Psych Chap 1-8
5.5 The equation for calculating a CI when σ is unknown has two components that are unchanged from the equation when σ is known, namely, M and _____ SE. _____ a t score. _____ √N. _____ a z score.
Hint: A comparison of the two equations will show that M and √N appear in both.
3.7 Which label best describes this distribution?** _____ negatively skewed _____ positively skewed _____ bimodal _____ unimodal
Hint: A distribution with one peak is referred to as unimodal, with two peaks bimodal, and with three peaks trimodal. In the case of multiple peaks, they do not necessarily have the same height.
4.8 A normal distribution _____ has two modes. _____ is symmetrical. _____ has a U shape. _____ is not commonly found in psychological research.
Hint: A normal distribution is bell-shaped, symmetrical, and commonly found in psychological (and other scientific) research.
2.5. Researchers found that, in all cities with at least one million residents, the more churches in the city, the higher the number of homicides. Which of the following is a possible confound? _____ the number of homicides _____ the number of churches _____ the cities that were included in the study _____ the year(s) in which the study was conducted
Hint: A potentially confounding variable is one that was uncontrolled for in the research and thus may have altered the results. In the case, the years in which the study was conducted may have been characterized by specific circumstances (such as high joblessness) that could have altered the outcome
5.7 Which interpretation of the CI is most widely accepted? _____ The cat's eye picture helps interpret the interval. _____ The CI gives useful information about replication. _____ MoE gives the precision. _____ The CI is one from the dance.
Hint: According to the authors, only this interpretation is endorsed unanimously.
4.2 This figure shows the standard normal distribution.** According to this figure, if someone has a z score of −1, this places her or him in the ____ percentile of the standard normal distribution? _____ 95th _____ 50th _____ 2.5th _____ 16th
Hint: Adding the two percentages that appear leftmost under the curve yields 16%, or 16th percentile.
1.2 Marion attends a university with about 2,000 students. Marion wants to know to what extent students receive preventive healthcare. She interviews 40 students. Based on these interviews, she concludes that preventive healthcare is accessed by 75% of students, 95% CI [63, 84]. What does it mean when Marion reports "95% CI [63, 84]"? _____ In the sample, the level of preventive healthcare access is most likely somewhere between 63% and 84%. _____ In the population, 63% to 84% of students have access to preventive healthcare. _____ In the population, the level of preventive healthcare access is most likely somewhere between 63% and 84%. _____ In the sample, 63% to 84% of students have access to preventive healthcare.
Hint: All of the students at the university have access to preventive care. Based on her sample, Marion estimated that 63-84% of them actually accessed it.
8.2 In the Halloween study, the order of exposure to the two sets of stimuli was counterbalanced in order to minimize _____ validity. _____ variance. _____ carryover. _____ reliability.
Hint: Although counterbalancing may have reduced reliability, validity, or variance, its primary function is to control for the effects of exposing the same participants to different conditions.
8.8 Based on the data, Joe and Anna conclude that hospitals are biased in favor of female nurses and recommend the development and implementation of a program to eliminate the bias. In making this decision, what should their primary concern be? _____ Type 0 error _____ Type I error _____ Type III error _____ Type II error
Hint: Assuming that H0 is no difference between the two groups, then, by rejecting it, the researchers risk committing Type I error.
3.9 Means and standard deviations require data that are at least at the ______ level of scaling. _____ nominal _____ ordinal _____ interval _____ ratio
Hint: Because the calculation of the mean includes the distance between the data item and the mean, an interval scale of measurement is required. Because the calculation of the standard deviation includes the mean, it too requires interval-level measurement.
5.8 How is the cat's eye picture of a CI affected by the level of confidence? _____ The shaded portion of the eye grows smaller as the confidence level decreases. _____ It changes color as the level of confidence changes. _____ It increasingly resembles a dog's eye as the level of confidence increases. _____ The picture remains constant regardless of the level of confidence.
Hint: Because the shaded portion of the eye represents the level of confidence, changes in the level affect the size of the shaded portion directly.
