Stats Exam #2
A week after participating in a workshop on driving safety, we asked a sample of 30 new drivers to report their frequency of texting while driving. We then compared their scores to the national norms for this behavior and found that t(29) = 2.95, p < .01, η2 = .08. The chance of a Type I error is ______. zero (0) 8% 1% it is not possible to determine
1%
If you reject your null hypothesis (p < .01), the probability that you have made a Type I error is ______ and the probability that you have made a Type II error is ______. 5%; zero zero; 5% 1%; zero zero; 1%
1%; zero
If N = 15 for a one-sample t test, then df = ______. 15 14 30 10
14
Edna compares two groups and finds a Cohen's d of .18, suggesting that the means of the groups differ by ______, which is a ______ effect. 18%; weak 18%; moderate 18 standard deviation units; weak 18 standard deviation units; moderate
18 standard deviation units; weak
Steve finds that the proportion of variability accounted for in his experiment is .18. This means that ______ of the variability in the dependent variable is accounted for by the independent variable and he has found a ______ effect. 81%; strong 3.5%; weak 18%; weak 18%: moderate
18%: moderate
Which G1 value would indicate a positively skewed distribution? 1.2 2.6 0 .45
2.6
Joyce asks individuals leaving a gym how many times a week they tend to exercise at the gym. She finds that on average, her participants exercise 3.67 times a week (SD = 2.00), 95% CI [1.44, 5.90]. This suggests that her mean of ______ likely represents a population mean between ______ and ______. 2.00; 3.67; 5.90 3.67; 1.44; 5.90 3.67; 1.67; 5.67 2.00; 1.44; 5.90
3.67; 1.44; 5.90
What percentage of scores in a normal distribution is between +1 and 1 standard deviation of the mean? 5% 34% 68% 95%
68%
In a normal distribution with M = 80, SD = 10, the range of scores that defines 68% of the distribution is ______. 75-85 70-95 70-90 80-100
70-90
Typically we compute the ______ confidence interval. 10% 50% 75% 95%
95%
When reporting the results of a one-sample t test we should also report ______. Cohen's d and eta squared (η2) Cohen's d or eta squared (η2) expected and observed frequencies the number of categories in our sample
Cohen's d or eta squared (η2)
As his class project Reggie asks 30 undergraduates to select their preference for class format (face-to-face or online). He analyses the data and finds t(28) = 5.73, p < .05, d = .40. How should he interpret his results? His results were significant with a weak effect size and he needs to report whether more students preferred face-to-face or online classes. His results were significant with 40% of the variability in preference for class type accounted for. He should analyze the data again by computing a different statistical test because the data are nominal. He should analyze the data again by computing the 95% confidence interval.
He should analyze the data again by computing a different statistical test because the data are nominal.
Which of the following is a characteristic of a normal distribution? It is asymmetrical. Most scores are on the right. There are two distinct peaks Scores taper off at both ends..
Scores taper off at both ends..
A researcher compared the average salary for a sample of first generation college graduates with the average for all college graduates one year postgraduation and found t(99) = 1.59, p > .05, d = .62. Is there a possibility of a Type II error? Yes, the probability of a Type II error is 5%. Yes, but we do not know the exact probability. No, you cannot have a Type II error when the null hypothesis is rejected. No, you cannot have a Type II error when the effect size is moderate or large.
Yes, but we do not know the exact probability.
