants, with the goal of learning something about an entire population potential participants

A group of farmers are considering a new type of fertilizer for potatoes. We know that the standard yield in the population is µ = 20, with σ=3 (bushels per plot), and normal in the population. The farmers test the new fertilize on N = 16 plots of land, and find the mean is 21.4. They are interested in knowing whether the fertilizer "makes any difference." 6. If the alpha rate is.05, two-tailed, what critical values would you need?

Z = plus and minus 1.96

Beta-carotene supplements have been thought to protect against cancer. A study published in the Journal of the National Cancer Institute randomly assigned 200 adults to receive a beta-carotene supplement or a placebo, and their health was studied over their lifetime. Who is the likely population for this study?

all possible adults in us

The total sum of squares is equal to the between sum of squares plus the within sum of squares.

always

Use DistrACTION (normal distribution) in Jamovi: What percentage of a distribution is above the median?

always 50%

populations

are defined by the researcher based on their research question can be so large that it is impossible to collect data on all members can be naturally occurring units such as "Americans", "College age Men", "people with a disease" and so on. all of these

Chi-square tests, as implemented in this class:

are one tailed only, looking for high values to reject

n a chi-square test,categories of a variable are:

assumed mutually exclusive and exhaustive

If I wanted to display the distribution of a continuous outcome (IQ score) as a function of a qualitative independent variable (facebook member vs. not facebook member), I would select which of the following ______________? (Note: more than one may be correct)

bar plot

If I wanted to display the distribution of a nominal variable, I could select which of the following

bar plot

The __________ reflects ordinary sampling variance and variance due to treatment group mean differences:

between group mean squares

A psychologist is studying marital satisfaction, and she wants to determine whether husbands OR wives report higher satisfaction. She recruits a sample of 100 husband-wife pairs and measures marital satisfaction on a 1-10 scale. If she uses a paired-samples t-test to analyze the data, which of the following sets of means provides the MOST evidence against the null hypothesis?

biggest difference

The pooled variance:

both is a weighted average of the variance within each group and is a better estimate of the population variance than either group variance

Standard errordecreases as function of:

both smaller S and larger N

For two events A and B, A and Bare independent if P(A|B) = P(A), which means...

both the probability of A occurring is the same as theprobability of A occurring given that B has already occurred and it's the same as saying, P(A and B) = P(A) x P(B)

Which type of plot(s) displays the interquartile range?

box plot

The F-distribution:

can only be positive

In an ANOVA analyses, the independents variables are _____ and the dependent variable is _____.

categorical, continuous

In two-sample independent t-tests, the independent variable is ________ and the dependent variable is __________?

categorical, continuous

small between group variability

close bell curves (size doesn't matter)

A social psychology study administers questionnaires to 150 students from a large public university that ask about behaviors and social norms around texting. The 150 students constitute what group?

convenience sample

In a chi-square testor independence, the measure of "effect size" is:

cramers v

A clinical psychologist is studying the progression of alcohol use in a teenage population. She collects a measure of alcohol use from the same group of teens at ages 16 and 18. Because the two measurements are obtained from the same people, she uses a paired-samples t-test to analyze the data. The null hypothesis predicts no change in alcohol use. The sample means are as follows: age 17 mean = 6, age 18 mean = 6.25, p = .15. Based on the probability value, which is the conclusion about the null hypothesis?

data support the null

In the population the average IQ is 100 with a standard deviation of 15 (assume normal distribution). A group of researchers believe that exposures to toxins in the environment early in life can depress adult IQ. They collect a sample of 300 individuals who were exposed to environmental toxins at an early age. The mean IQ in that sample was 97. Test the hypothesis. 14. Is this a directional or non-directionalresearch hypothesis?

directional

Theeffect size in ANOVA is:

eta squared the ratio of sum of squares betweento sum of squares total

In the population the average IQ is 100 with a standard deviation of 15 (assume normal distribution). A group of researchers believe that exposures to toxins in the environment early in life can depress adult IQ. They collect a sample of 300 individuals who were exposed to environmental toxins at an early age. The mean IQ in that sample was 97. Test the hypothesis. 24. If this was a one tailed test, positive direction, would youreject or fail to reject?

fail to reject (because the effect was in the opposite direction)

All else being equal, the standard error in a dependent t-test will be larger than an independent groups t-test, but the degrees of freedom will be smaller:

false

In an independent group t-test, as degrees of freedom increases, it is harder to reject the null hypothesis because the standard error gets larger.

false

The "independent" in the independent groups t-test means pretty much the same thing as statistical independence between groups just like a chi-square test.

false

When there are more groups in an ANOVA, critical values in F, alpha = .05, increase.