1.5 An instructor polls the students in her class about their support for using a different grading system at the university. Once she analyzes the results, she concludes, "Support in the sample was almost exactly split (50%), but the confidence interval ranges from about 40% to 60%, so in the population it is not very clear whether support is in the minority, evenly split, or in the majority." Which study in the previous chart best matches this conclusion? _____ Study 4 _____ Study 1 _____ Study 2 _____ Study 3
Hint: Both the point estimate and the CI in Study 1 are closest to the instructor's description of the results from the sample of her students.
2.4. Sometimes a research study includes two levels of the IV, with the first level being the customary state of affairs, which we consider the baseline level. The other level is altered from the ordinary condition so that we can make a comparison. The first level is properly referred to as the ________. _____ confirmatory _____ control _____ ordinary _____ uncontrolled
Hint: Control refers to both a level or condition of the IV as well as to a group of participants to whom that level is assigned.
8.10 For a paired-samples t test, what are the degrees of freedom (df)? _____ N - 1 _____ MDiff / SD _____ N _____ µ1 − µ2
Hint: Equation 8.1 makes this clear.
4.3 When using a random sample, the sample mean, M, will _____ tend to be near the population mean, μ. _____ always be just a bit less than the population mean, μ. _____ differ from the population mean, μ, by the SD. _____ be exactly the same as the population mean, μ.
Hint: Given a random sample, M will approximate μ and is as likely to overestimate it as underestimate it.
7.9 A researcher randomly assigns participants to either an exercise group or a sleep group before taking a motor-skills test. She uses the NHST approach, with a null hypothesis that Msleep - Mexercise = 0 and an α of 0.05. She reports: t(38) = 3.02, p = 0.004. Which of the following is the best answer? _____ The 95% CI for Msleep - Mexercise will include 0. _____ The researcher will fail to reject the null hypothesis. _____ The likelihood of Type I error is high. _____ This is a statistically significant finding.
Hint: Given the small p value, the researcher is justified in declaring significance and rejecting the null hypothesis.
1.10 Researchers reported a study in which their estimate of the level of pain that their participants reported following a one-hour exposure to relaxation training was 36% [21, 51]. What do the last two numbers represent? _____ the origin and endpoint of the pain scale _____ the number of female and male participants, respectively _____ the average point estimate _____ the 95% CI
Hint: Hint: The specific notation is interpreted as being 95% confident that the "true value" approximated by the point estimate of 36% lies within the range [21, 51].
8.5 Compared to an independent-groups design, a paired design provides _____ a longer CI for the difference, especially if the paired measures are inconsistent. _____ a shorter CI for the difference, especially if the paired measures are inconsistent. _____ a longer CI for the difference, especially if the paired measures are consistent. _____ a shorter CI for the difference, especially if the paired measures are consistent.
Hint: If the measures are consistent, there is little, if any, need for a standardizer in calculating the value of d, thereby reducing the length of the CI.
8.4 Which of the following statements about Cohen's d is the best answer? _____ It cannot be calculated for the paired design. _____ If used with paired designs, the variables must all the measured on the same scale. _____ It is only useful in the paired design if the NHST approach is used. _____ It provides a useful way to express a standardized effect size for the paired design.
Hint: In addition to its applicability, regardless of the scales of measurement involved, it may be used with the NHST approach or the estimation approach and with independent-groups and paired designs.
1.7 What does the diamond in this plot represent?** _____ the overall point estimate and confidence interval _____ the overall population _____ the overall level of sampling variability _____ the overall level of hybridization
Hint: In this forest plot, the red diamond summarizes the results represented by the four displays—point estimates and CIs—in green.
1.9 Suppose you want the MoE from a replication study to be about half of the MoE from the original study. The size of the sample in the replication study should be ________ as large as the size of the sample in the original study. _____ one-fourth _____ four times _____ half _____ twice
Hint: Increasing the sample size generally decreases the MoE. The example found in the textbook specified that, to cut the MoE in half, the replication study should use a sample four times that of the original.
5.9 What does it mean to say that the CI is a replication interval? _____ It indicates whether a replication will be successful. _____ It indicates whether a replication should be attempted. _____ It is a predictor of how many replications should be conducted. _____ It is the interval in which the mean of a replication is likely to fall.
Hint: Interpreting the CI as a replication interval means that it predicts the likelihood that the mean of a replication will fall within it. The likelihood is the same as the confidence level.
