Statistics Exam 3
Dr. Stake concludes that morning stats classes don't differ from afternoon stats classes in average grade. However, there is actually a difference at the population level. What kind of error has she made?
A type-2 error
95% confidence interval used when the alpha level is _____.
0.05
A researcher find that r= 0.7 . What is the effect size for this correlation?
0.49
The probability of a 95% confidence interval including the SAMPLE MEAN is ______.
1
What is the standard deviation of a z-score distribution? What is the variance?
1 and 1
Which of the following has the largest sampling error? 1- 200 with 10 SD 2-100 with 10 SD 3 200 with 5 standard deviation 4- It is impossible to tell.
100 with 10 SD
Each quartile of a distribution of scores contains ______ of all the scores.
25%
What percentage of scores are between the third and fourth quartile?
25%
Which of the following statements about alpha levels of hypotheses test is NOT true? 1- alpha level determines the size of the region of rejection (critical region) 2- alpha level determines whether you are conducting one or two tailed tests 3- alpha level determines the maximum p-value that will allow the researcher to reject the null hypothesis 4-alpha level is usually set at .05 or .01
3- determines one or two tailed test
What cannot be true regarding the median?
60% of scores are above the median
What is true about the difference between interval and ratio scale of measurements?
Interval scales may have a score of 0, but unlike ratio scales it does not represent the true absence of what is being measured.
Which of these is the correct interpretation of the p-value?
It shows the probability that you would have obtained the sample statistic's value or more extreme if the null hypothesis were true.
Dr. Stake concludes that students who study more get higher average statistics grades students who study less, and there is actually a difference at the population level. What kind of error has she made?
No error has been made.
What describes a Type 1 error?
rejecting a true null hypothesis
Which of the following studies would best be analyzed with an independent samples t-test?
You randomly assign children with ADHD to two different groups and then compare the two groups on their academic success in class for a month.
If the z-score for your treated sample mean is NOT in the critical region, then the most appropriate statistical decision is to_______.
retain the null hypothesis
In a hypothesis test, the critical region consists of____.
sample values that are very unlikely to be obtained if the null hypothesis is true
A researcher concludes that a new treatment works significantly better than an existing treatment for improving depression. However, this finding is just unique to the specific sample and does not reflect what would happen in the population. This is an example of a. a type I error b. incorrectly rejecting the null c. a type II error d. a and b are correct
a and b are correct
An independent samples t-test is appropriate for what type of research design?
a between-participants design
A good analogy for a Type 2 error is _____.
a blood test incorrectly indicating that a person does not have a disease
The most important reason for determining a variable's scale of measurement is to _________.
determine which type of statistical analyses are appropriate to use
Why are deviation scores not useful measures of variability in a sample?
deviation scores across a sample will always add up to 0
SD and SE have a ______ relationship.
direct
_______ allows researchers to describe (1) how far mean scores have shifted in the population or (2) the percentage of variance that can be explained by a given variable
effect size
You decide to create a graph with mean GPA on the y-axis and number of hours studied per week on the x-axis. Which of the following would be the most appropriate graph to use?
either a histogram or frequency polygon
Cause/effect questions are the type of questions used by which method of research?
experimental
A Type 2 error could also be called a _____.
false negative
If rejecting the null is thought of as a "positive" test result and failing to reject it a "negative", a Type 1 error could be also be called a_______.
false positive
A type I error means that a researcher has...
falsely concluded that a treatment has an effect
A type II error means that a researcher has....
falsely concluded that a treatment has no effect
A list of all possible values of a variable and the number of times each value occurs is called a ____.
frequency distribution
A group of researchers thought that the amount of time allotted to take a quiz would cause changes in students' frustration levels. What was their dependent variable?
frustration levels
Which dataset would be most appropriate to use a histogram to graph? a. tests given per section of statistics b. graduates from a psychology program by year c. time taken to complete a statistics test d. psychology professors by university
graduates from a psychology program by year
A positively skewed distribution is skewed to the ________.
has a peak in the left of the graph
A negatively skewed distribution is skewed to the _______.
has a peak in the right side of the graph
A frequency distribution shows ________.
how many individuals scored a particular score for a variable that you measured
If you calculate the 95% confidence interval for a sample mean, you know that?
in repeated sampling, the true population mean would fall in the given interval 95% of the time
Dependent variables are ______.
measured for possible changes
Which of the following is most likely to be measured on a ratio scale?
minutes to complete a race
A set of students is surveyed about their major, what is the best measure of central tendency for this variable?
mode
If there is greater variability the scores of a population, you would expect______.
more sampling error
What is the shape of the distribution for the following data: 1, 2, 3, 3, 4, 4, 4, 5, 5, 5, 5, 6, 6, 6, 6, 7?
negatively skewed
Course numbers for classes (MATH 2331, PSYC 2370) are examples of which scale of measurement?
nominal
Whether someone is in the experimental group or the control group in a study represents which scale of measurement?