In an experiment the alternative hypothesis predicts ______. a difference between groups no difference between groups a difference between the sampling distribution and a population the degree of similarity between groups
a difference between groups
If we want to find whether the first year class at our college has higher scores on the SAT writing test than the national average for the test, we would compute ______. the effect size practical significance a one-sample t test an alternative hypothesis
a one-sample t test
Which of the following represents the highest score? a score at the 1st percentile a score at the 50th percentile a score at the 5th percentile a score at the 95th percentile
a score at the 95th percentile
A ______ distribution has two distinct peaks. normal bimodal positively skewed negatively skewed
bimodal
If you have data from qualitative measures that you wish to examine with descriptive statistics, you must first ______. code the data graph the data summarize the data using frequencies you cannot analyze data from qualitative measures with descriptive statistics
code the data
Joyce asks individuals leaving a gym how many times a week they tend to exercise at the gym. She finds a mean of 3.67 (SD = 1.89), but her friend is not satisfied because she feels that Joyce needs to calculate the ______ to understand the margin of error in the results. statistical significance effect size confidence interval practical significance
confidence interval
Power is defined as ______. correctly rejecting a true null hypothesis correctly rejecting a false null hypothesis correctly retaining a true null hypothesis correctly rejecting a true alternative hypothesis
correctly rejecting a false null hypothesis
A researcher reports that 30% of the participants in the sample were between the ages of 45 and 65. What type of descriptive statistic is the researcher reporting? percentage frequency cumulative percentage central tendency
cumulative percentage
The proportion of the sample that falls within a specified interval is the ______. percentage frequency cumulative percentage central tendency
cumulative percentage
In her study of adjustment to college, Sasha decided to use only first year, first generation college students who lived on campus. This decision is likely to ______ the error variance in her results because of the ______ of her sample. increase; difference decrease; difference increase; homogeneity decrease; homogeneity
decrease; homogeneity
The numbers used to summarize characteristics of a sample is known as ______. qualitative analyses descriptive statistics qualitative statistics a bar graph
descriptive statistics
The critical value of a statistic defines the ______. top 2.5% of the distribution for a one-tailed hypothesis bottom 2.5% of the distribution for a one-tailed hypothesis extreme 5% of the distribution for a one-tailed hypothesis and extreme 2.5% of the distribution for a two-tailed hypothesis extreme 2.5% of the distribution for a one-tailed hypothesis and extreme 5% of the distribution for a two-tailed hypothesis.
extreme 5% of the distribution for a one-tailed hypothesis and extreme 2.5% of the distribution for a two-tailed hypothesis
A researcher reports that there were 126 females and 132 males in the sample. What type of descriptive statistic is the researcher reporting? percentage frequency cumulative percentage central tendency
frequency
A simple count of how many times a score occurred in a sample is the ______. percentage frequency cumulative percentage central tendency
frequency
In order for the results of a one-sample t test to be significant, the computed t value must be ______. greater than the critical t value listed in the t table for our degrees of freedom (df) and p value less than the critical t value listed in the t table for our degrees of freedom (df) and p value equal to the critical t value listed in the t table for our degrees of freedom (df) and p value greater than the critical t value for the degrees of freedom (df) for our population
greater than the critical t value listed in the t table for our degrees of freedom (df) and p value
The 99% confidence interval will be ______ the 95% confidence interval. larger than smaller than the same as not different than
larger than
A distribution that is ______ has a high peak with most of the scores clustered in the middle of the curve. platykurtic mesokurtic leptokurtic uniform
leptokurtic
The appropriate measure of central tendency for a normally distributed interval variable is which of the following? median mean mode standard deviation
mean
The arithmetic average is also known as the _____. mode median mean central tendency
mean
Which of the following measures of central tendency is the most sensitive to change? mode median mean z score
mean
The mu (µ) and sigma (σ) in a population correspond to the ______. median and variability in a sample mean and standard deviation in a sample mode, mean and mean in a sample mean and range in a sample
mean and standard deviation in a sample
Some researchers argue we have focused too much on statistical significance and we should instead report the ______. descriptive statistics effect size for the sample and the population difference between the sample and the population mean difference and confidence interval for the mean difference
mean difference and confidence interval for the mean difference
In order to compute a one-sample t test we must ____. collect data from a sample of at least 100 measure our variable on an interval or ratio scale randomly select our sample compute the expected frequency of our sample
measure our variable on an interval or ratio scale
The score that cuts the sample in half so that 50% of the sample is at or below that score is the ______. mode median mean range
median
Which of the following is the appropriate measure of central tendency to report with an extremely skewed distribution? mean range mode median