2.3. To what extent might prayer improve grades? Participants were told they were about to take a difficult logic test. Half were asked to pray for help on the exam; the other half were asked to prepare silently for the exam. All participants then took the logic test. Scores were the same for both groups. Which of these statements is true about the study? _____ No causal conclusion could be drawn from the study. _____ The IV was the logic test. _____ The study was non-experimental. _____ The DV was prayer or no prayer.
Hint: It is independent in the sense that its values are at the researcher's discretion. In this case, there was an independent variable—prayer and no prayer—and two groups in the experiment. The absence of a difference in outcome between the groups, together with questions about the participants and the procedure, prevent any causal conclusion. The DV was the score on the logic test.
5.6 What does the "dance of the CIs" refer to? _____ the shift of the effect size and its CI over successive samples _____ the pattern of the changing effect size and CI from sample to sample could be set to music _____ the tendency of the SD to vary over successive samples _____ the fact that the effect size and the CI are partnered
Hint: Like the dance of the means, the term "dance" is meant to describe the back-and-forth pattern of the effect size and CI over successive samples.
2.6. To measure a variable involves the assignment of ________ to it in such a way that there is a one-to-one correspondence between the state of the variable and the measure. _____ qualities _____ signifiers _____ numbers _____ units
Hint: Numbers are the symbol system to which a variable is mapped in order to measure it.
2.10. Open Science advocates preregistration as a check on each of the following biases except _____ cherry picking. _____ exploratory analysis. _____ faces in the clouds. _____ planned analysis.
Hint: Planned analysis is a component of preregistration and is designed to discourage the other practices that are listed.
6.4 Which statement is correct? _____ The definition of p-value is deliberately ambiguous. _____ P-values can range from 0 to infinity. _____ P-values can range from −1 to 1. _____ P-values can range from 0 to 1.
Hint: Probability values range between 0 and +1 inclusively.
7.10 For the same study described in the previous question, imagine that the researcher had not randomly assigned participants to sleep or exercise. Instead, imagine that she recruited participants and split them into two groups based on whether or not, in the hour before the study, they happened to have slept or exercised. What would be different about this approach? _____ Without random assignment, no confidence interval can be calculated. _____ Because sleep and exercise are measured differently, it would be necessary to use d. _____ Without random assignment, the NHST approach cannot be used. _____ Without random assignment, the researcher cannot draw causal conclusions.
Hint: Random assignment to groups is essential for causal claims from data.
6.5 When a p-value is near zero, this indicates the probability that further research should be conducted. _____ the data obtained are very likely if the null hypothesis is true. _____ the data obtained were not sufficient to tell us _____ anything about the null hypothesis. _____ the data obtained are very unlikely if the null hypothesis is true.
Hint: Remember that the p-value is premised on the assumption that the null hypothesis is true. Thus, near-zero p-values indicate that the assumption is unlikely.
4.9 Which of the following expressions is the correct formula for a z score of a sample from a population? _____ (X - μ)2 / n _____ (X - μ) / σ _____ √SD2 _____ ∑X/n
Hint: See Equation 4.1.
4.6 The standard error of the mean is _____ the mean of the population divided by M. _____ the mean of the outliers divided by the standard deviation. _____ the ratio of the median and the mode. _____ the standard deviation of the population divided by the sample size.
Hint: See Equation 4.3.
3.2 In the dot plot, the distribution is not symmetrical; the tail above the median is longer than the tail below the median. What is this lack of symmetry called? _____ skew _____ abnormality _____ outlier bias _____ uneven spread
Hint: Skew (positive or negative) refers to one of the tails of the distribution being longer than the other one. In the case, the distribution has a positive skew.
5.1 The margin of error refers to _____ the error that results from the use of faulty methods. _____ a statistic that describes the range of likely values of an effect size. _____ the limit to the amount of error in a statistic before it becomes useless. _____ a weighting factor corresponding to a percentage of the area beneath the normal curve.
Hint: Specifically, the MoE is half of the length of an interval that defines the likely values of an effect size (point estimate).