false

Verify that the 95%confidence interval goes from .602 to .774. Is that symmetric around the estimate?

false not symetric

In naturalistic studies, high alcohol (vs low) is associated with high heart disease rates, but:

high alcohol use individuals are different are different than low alcohol individuals on possibly many variables beside alcohol use all of these you may have to lose external validity and do an experimental study on rats to evaluate the impact of alcohol use on disease you can't draw causal contributions because of confounding variables

When research participants are randomly assigned into two groups for purpose of statistical analyses, the appropriate statistical method is:

independent groups t-test, df = N1 + N 2 - 2

A researcher isconducting a clinical trial randomly assigning individuals to treatment andcontrol. This will require a:

independent samples t-test

random sampling

is critical to both external and internal validity

In a normal distribution the value + or - 1.96 is important because

it is a range of values in a Z distribution that cuts of 95% of cases in the middle it provides a critical value to multiple by to compute a 95% confidence interval it is the point on the Z-score scale cutting off 2.5% on both tails

In an independent samples t-test, the ordinary Cohen's effect size is controversial because:

it is not controversial at all

The Cohen's d in the dependent samples t-test is often described as sketchy and difficult to interpret. The chief reason is:

it uses the standard deviation of difference scores in the denominator

In the population the average IQ is 100 with a standard deviation of 15 (assume normal distribution). A group of researchers believe that exposures to toxins in the environment early in life can depress adult IQ. They collect a sample of 300 individuals who were exposed to environmental toxins at an early age. The mean IQ in that sample was 97. Test the hypothesis. 17. What is the samplingdistribution of the mean?

mean = 100, standard error = 0.866

Suppose a research team at UCLA wants to estimate the average depression level in the general population. To do so, they recruit a random sample of 300 participants from throughout the city. What is the estimate for this scenario?

mean depression score for 300 participants

µ and σ are population values of the mean and standard deviation, pronounced:

mu and sigma

To find the expected frequency under the null hypothesis ina chi-square test of independence:

multiply the two marginal frequencies and divide by N

Chi-square valueswill tend to be negative when:

never, chi-square cannot be negative

Which cell is contributing the most to the overall chi-square?

no assistance and low achieving

Can voting be considered "causal"?

no its not an experiment

The research design in which "no causal conclusion, correlation statement only for the sample" is:

no random sampling, no random assignment

Beta-carotene supplements have been thought to protect against cancer. A study published in the Journal of the National Cancer Institute randomly assigned 200 adults to receive a beta-carotene supplement or a placebo, and their health was studied over their lifetime. Which level of measurement describes the treatment assignment variable (beta-carotene supplement vs. placebo)?

nominal

Beta-carotene supplements have been thought to protect against cancer. A study published in the Journal of the National Cancer Institute randomly assigned women to receive a beta-carotene supplement or a placebo, and their health was studied over their lifetime. The outcome variable classified women according to whether cancer occurred or not. Which level of measurement describes the outcome variable (cancer vs. no cancer)?

nominal

Now conduct a one-sample t-test using a null of 0, on the difference variable. What has changed relative to the dependent samples t-test in question 14 (the previous question)?

none changed

In a chi-square testof independence, the degrees of freedom are:

number of rows minus one times number of columns minus one

For what test(s) is the null not equal to 0?

one sample t test

An industrial organizational psychologist working for a large company summarizes data from employee performance ratings that range from "underperforming", "average", "above average", and "superior". What level of measurement does the performance rating variable use?

ordinal

A depression questionnaire asks the question, "I felt that I had nothing to look forward to." Respondents answered on a scale ranging from 1 (Strongly disagree) to 5 (Strongly agree). Which level of measurement describes this variable?

ordinal, quasi-interval

Assume you have four groups (k = 4), and the overall test F test is significant indicating that at least one group is different than another group in the population. You want to follow up by looking at all possible pairwise comparisons and there are (k * (k-1)) / 2 of them = 6. Why not just do six ordinary independent t-tests?

overall family wise type I error rate would be inflated

An industrial organizational psychologist uses a 7-point rating scale to estimate the mean job satisfaction in a particular industry (1 = very dissatisfied ... 4 = neutral ... 7 = very satisfied). She has reason to believe that the particular industry she is studying could have better satisfaction than most. To test this prediction, she uses a null hypothesis that says the true satisfaction mean is 4 (neutral). Which of the following p-values is consistent with the finding that the estimate from her data discredits the null hypothesis?

p=.01

Eta squared is one overall effect size in ANOVA, while_________ is a very similar "percent of variance explained" between two continuous variables.