median
A distribution that is ______ has a moderate peak with a gradual increase of frequency toward the middle of the curve. platykurtic mesokurtic leptokurtic uniform
mesokurtic
The most frequent score in the sample is the ______. mode median mean range
mode
Which of the following is an appropriate way to describe a nominal variable? mean median mode standard deviation
mode
A ______ distribution has its tail on the left. normal bimodal positively skewed negatively skewed
negatively skewed
A ______ distribution is shaped like a bell. normal bimodal positively skewed negatively skewed
normal
One of the assumptions of the one-sample t test is ______. nominal data normally distributed population ordinal data sample size of 50 or more
normally distributed population
When we find statistical significance it suggests that our results were ______. due to chance alone and belong to the sampling distribution defined by the alternative hypothesis not due to chance alone and belong to the sampling distribution defined by the alternative hypothesis due to chance alone and belong to the sampling distribution defined by the null hypothesis not due to chance alone and do not belong to the sampling distribution defined by the null hypothesis
not due to chance alone and do not belong to the sampling distribution defined by the null hypothesis
A researcher finds a p value of .17. Using the standard criterion for statistical significance, are the results statistically significant? And as such should the researcher reject or retain the null hypothesis? not statistically significant, retain the null not statistically significant, reject the null statistically significant, retain the null statistically significant, reject the null
not statistically significant, retain the null
The ______ sets up the sampling distribution to which we compare a study's results. alternative hypothesis experimental hypothesis null hypothesis researcher
null hypothesis
The type of pose in one's Facebook picture makes no difference in ratings of narcissism by those viewing the page. This is an example of a(n) ______. null hypothesis alternative hypothesis experimental hypothesis two-tailed hypothesis
null hypothesis
Degrees of freedom represent the ______. number of scores free to vary in a sample estimated sample size percentage of variability accounted for by the population measure distance between the sample mean and population mean divided by the sample size
number of scores free to vary in a sample
What is the difference between coding and numerical coding? coding is used for qualitative data and numerical coding is used for quantitative data numerical coding is more scientific than coding numerical coding includes an extra step of assigning numbers to categories coding does not require you to categorize the data
numerical coding includes an extra step of assigning numbers to categories
Using a provocative pose in one's Facebook picture will result in higher ratings of narcissism by viewers than using a picture that shows a person standing with friends. This is an example of a ______. null hypothesis two-tailed hypothesis one-tailed hypothesis it is not possible to tell the type of hypothesis
one-tailed hypothesis
If we want to find whether the first year class at our college has higher scores on the SAT writing test than the national average for the test, our directional alternative hypothesis (Ha) might state ______. there will be no difference in SAT writing scores between our first year class and the national average there will be a difference in SAT writing scores between our first year class and the national average the SAT writing scores for our first year class will equal the national average for the test our first year class will score higher than the national average for the SAT writing test
our first year class will score higher than the national average for the SAT writing test
When the results for a study fall in the region of rejection it implies that ______. our sample does not belong to the sampling distribution as defined by the null hypothesis and we should reject the null hypothesis our sample does not belong to the sampling distribution as defined by the alternative hypothesis and we should retain the null hypothesis our sample belongs to the sampling distribution and the researcher should retain the null hypothesis there was probably a confound in the study and we should reject the alternative hypothesis
our sample does not belong to the sampling distribution as defined by the null hypothesis and we should reject the null hypothesis
Data points that vary greatly from the main cluster of your distribution are known as ______. outliers standard deviations kurtoses negative skews
outliers
The criterion level that researchers typically use is ______. p < .01 p < .025 p < .05 p < .10
p < .05
Statistics from a population are called ______. measures of central tendency measures of variability parameters descriptive statistics
parameters
A researcher reports that females comprised 49% of the sample. What type of descriptive statistic is the researcher reporting? percentage frequency cumulative percentage central tendency
percentage
The proportion of a score within a sample is the ______. percentage frequency cumulative percentage central tendency
percentage
The criterion level defines the ______. type of hypothesis to be used in a study sampling distribution in a study percentage of the sampling distribution that the participants select for rejecting the null hypothesis percentage of the sampling distribution that the researcher selects for the region of rejection
percentage of the sampling distribution that the researcher selects for the region of rejection
A ______ tells you what percentage of a distribution scored below a specific score. frequency percentile mean standard deviation
percentile
A distribution that is ______ is spread out and relatively flat. platykurtic mesokurtic leptokurtic uniform