6.9 A researcher administers a moral-reasoning test to participants randomly assigned to complete the test during the morning or during the afternoon. She finds that those who took the test in the afternoon are more judgmental than those who took it in the morning, t(38) = 2.71, p = 0.01. She rejects the null hypothesis that time of day has no effect on moral reasoning. What type of error is her conclusion related to? _____ Type II _____ Neither. The p-value is so small that there is no doubt that her results are accurate. _____ Type I _____ Both Type I and Type II
Hint: That she rejected the H0 is consistent with the definition of Type I error. Accepting H0 would be consistent with Type II error.
7.1 Emilia randomly assigns participants to taste samples of either Godiva chocolate or Hershey chocolate. After sampling, participants are asked to rate their enjoyment on a scale from 1 to 10 (1 = disgusting, 10 = heavenly). Emilia finds: MGodiva - MHershey = 2.1, 95% CI [1.1, 3.1] Which of these conclusions is best supported by her data? _____ Godiva chocolate was liked more than Hershey chocolate was. The CI indicates at least a slight preference but possibly a large one. _____ Godiva chocolate is liked almost the same as Hershey. The CI indicates that any difference is quite small. _____ Godiva chocolate was liked a bit more in this sample, but the CI is so broad that no firm conclusions can be made. _____ Godiva chocolate is not liked as much as Hershey. The CI indicates at least a moderate preference for Hershey.
Hint: The CI spans an interval from very slight preference to substantial preference (1.1 to 3.1) for Godiva chocolate over Hershey.
1.3 In the figure above, which study provided the most precise estimate?** _____ Study 2 _____ Study 3 _____ Study 1 _____ Study 4
Hint: The CI was shortest in this study, making its estimate the most precise
7.5 Cohen's d is _____ a standardized way of expressing group differences that doesn't depend on the scale of the original measurement. _____ a test for homogeneity of variance. _____ the same measure as the margin of error. _____ the lower bound of the CI.
Hint: The appeal of Cohen's d is that it is indifferent to the scale of measurement.
2.7. Patryja asked 20 participants to complete a measure of extroversion. How can she determine if her measure is reliable? _____ Ask the same participants to take the same measure again to see if results are consistent. _____ Ask the same participants to take a different measure of extroversion to see if results from the two measures are consistent. _____ Ask new participants to take a different measure of extroversion to see if the results are consistent with those from the previous participants. _____ Ask a group of new participants to take the same measure to see if the results from the two groups are consistent.
Hint: The better measure of reliability would come from this procedure rather than that in "a," as there may be potential confounds in the use of a new group of participants. Answer options "b" and "c" are more relevant to validity.
2.8. Patryja asked 20 participants to complete a measure of extroversion. How can she best determine if her measure is valid? _____ Ask new participants to take a different measure of extroversion to see if the results are consistent with those from the previous participants. _____ Ask the same participants to take a different measure of extroversion to see if results from the two measures are consistent. _____ Ask the same participants take the same measure again to see if results are consistent. _____ Ask a group of new participants to take the same measure to see if the results from the two groups are consistent.
Hint: The better measure of validity comes from this procedure rather than in "Ask new participants to take a different measure of extroversion to see if the results are consistent with those from the previous participants," given that new participants might bring confounds. The other options are more relevant to reliability.
7.8 Researchers randomly assigned college students to drink either water or two cans of Red Bull. Immediately afterwards, all students completed the GRE. The researchers concluded that Red Bull had essentially no effect on GRE scores. Which result matches this conclusion? _____ dunbiased = -1.0, 95% CI [−1.2, −0.8] _____ dunbiased = 0.01, 95% CI [−0.02, 0.04] _____ dunbiased = 0.01, 95% CI [−2.0, 2.0] _____ dunbiased = 1.0, 95% CI [0.8, 1.2]
Hint: The compact CI interval [−0.02, 0.04] and its inclusion of zero make it more consistent with the conclusion than any of the other answers do.
4.4 In general, which of these would provide the best estimate of the population mean? _____ It is not the size of the sample but its quality that matters most. _____ a sample of 1,000 participants _____ a sample of 1 participant _____ a sample of 100 participants
Hint: The comparison of mean heaps in Figure 4.7 makes clear that enlarging sample size narrows the distribution of sample means, thereby improving the estimate of the population mean.