r squared

Time, weight, and height are all examples of:

ratio variables

the standard error

refers to how "wrong" you will be, on average, in guessing the population mean from the sample mean

A group of farmers are considering a new type of fertilizer for potatoes. We know that the standard yield in the population is µ = 20, with σ=3 (bushels per plot), and normal in the population. The farmers test the new fertilize on N = 16 plots of land, and find the mean is 21.4. They are interested in knowing whether the fertilizer "makes any difference." 11. If this was a onetailed test, positive direction, would you reject or fail to reject?

reject

In the population the average IQ is 100 with a standard deviation of 15 (assume normal distribution). A group of researchers believe that exposures to toxins in the environment early in life can depress adult IQ. They collect a sample of 300 individuals who were exposed to environmental toxins at an early age. The mean IQ in that sample was 97. Test the hypothesis. 22. Do you reject or fail to reject?

reject

If people score the same over repeated measures, but those scores do not predict what they are suppose to predict, then the measure is:

reliable but not valid

Perhaps the major factor influencing the width of a confidence interval is

sample size

For a t-test, incontrast to a z-test, the standard error is computed as:

sample standard deviation divided by the square root of N

A Huffington Post poll of 772 registered voters found that 42% of respondents approve of Donald Trump's performance as President, whereas a similar CNN poll found that 44% approve. Which of the following is responsible for the difference between the two polls?

sampling error

A research team at UCLA wants to estimate the average depression level in the general population. The team administers the Beck Depression Inventory to a community sample of 300 participants and gets a mean of 20. This sample mean is unlikely to be exactly the same as the true mean in the full population. Which of the following terms describes the difference between the sample mean and the true mean of the population?

sampling variabiility

An educational psychologist is interested in whether test scores improve between 7th and 8th grade. She recruits a sample of 100 students and finds test score averages of 50 and 53 in 7th and 8th grade, respectively. The paired-samples t-statistic is 1.85 and has a one-tailed probability value of .08. Which of the following conclusions is true regarding the change in scores?

scores did not change from 7th to 8th grad

small residual variability

skinnier bell curves (distance doesn't matter)

The Jamovi book's simple way of writing the standard error in the independent t-test is:

standard deviation (pooled) times square root of 1/N1 + 1/N2

The expected variability or standard deviation of the means from MANY different random samples is known as what quantity?

standard error

In the following equation CI95= (xbar 1-xbar2)+_ CVt (S(xbar 1-xbar2)) the last term(S(xbar 1-xbar2)) is:

standard error of the distribution of difference between sample means

The statistical test was significant <.001, what kind of test was that?

t test

Testing that a

t-test

As the degrees of freedom goes up, at alpha = .05 two-tailed, the tails of the distribution become ______________

the critical values decrease, thinner more like the normal distribution

A group of farmers are considering a new type of fertilizer for potatoes. We know that the standard yield in the population is µ = 20, with σ=3 (bushels per plot), and normal in the population. The farmers test the new fertilize on N = 16 plots of land, and find the mean is 21.4. They are interested in knowing whether the fertilizer "makes any difference." 3. The alternative hypothesis is:

the fertilizer changes the yield (i.e., its different than 20)

In the population the average IQ is 100 with a standard deviation of 15 (assume normal distribution). A group of researchers believe that exposures to toxins in the environment early in life can depress adult IQ. They collect a sample of 300 individuals who were exposed to environmental toxins at an early age. The mean IQ in that sample was 97. Test the hypothesis. 15. The null hypothesis is:

the mean IQ in a sample exposed to toxins is 100 or more AND the sample is just arandom sample from a population with mean = 100, standard deviation = 15

In an independent samples t-test, the sample statistic analyzed is:

the mean of one group minus the mean of a second group

Tothe degree that the null hypothesis in ANOVA is false:

the mean squares between will be larger than the mean squares within

A group of farmers are considering a new type of fertilizer for potatoes. We know that the standard yield in the population is µ = 20, with σ=3 (bushels per plot), and normal in the population. The farmers test the new fertilize on N = 16 plots of land, and find the mean is 21.4. They are interested in knowing whether the fertilizer "makes any difference." 2. The null hypothesis is:

the sample mean is just a random sample from a population with a mean equal to 20 and standard deviation equal to 3 AND in the population of crops that received the fertilizer, the mean is 20

In a t-test, as degrees of freedom decreases:

the t-distribution has "heavier" tails

Now conduct a one-sample t-test using a null of 0.40, on thedifference variable. What has changed relative to the dependent samples t-test in question 14 and the one sample t-test in question 15 (the previous question)?

the t-test and p value have changed

A reasonable conclusion appears to be that although there isa statistically significant result here, the overall effect size is small, eta= .035, and only one comparison is actually significant (Freq vs Some). It seems like in this population, exercise is not having a huge impact on heart rate, more research is needed.