platykurtic
The ______ is the distance between the minimum and maximum scores. mode range standard deviation variance
range
Which of the following is a recommended way to maintain the confidentiality of your participants? obtain written informed consent from all participants use pseudonyms for your participants staple the forms with participants' names and other identifying information to their responses report data about participants in aggregate form
report data about participants in aggregate form
When the results for a study fall in the region of acceptance we should ______. reject the null hypothesis retain the null hypothesis retain the alternative hypothesis conclude we have found statistical significance
retain the null hypothesis
All other things being equal we prefer a ______ confidence interval because ______. larger; we are more confident that we have identified the true population mean difference larger; it allows more variation in our sample smaller; it is more likely that we have identified the exact population difference smaller; it suggests our results are closer to the true population mean difference
smaller; it suggests our results are closer to the true population mean difference
Which of the following is a measure of variability? mode median standardized score standard deviation
standard deviation
The order of the hypothesis testing process is described by which of the following? define the sampling distribution, state hypotheses, collect data, compare results to sampling distribution, decide whether to reject or retain the null hypothesis state hypotheses, collect data, define the sampling distribution, decide whether to reject or retain the null hypothesis, compare results to sampling distribution collect data, state hypotheses, compare results to sampling distribution, define the sampling distribution, decide whether to reject or retain the null hypothesis state hypotheses, define the sampling distribution, collect data, compare results to sampling distribution, decide whether to reject or retain the null hypothesis
state hypotheses, define the sampling distribution, collect data, compare results to sampling distribution, decide whether to reject or retain the null hypothesis
A researcher finds a p value of .0. Using the standard criterion for statistical significance, are the results statistically significant? And as such should the researcher reject or retain the null hypothesis? not statistically significant, retain the null not statistically significant, reject the null statistically significant, retain the null statistically significant, reject the null
statistically significant, reject the null
The one-sample t test is computed by ______. subtracting the population mean from the sample mean and dividing by the standard deviation of the sample subtracting the sample mean from the population mean and dividing by the standard deviation of the sample subtracting the population mean from the sample mean and dividing by the estimated standard error of the means subtracting the population mean from the sample mean and dividing by the standard error of the means
subtracting the population mean from the sample mean and dividing by the estimated standard error of the means
One key component in the Discussion section for a study computing a one-sample t test is ______. the problems with past research that led to the current research the t, df, and p values the implications and practical significance of the findings the exact confidence interval(s)
the implications and practical significance of the findings
A researcher found that students who took a research methods course watched more TED talks than those who had not taken a research methods course. In order to evaluate the practical significance of these results, at minimum you would need ______. the p value the proportion of variability in TED talks watched based on having the class or not the mean TED talks watched for each group Cohen's d
the mean TED talks watched for each group
Which of the following descriptive statistics is appropriate to use with ordinal data? the skewness statistic the median the standard deviation the mean
the median
The purpose of inferential statistics is to allow researchers to determine whether ______. the computed statistic is reliable a study has internal validity an outcome can be generalized to samples of different sizes the outcome of a study is typical or unusual for a particular sampling distribution
the outcome of a study is typical or unusual for a particular sampling distribution
A researcher compared the average salary for a sample of first generation college graduates with the average for all college graduates one-year postgraduation and found t(99) = 1.59, p > .05, d = .62. The researcher can conclude ______. the postgraduation salary of first generation students does not differ from that of all college graduates and the effect size is moderate first generation graduates make significantly less than the average for all college graduates, although the effect size is moderate although there is a significant difference between the salaries of first generation graduates and all college graduates, the effect size is weak there is no difference between the average salary of first generation graduates and all college graduates and the effect size makes no difference
the postgraduation salary of first generation students does not differ from that of all college graduates and the effect size is moderate
Dr. Knoital finds t (19) = 4.26, p < .01. He can infer that ______. the sample scored 4.26 points above the population the sample consisted of 20 participants the critical t value is greater than 4.26 the scores of less than 1% of the sample matched the population value
the sample consisted of 20 participants
Which of the following is the most accurate way to determine if our distribution is normal? a histogram the skewness statistic a frequency polygon the standard deviation