6.2 In the NHST approach, what is the null hypothesis? _____ the assumption that one's data will be flawed _____ a statement giving a specific value of the parameter one is studying, a value that one will test to determine if that value is plausible _____ an open-minded approach, where one has no hypotheses prior to conducting research _____ a hypothesis that has already been rejected by previous researchers but still appears promising because of subsequently identified mistakes in their procedures
Hint: The concept of the null hypothesis is widely misunderstood, and the authors are careful to define it as a single value of a population parameter, the plausibility of which will be tested.
6.8 A Type II error is _____ failing to reject the null hypothesis when it is actually true. _____ rejecting the null hypothesis when it is actually false. _____ rejecting the null hypothesis when it is actually true. _____ failing to reject the null hypothesis when it is actually false.
Hint: The confusion over the two types of error involving H0 may be resolved by associating Type I with the rejection of H0 and Type II with the acceptance of H0. With Type I, the error is rejecting when H0 is true. With Type II, the error is accepting H0 when it is false.
5.4 A sample with 24 effect sizes has a df value of _____ 12 _____ 23 _____ 4 _____ 25
Hint: The degrees of freedom (df) refers to the number of independent contributors to an aggregated entity. For example, if the product of a set of seven numbers when multiplied is P, then the value of each of the first six numbers in the set is free of what the values of the other five are. But the seventh number is not. Its value is fixed by the values of the other six and the value of P.
8.7 From these data, Joe and Anna would best conclude that _____ the CI on the difference is too broad to draw a firm conclusion. _____ the hospitals seem to prefer female applicants, and the preference could be anywhere from about 0.5 points to 1.5 points on a 10-point scale. _____ the hospitals seem to have equal preferences, though the real difference could be anywhere from between 7 and 8 points. _____ the hospitals seem to prefer females by a wide margin anywhere from 3 to 9 points. Hint: The difference CI is short, spanning the distance from approximately 0.5 to 1.5 in favor of female applicants.
Hint: The difference CI is short, spanning the distance from approximately 0.5 to 1.5 in favor of female applicants.
6.1 How does Null Hypothesis Significance Testing (NHST) differ from the estimation approach to analyzing data? _____ NHST is actually the exact same thing as the estimation approach, but it is called estimation in the U.S. and NHST in Europe and Australia. _____ NHST and estimation approaches are completely incompatible, so using one means you must avoid the other. _____ NHST is different, but it is based on the same foundations as the estimation approach, and one can usually translate results back and forth between these approaches. _____ NHST is the approach used for experimental research, and estimation is used for all other types of research.
Hint: The estimation approach of the new statistics is presented as an alternative NHST despite their having much in common. The downside of NHST was briefly outlined in this chapter and will be returned to in future chapters.
3.5 Marbeya scored a 90% on the last exam. The class average was 70% with a standard deviation of 15%. Based on this information, her z score will be _____ the highest in the class. _____ exactly 0. _____ greater than 0. _____ less than 0.
Hint: The fact that her score lies above the mean assures that her z score will be positive. There is no indication that it was the highest score.
7.4 Calculating the CI for the difference between two independent groups requires each of the following except _____ a sample size component, reflecting the size of the sample. _____ an expectation component reflecting the expected CI's mean. _____ a variability component, reflecting the variation in scores in both groups. _____ a t component, based on the degrees of freedom and confidence level desired.
Hint: The first three answers are the components the authors identify.
8.6 Joe and Anna are working on a research project to determine whether employers treat male and female nursing applicants differently. They send two forms of the resume to personnel staffs at 14 hospitals. The resumes contain the same qualifications and educational background, but has an unambiguous male name on it and the other an unambiguous female name. A copy of each form was sent to the hospitals. Joe and Anna then contacted each hospital and requested a rating (scale of 1-10) of the personnel staff's interest in interviewing the applicant. This chart shows the (fake) data obtained. **Chart showing confidence intervals for interest in interviewing male and female candidates. The results shown as triangles indicate that _____ the CI for the difference was about 2 points wide. _____ the personnel staffs were about 1 point more interested in female applicants than male applicants. _____ the variation in scores was about 1 point. _____ the level of error in these scores is about 1 point. Hint: The length of the CI on the difference (MFemale - MMale) is approximately 1. That CI lies above means that female applicants were of more interest to personnel staffs than male applicants were.