nominal
Bar graphs are used to represent the frequency for which type of variable?
nominal and ordinal
Mode is best used for _______.
nominal or categorical variables
What scale of measurement does not involve measuring a quantity?
nominal scale
What population parameters must be known to run an independent samples t-test? a. the mean of population 1 b. the mean of population 2 c. the mean and standard deviation of population 2 d. none of the above
none of the above
An example of a variable measured on a ratio scale would be ______.
number of random acts of kindness
Which of the following is an example of a discrete variable? 1- time to complete a test 2- weight of fish caught at a lake 3- number of spotlights in city 4- height of buildings in a town
number of spotlights in a city
If you scored at the 90th percentile on a test, you would know that _________.
only 10% of the students scored higher than you
A group of researchers believed a person's perceived economic status would cause changes in their support for political policies that redistributed income. What was their independent variable?
perceived economic status
Scores above the mean have a ________ z-score.
positive
A doctor collects data from his patients on whether or not they are a smoker to see how it affects their health. Whether or not someone is a smoker is and example of a ___________.
quasi-independent variable
The most powerful way to create groups for an independent samples t-test is to.....
randomly assign participants to two different groups
A researcher will conduct a survey about college students' political orientations. The easiest way to get a representative sample would be to.....
randomly select students to survey
Many physical dimensions such as height, depth, and distance are _______ variable.
ratio
If the null hypothesis is outside the confidence interval, then the decision is to _________.
reject the null
If the z-score for your treated sample mean is the critical region of the sampling distribution, the most appropriate statistical decision is to______.
reject the null hypothesis
Median is used when the distribution will be __________.
skewed
Which of the following doesn't belong with the others? 1- bell-shaped 2- symmetric 3- uniform/rectangular 4- skewed
skewed
Based on the effect size conventions, d=0.18 is a...
small effect size
The variance of a data set is the ________.
square of the standard deviation; squared average of how far all individual scores are away from the mean
The best measure of sampling error is the _________.
standard error of mean
An advantage of the stem and leaf plot over a histogram is that ______.
stem and leaf provides the original individual scores
What do descriptive statistics allow us to do?
summarize the characteristics of a sample of scores
Which of the following is the most likely a continuous variable? -type of therapy -number of children -number of vacations -temperatures in degrees celsius
temperatures in degrees celsius
Standard deviation is best conceptualized as the _________.
the average distance of scores from the mean
A standard deviation is conceptually most similar to what?
the average of all deviations from the mean
If a researcher conducts both a one-tailed and a two-tailed hypothesis test, both with an alpha of 0.5, which is true of the two tests' critical regions?
the critical region is the same size in both tests
The numerator of an independent samples t-test represents what?
the difference between the two sample means in the study
The denominator for a t-test represents what?
the difference between the two sample means you can get by chance
A predicted effect is tested by a null significance hypothesis test, and statistically significant result is found. What would be the conclusion of this test be?
the effect is likely but not certain to exist in the population
A null hypothesis is most likely to be rejected when...
the effect size is large, but there is little variability in the scores
A researcher increases his level of confidence from 90% to 95%. What will happen to the precision of his estimate?
the estimate will be less precise
In a frequency distribution graph, the vertical axis shows_______.
the frequency
What can a box plot tell us about the median?
the heavy horizontal line in the middle of the box; can estimate
What is the main difference between an independent samples t-test and a single sample t-test?
the independent samples test uses sample means to estimate both population means
The correct interpretation of a 95% confidence interval is _______.
the interval has a 95% chance of including the population mean
All other things being equal (e.g., sample size, etc), which of the following is true? a. the larger the absolute value of your test statistic, the smaller your p value b. the larger the absolute value of your test statistic, the larger your p value c. there is no relationship between the test statistic and the p valued.
the larger the absolute value of your test statistic, the smaller your p value
The higher the confidence interval (95 or 99%)....
the larger the range of values as estimates of the population
The midpoint of a confidence interval is always____.
the mean of the sample (single sample study) or the mean difference in the samples (two-group studies)
As the sample size increases, what happens to the mean and standard error of a sampling distribution?
the mean stays the same and the standard error decreases
In a frequency distribution for a person's age, the height of the bar or curved line represents_________.
the number of people of a particular age
If a 95% confidence interval for a two-sample test DOES contain 0_______.
the p value will be more than 0.05
What is the sample mean aften treated as an estimate of?
the population mean
What would be a reasonable null hypothesis for a two-sample t-test?
the population means are the same
If each sample includes only 1 score, the standard error of the sample means would be ______.
the population standard deviation
If each sample includes only one score, the standard error of sample means would be _________.
the population standard deviation
The alpha level determines....
the probability of a type I error
The power of a statistical test is best described as ________.
the probability of finding a significant effect/relationship when one in fact exists in the population
A new instructional method is found to increase average exam grades from 80.20 to 80.21. That's not much of a change, but it was found to be statistically significant. How could that happen.