the skewness statistic
Variance is ______. the standard deviation squared the square root of the standard deviation the maximum observed score minus the minimum observed score none of these
the standard deviation squared
Practical significance refers to ______. the magnitude or strength of the effect of a variable the usefulness of our results in everyday life our ability to use the results in another study whether the participants found the study useful
the usefulness of our results in everyday life
A week after participating in a workshop on driving safety, we asked a sample of 30 new drivers to report their frequency of texting while driving. We then compared their scores to the national norms for this behavior and found that t(29) = 2.95, p < .01, η2 = .08. We conclude that ______. there is not a significant difference between our sample and the population but the effect size is strong there is not a significant difference between our sample and the population and the effect size is weak there is a significant difference between our sample and the population but the effect size is strong there is a significant difference between our sample and the population and the effect size is weak
there is a significant difference between our sample and the population and the effect size is weak
If we want to find whether the first year class at our college has different scores on the SAT writing test than the national average for the test, our nondirectional alternative hypothesis (Ha) might state ______. there will be no difference in SAT writing scores between our first year class and the national average there will be a difference in SAT writing scores between our first year class and the national average the SAT writing scores for our first year class will equal the national average for the testour first year class will score higher than the national average for the SAT writing test our first year class will score higher than the national average for the SAT writing test
there will be a difference in SAT writing scores between our first year class and the national average
A distribution that is ______ is one in which all ratings or scores have the same frequency. platykurtic mesokurtic leptokurtic uniform
uniform
One appropriate way to code data would be ______. putting every other response into a different coding category using predetermined categories based on theory or research alphabetizing responses randomly placing data into categories
using predetermined categories based on theory or research
The critical t value for p < .05 represents the ______. maximum t value possible for a specific df value that defines the middle 95% of the distribution if the alternative hypothesis is false value that defines the extreme 5% of the distribution defined by the null hypothesis value that must exceed the obtained t value in order to find statistical significance
value that defines the extreme 5% of the distribution defined by the null hypothesis
A researcher compared the average time (in minutes) spent exercising over a week for a sample of seniors in an assisted living facility with the average found from a national survey of those over 65 years of age. She reported (M - µ) = 15.60, 95% CI (10.32, 20.96). You can interpret this as meaning ______. there was no difference between the sample and population means the seniors in the assisted living facility exercised about 16 min less each week than the national average we can be 95% confident that the mean difference (15.60) in exercise minutes between our sample and the national average represents a population whose mean difference falls between 10.32 and 20.96 min the sample in assisted living is exercising significantly less than the average senior
we can be 95% confident that the mean difference (15.60) in exercise minutes between our sample and the national average represents a population whose mean difference falls between 10.32 and 20.96 min
In computing a one-sample t test, we divide the difference between our sample mean and the population mean by the estimated standard error of the means because ______. the standard deviation of the sample is too small to use we do not know the standard deviation of the sampling distribution and have to estimate it using the standard deviation of our sample we do not know the standard deviation of the sampling distribution and have to estimate it using the standard deviation of the population the standard error is greater than the standard deviation of the sample
we do not know the standard deviation of the sampling distribution and have to estimate it using the standard deviation of our sample
Alternative hypotheses always predict ______. a difference between groups no difference between groups a difference between the sample and population what the researcher expects to find
what the researcher expects to find
Individual differences within the sample such as age, gender, and education level can create uncontrolled differences in the measure of our study. This difference is called ______ variance, and it can ______ the power of our study. between-groups; increase independent groups; decrease within-groups or error; decrease between groups; decrease
within-groups or error; decrease
Scores that are expressed in terms of standard deviations from the mean are called ______. z scores p values t scores SD values
z scores
You want to find out whether a significantly greater percentage of students at your university binge watch television series than the national percentage for binge watching. Can you compute a one-sample t test on these data? Yes, you have sample data and a national value for comparison. No, the data are a nominal scale and a t test requires interval or ratio data. No, students cannot be legitimately compared to a national sample of all television viewers. You do not have enough information to make a decision.