Hint: The length of the CI on the difference (MFemale - MMale) is approximately 1. That CI lies above means that female applicants were of more interest to personnel staffs than male applicants were.
8.3 The researchers found Mdiff = 10 µg/dl, 95% CI[-25, 45]. Which of the following conclusions is best supported by this analysis? _____ Halloween imagery did not greatly influence cortisol levels, with only small effects likely if the study were to be replicated. _____ Halloween imagery decreased participants' cortisol levels from moderate to low. _____ It is not clear from these data, because the CI was long and therefore consistent with a large decrease to no effect to a large increase. _____ Halloween imagery increased cortisol levels from moderate to high. Hint: The lengthy CI means a substantial range in which the effect size could vary, making it rather pointless to draw a directional conclusion about the current results or those from a replication.
Hint: The lengthy CI means a substantial range in which the effect size could vary, making it rather pointless to draw a directional conclusion about the current results or those from a replication.
7.3 At a treatment clinic, Desrae randomly assigns 12 depressed patients to either a new type of brain stimulation (Group 1—the treatment group) or the standard treatment (Group 2—the control group). After 1 week, participants complete a scale that measures depressive symptoms. The control group still has high depression (MControl = 15). The group that received brain stimulation has lower depression (MBrainstim = 9). Comparing the data from the two groups, she finds: MControl - MBrainstim = 6, 95% CI [2.54, 8.63] What should she conclude? _____ The new treatment clearly is not effective. _____ The patients who received the new treatment improved as a result of expecting that the new treatment would make them less depressed. _____ The results are promising because the CI rules out no difference, and the mean difference is above zero. _____ The new treatment is clearly effective but only barely.
Hint: The location of the difference CI above zero and the absence of overlap between the CIs of the two groups is strong evidence that the results are promising.
4.1 Which of the following statements is the best description of statistical sampling? _____ A sample is used to make inferences about a population. _____ A population is used to make inferences about a sample. _____ One sample is just as good as another when it comes to making inferences. _____ Descriptive statistics are applied to populations rather than to samples.
Hint: The logic of sampling begins with a population from which samples are taken. Descriptive statistics may be calculated for populations and samples.
7.2 This figure compares exam scores from two different groups. What is best concluded from this figure?** _____ The CI of the difference indicates anywhere from a moderate up to a large advantage for Group 2. _____ The CI of the difference is small and centered around 0. _____ The CI of the difference indicates anywhere from a moderate up to a large advantage for Group 1. _____ The CI of these data ranges from 3 to 6.
Hint: The mean of the difference is approximately 6 with a CI ranging from approximately 2.5 to 9. Saying the CI of the difference indicates anywhere from a moderate up to a large advantage for Group 2 offers the closest description.
3.4 In this histogram, what should the y-axis be labeled?** _____ standard deviation _____ mode _____ mean _____ frequency
Hint: The mean, mode, and standard deviation of a distribution have fixed values; they do not vary.
3.10 Josephine scored at the median for her class. What is her percentile? _____ 0% _____ 25% _____ 100% _____ 50%
Hint: The median is the measure of central tendency that divides a data distribution exactly in half. The 50 percentile is the point at which half of the distribution lies below and the other half above
6.10 In NHST, once a test statistic is available, its distribution should be consulted in order to determine a p-value. How is it determined? _____ by multiplying the test statistic by 1.96 _____ by determining the mode of the test-distribution statistic _____ by determining the probability of a p-value more extreme _____ by determining the probability of a p-value less extreme
Hint: The method of NHST relies on the use of probabilities and whether they are sufficiently extreme to warrant a decision about the truth of the null hypothesis.
3.1 This dot plot shows the distribution of ages for a group of 110 participants.** The diamond shows the median. What is the mode of this distribution? ____ 26 ____ 21 ____ 18 ____ 19
Hint: The mode is the most-frequent score.
1.6 What is one of the two major guidelines for Open Science? _____ Once is enough. _____ Share only what worked. _____ Be open to new ideas. _____ Seek replication.
Hint: The other major guideline is "Do we have the full story?"