true

ANOVA is an extension of the two-sample independent groups t-test to situations where there are more than two groups.

true

As the degrees of freedom within goes up, critical values in F, alpha = .05, go lower towards 1.0.

true

Both the t and z distributions are symmetric and centered at 0.

true

Data. Conduct an ANOVA (use ANOVA command, not one-way) on PULSE as the DV and EXER as the IV.The F-value is 3.38and the p value is .036

true

Generally speaking, the research design associated with a dependent t-test does a better job of controlling for confounding variables than the research design associated with an independent t-test.

true

Generally speaking, the standard error will be smaller in the dependent samples t-test than an independent samples t-test, leading to possibly more power to reject.

true

In a z-test you have to assume you know the population standard deviation but in a t-test you will have to estimate it.

true

In an independent t-test, the homogeneity of variance of assumption is needed to justify taking a weighted average of the two group variances.

true

In order for a correlation to be a good estimator of the population value, one must collect the full range of scores on variables X andY; if there is restriction, the observed correlation will be too low.

true

In this figure the F is not significant because there is too much within variance relative to between variance.

true

N - 1, # pairs - 1, and N1 + N2 - 2 is the degrees of freedom in the one-sample t-test, dependent groups t-test, and independent groups t-test.

true

One way of thinking of a "regression" line is that it represents the mean of Y conditional on each value of X.

true

The book suggests that Cohen's d of .2, .5, and .8 are "small", "medium" and "large" effects respectively.

true

The correlation coefficient describes only the linear relationship between two continuous variables.

true

The effect size inthe above was -0.172 which means that the weight in the sample was .172standard errors below what was expected under the null hypothesis.

true

The goal of the Tukey honestly significantly different test (HSD) is to keep the overall family wise Type I error rate at .05?

true

The null in ANOVA is that the group means are equal in the population. The alternative hypothesis in ANOVA is always that the population means are different (at least one mean is different from another)

true

The overall effect size in ANOVA can be interpreted as a percent of variance explained even though sum of square terms are in the equation

true

The standard error in the two group independent t-test is essentially the adding together of a standard error of a mean based on each group.

true

X bar estimates mu, S squared estimates sigma squared, and restimated rho.

true

In the population the average IQ is 100 with a standard deviation of 15 (assume normal distribution). A group of researchers believe that exposures to toxins in the environment early in life can depress adult IQ. They collect a sample of 300 individuals who were exposed to environmental toxins at an early age. The mean IQ in that sample was 97. Test the hypothesis. 23. What type of error is possible?

type 1

A group of farmers are considering a new type of fertilizer for potatoes. We know that the standard yield in the population is µ = 20, with σ=3 (bushels per plot), and normal in the population. The farmers test the new fertilize on N = 16 plots of land, and find the mean is 21.4. They are interested in knowing whether the fertilizer "makes any difference." 10. What type of error is possible?

type 2

In a chi-square test of independence: the null is:

variable R and variable C are statistically independent

The term "meansquares" is just jargon for a

varience

A paired samples (dependent groups) t-test would be done:

when people in two groups are "matched" on confounding variables in developmental research over time all of these when you have the same people measured twice

Histograms with imposed densities can be used _________

when you have quantitative variable

The research design associated with a dependent samples t-test is referred to as ___________ and the research design associated with an independent t-test is ________

within group, between group

Assuming the previous question is correct, if this was a one-tailed test (McCain higher in population) instead of a two-tailed, would the t-test value of -4.77 have been the same?

yes

Use the MathAchievement Data. The administrators in this district expected about 20% TypicallyAchieving, 70% Low Achieving, and 10% Learning Disabled in this community. Does a goodness-of-fit test show this to be reasonable given the data?

yes, chi-square is 3.47 on 2 df, p = .177

The chief advantage of an experiment relative to an observational study is:

you can possibly make causal attributions

Sum of squares total is?

Σ(Y−Y−⋅⋅)^2

Sum of squares between is?

Σ(Y−j−Y−⋅⋅)^2


Set pelajaran terkait

Module 16-17 (LaunchPad Questions) sai

View Set

Financial Accounting Study Guide Meramec STL

View Set

Chapter 5: Scatter Control (Important Relationships)

View Set

Law 231 Unit 3 Assessment - Anthony Naayem

View Set

Ch. 15 Care of Newborn & Infants

View Set

Chapter 4 Life insurance Review Pt 2

View Set

Chapter 7 Understanding Theory and Research Frameworks

View Set

Mechanical Properties of Materials (Assignment #5)

View Set