No, the data are a nominal scale and a t test requires interval or ratio data.
Researchers examining the impact of aspirin on preventing heart attacks found a very weak effect size but concluded that aspirin was indeed helping to prevent heart attacks and prevent individuals from dying from a heart attack. How is this possible? The results were not statistically significant. The confidence interval was very wide. The effect size was weak but consistent. The impact of aspirin had practical significance.
The impact of aspirin had practical significance.
Which of the following characterizes bar graphs for nominal variables? The shape is usually not meaningful. The frequency of scores is on the x-axis. The categories are on the y-axis. The bars should touch.
The shape is usually not meaningful.
Why do most researchers report the mean and standard deviation instead of the mean and variance? The variance is an unreliable estimate of variability. The variance is out of proportion in relation to the mean. The variance is more difficult to calculate than the standard deviation. The variance does not have an absolute zero.
The variance is out of proportion in relation to the mean.
In the Results section for a study, comparing a sample of scores to a population value, we would include the ______. type of statistical test computed, computed value of the test, its df and significance level, effect size, and practical significance descriptive statistics of our measurement, type of statistical test computed, computed value of the test, its df and significance level, and effect size descriptive statistics of our measurement, type of statistical test computed, computed value of the test, its df and significance level, effect size, and practical significance type of statistical test computed, computed value of the test, its df and significance level, and effect size
descriptive statistics of our measurement, type of statistical test computed, computed value of the test, its df and significance level, and effect size
The Discussion section for a study that computed a one-sample t test should ______. report all the descriptive statistics discuss whether the results are consistent with previous research list all of the statistics that were computed focus on statistical significance and ignore the effect size
discuss whether the results are consistent with previous research
In an experiment examining the effect of type of cell phone ring (popular song vs. piano playing) on distraction, the alternative hypothesis would predict ______. distraction levels will differ for the two types of cell phone rings distraction levels will not differ for the two types of cell phone rings. a correlation between the distraction levels for the types of cell phone rings. none of these represents an alternative hypothesis.
distraction levels will differ for the two types of cell phone rings
In an experiment examining the effect of type of cell phone ring (popular song vs. piano playing) on distraction, the null hypothesis would predict ______. distraction levels will differ for the two types of cell phone rings distraction levels will not differ for the two types of cell phone rings a correlation between the distraction levels for the types of cell phone rings none of these represent an alternative hypothesis
distraction levels will not differ for the two types of cell phone rings
A sampling distribution is created by ______. collecting samples of various sizes from a population drawing many samples of the same size from a population and computing the same statistic for each sample repeating a study multiple times with the same size samples from different populations drawing different size samples from a population and computing their mean
drawing many samples of the same size from a population and computing the same statistic for each sample
How much information about your sample should you include in your write-up? as much as possible just the number of people--otherwise, you run the risk of an ethical violation whatever each individual participant authorizes you to share enough information that another researcher could replicate your study with different participants
enough information that another researcher could replicate your study with different participants
The region of rejection is generally the ______ of the sampling distribution. middle 95% extreme 5% middle 68% middle 50%
extreme 5%