6.6 You read in the results section of a research article, "We found that the two groups were significantly different in terms of depression scores (t(25) = 2.1, p = .046)." Based on this statement, you know that _____ the two groups being compared had the same levels of depression. _____ had an estimation approach been used, the 95% confidence interval would have included 0. _____ the researchers will not reject the null hypothesis. _____ the p-value reported by the researchers is based in the assumption that the null hypothesis is true.
Hint: The p-value could be interpreted differently, depending on the p-value the researchers had selected prior to conducting their research. Regardless of that value, it would have been based on the premise that the null hypothesis is true. The correctness of the other two answers is dependent on what the p-value was.
6.3 What does p indicate? _____ the probability of rejecting the null hypothesis _____ the probability that a data analysis will be conducted without having to correct the results _____ the probability of obtaining results similar to the one's own or more extreme IF the null hypothesis is true _____ the probability of a false positive
Hint: The p-value is a probability indicating the likelihood of results and premised on the assumption that the null hypothesis is false.
5.2 What does the 95% in a 95% CI refer to? _____ the percentage of the values of an effect size that lie within a specific interval _____ the percentage of the data that are valid _____ the likelihood of replicability of the data _____ the degree of deviation between the lowest and highest effect sizes in a sample
Hint: The percentage that distinguishes a CI is a percentage index of how much of the distribution of the effect size is included.
2.1. Which of these would best represent random sampling from a population? _____ You put the names of all 1,000 of the company's customers into a bowl and randomly select 100 of them to interview. _____ You randomly select one customer. Once you have interviewed him or her, you flip a coin. If the coin is heads, you ask the customer to refer you to someone else he or she knows who has purchased the product. You then interview that person and again flip a coin. This continues until you obtain 100 interviews. _____ You get a list of the most recent 200 customers and randomly select half of them to be interviewed. _____ You set up a booth where your company sells a product and ask the next 100 customers who walk in to be interviewed.
Hint: The population includes everyone who has purchased the product, and using a random draw from that population produces a random sample as everyone in the population would have the same chance (0.1) of being in the sample.
1.1 Marion attends a university with about 2,000 students. Marion wants to know to what extent students receive preventive healthcare. She interviews 40 students. Based on these interviews, she concludes that preventive healthcare is accessed by 75% of students, 95% CI [63, 84]. What is the population in Marion's study? _____ 2,000 students _____ 75% of students _____ 95% of students _____ 40 students
Hint: The population includes everyone who is a student at the university and thus everyone who could conceivably receive preventive healthcare.
3.3 Normal distributions are _____ symmetrical _____ sharply peaked _____ flat (no central peak) _____ bimodal
Hint: The shape of the normal distribution is that of a bell, that is, one side shaped just opposite the other side.
1.4 In the previous chart, all other things being equal, which study most likely had the largest sample?** _____ Study 2 _____ Study 4 _____ Study 3 _____ Study 1
Hint: The shortness of the CI is indicative of a large sample. Generally, the size (or length) of the CI varies inversely with the sample size.
7.7 When comparing two independent groups _____ the more variation in the data, the shorter the CI of the difference. _____ the larger the sample sizes, the shorter the CI of the difference. _____ the smaller the sample sizes, the shorter the CI of the difference. _____ the larger the mean of sample means, the shorter the CI of the difference.
Hint: The size of the sample generally varies inversely with the length of the CI.
8.9 Based on the CI on the difference shown in the figure, if the NHST approach is used, which of the following conclusions is most likely? _____ This is not a statistically significant result, p > 0.05, so fail to reject the null. _____ No conclusions can be drawn about the NHST approach. It does not apply to paired designs. _____ Female nurses are paid less than male nurses are at the hospitals. _____ This is a statistically significant result, p < 0.05, so reject the null.
Hint: The small length of the CI on the difference in interest suggests that an NHST analysis would produce a statistically significant result. Though the result is consistent with the possibility of a pay differential, it is not evidence for such.
4.5 What is the standard error of the mean? _____ the average amount by which a sample mean mis-estimates the population mean _____ the sample size _____ a problem that occurs when trying to calculate a mean with sample size of zero _____ another name for a z score
Hint: The standard error of the mean is the standard deviation of the distribution of sample means and thus represents the accuracy of the estimated value of the population mean.
4.7 According to the ________, the means of many different samples tend to be normally distributed. _____ Law of Small Numbers _____ Central Limit Theorem _____ Hook/Smyrnoff Law _____ Variation Tendency Hypothesis
Hint: The textbook authors refer to the central limit theorem as magical because, despite the irregularity of the population distribution, the distribution of sample means drawn from the population tend to be normally distributed.
2.9. Friendliness was measured by asking each participant to classify herself or himself as not friendly (1) or friendly (2). What level of measurement is this? _____ interval _____ nominal _____ ratio _____ ordinal
Hint: The use of numbers in this case is to designate each participant as one or the other. In other words, the number names the category to which the participant is self-assigned.
5.3 The t statistic is useful _____ when the data distribution has missing values. _____ when μ is unknown. _____ when σ is unknown. _____ when there is unusually large variance in the data distribution.
Hint: The value of t is calculated using M, μ, and s because σ is unknown.
7.6 Each of the following assumptions is made when calculating a CI for the difference between two _____ independent groups except _____ the groups were created simultaneously. _____ scores are normally distributed for both groups. _____ the variances are approximately equal for both groups (homogeneity of variance). _____ both groups are random samples.
Hint: There is no requirement for the simultaneous creation of the groups.
2.2. The statistics that summarize a data sample are referred to as ________ and are used to calculate ________ statistics, which refer to the population from which the sample came. _____ descriptive; inferential _____ specific; general _____ local; global _____ constructive; comprehensive
Hint: These are the official terms for the two primary categories of statistics, one referring to the sample and the other to the sample's relation to the population.
3.6 Which of these sets of scores would have the largest standard deviation? _____ 5, 5, 5, 5, 5, 5 _____ 4, 4, 5, 5, 6, 6 _____ 9, 9, 9, 9, 9, 9 _____ 1, 1, 5, 5, 9, 9
Hint: This particular set of numbers varies more than the others do.
1.8. This type of plot represent the results from what type of analysis?** _____ a mean analysis _____ a forest analysis _____ a mediator analysis _____ a meta-analysis
Hint: This type of plot is known as a "forest plot" and is a type of CI associated with meta-analysis.
4.10 Juan worked really hard in his math class and scored way above the class average. What will Juan's z score be? _____ less than 0 _____ greater than 0 _____ right around 0 _____ within 1 SD of the class average
Hint: To have a score "way above the class average" implies a score more than 1 SD above the average.
5.10 According to the authors, whenever an error bar is used in a graph, it is essential to _____ show the CI separately. _____ label it as "error bar." _____ indicate what it means. _____ display it a different color.
Hint: To prevent what the authors refer to as the "tragedy of the error bar," they urge that the error always be defined in terms of what is represents—CI, SD, SE, or otherwise.
8.1 To what extent is Halloween bad for your health? Participants were exposed to photos of neutral stimuli (e.g., dogs and cats) and also to photos of Halloween-related objects (e.g., ghosts, witches, and jack-o-lanterns). The order of exposure was counterbalanced. After each round of photographs, participants had their blood levels of cortisol, a chemical which indicates stress, measured. The difference in cortisol levels was examined, Mdiff = MHalloween-MNeutral. Typical cortisol levels are 7-18 µg/dl. What type of research design is this? _____ within-subjects two-sample study _____ between-subjects two-sample study _____ between-subjects one-sample study _____ within-subjects one-sample study
Hint: Two groups were created in the study. The same participants were presented with two sets of stimuli, making the groups paired, that is, a within-subjects design.
3.8. Which measure of location is most sensitive to outliers? _____ median _____ mode _____ standard deviation _____ mean
Hint: Unlike the median and the mode, the calculation of the mean involves the difference of each data item from the mean. The standard deviation is not a measure of location per se.
6.7 A researcher measures learning in 12 students who were randomly assigned to take Psychology 101 online or in a traditional classroom. With a null hypothesis of no difference, she finds no statistically significant difference in learning (t(10) = 0.70, p = .50). Should she conclude that online courses are just as effective as regular courses are? _____ Yes, because the 95% CI would not include 0 difference in learning. _____ Yes, because the p-value is large. _____ No, because a large p-value is not evidence that the null hypothesis is true. _____ No, because only p < 0.05 would justify doing so.
Hint: Using a large p-value as evidence that the null hypothesis is true is one of the red flags the authors raise.