the sample size was very large
In a frequency distribution graph, the horizontal axis shows_____.
the scores for the variable
The standard error of mean is _________.
the standard deviation of the sample means
What happens to the SE when the sample size increases?
the standard error decreases
The height of each bar on a frequency histogram represents__________.
the total number of participants who scored that particular score
If you sum up the frequency values in a frequency distribution, that number will tell you ?
the total number of scores in your same
A researcher shows that a new treatment significantly reduces depression, with an r-squared of 0.25. What does this mean?
the treatment accounted for 25% of the variance in depression
When the null of an independent t-test is rejected, what is the conclusion being made?
the two populations being compared probably have different means
Which of the following could be a null hypothesis of a two-tailed hypothesis test?
the two populations have the same mean
Which of the following would be the null for a two-tailed hypothesis test? -the two populations have the same mean -the two populations have different means -population 1's mean is equal to or greater than population 2 -population 1's mean is less than population 2's mean
the two populations have the same mean
A two-sample t-test results in an obtained value for t of zero. When will this happen?
the two samples have the same mean
Which of these is NOT true of a sampling distribution?
the variability of the sampling distribution is the same as the variability of a distribution of individual scores from the same population
Which of the following is NOT true of a sampling distribution?
the variability of the sampling distribution is the same as the variability of the individual scores
If a person has a z-score of 0, what does that mean?
their score is equal to the mean score
For an independent samples t-test, the null hypothesis states that.....
there is no difference between the two population means
The null hypothesis for a one-sample test states_____.
there is no difference between two population means
A researcher conducts a study in which one group of students receives encouraging words before a test and a control group receives no encouraging words. She examines the impact of this on test scores. The results are as follows: t(40)=3.00, p=0.004. What is the most appropriate conclusion given an alpha level of 0.05?
there was a significant difference in test scores between the groups
If the same data is displayed in a frequency polygon (line graph) and a bar graph, how will the shapes of the two graphs differ?
there will be no difference in shape
What describes why confidence intervals are often useful?
they provide a range of estimated values for the population mean rather than a single number
Inferential statistics are estimates of unknown information, so they always involve some degree of ___________.
uncertainty
What can a box plot tell us about the maximum score?
uppermost vertical line
The owner of Betty's Machetes conducts a survey with a sample of 25 of her customers to see the mean (average) satisfaction rating for their last machete purchased. If she wants to see if she can generalize the results to the larger population of customers, she should _______.
use both descriptive and inferential statistics
If you choose a sample at random from a population, itt will most likely be _____.
very close to the population mean
When we use inferential statistics to arrive at a conclusion in our study_______.
we are confident of our conclusion but realize that we are not 100% sure
Which of the following is a continuous variable? 1- weight 2- placement in a race 3- number of traffic tickets received in a year 4- college major
weight
What is the assumption of homogeneity of variance being violated look like?
when one group has a narrow distribution of scores and the other group has a very wide distribution of scores
When would you be least likely to use inferential statistics?
when you're only interested in the scores you've measured
The interquartile range for a set of scores tells you _________.
where the middle 50% of the scores lie around the median
You just completed a study in which you concluded no significant difference in introversion personality scores between greek and non-greek students. It is possible that...
you are making a type II error
If the confidence interval contains 0, what does this mean?
you would reject the null hypothesis
Suppose you find out your z-score was +3.00. What does this mean?
your score was higher than most of the other students in the class
The distribution of sample means (for a specific sample size) consists of _________.
all the sample means that could be obtained (for a specific sample size)
Confidence intervals are most often used as_____.
an inferential statistic to supplement null hypothesis testing
A professor wants to represent how many people are morning versus evening people, what kind of graph would he use?
bar graph
What disadvantage does a lab study have?
behavior may be less realistic
A statistics instructor pulls out 10 of her students' exams from a pile of 50 to start grading. Because the suspense is killing her, she calculates the mean exam score for these 10 students to get a better idea of how the whole class might do. The instructor has used....
both descriptive and inferential statistics
What can a box plot tell us about the mean?
can estimate, but cannot be for sure
What can a box plot tell us about the mode?
cannot estimate
An advantage of experimental over correlation research is _______.
clearer statements of causality can be made
Anytime a researcher conducts a study and uses inferential statistics, it is possible will______.
commit both types of errors or make no error at all
To assess students' interests in class lectures, an instructor tracks daily attendance. "Interest" would be an example of what type of variable?
continuous, quantitative
A researcher has participants rate their overall happiness on a scale of 1 to 10 to see how this relates to their GPA. We would describe the underlying variable of happiness as _________ and the specific way we are measuring it as __________.
continuous; discrete
A good example of descriptive statistics would be when you
create a bar graph that shows student average course evaluations for male and female intrusctors
Other things help constant, as you increase sample size, the shape of the sampling distribution of the mean will _____.
decrease
A researcher calculates the average reaction time (in milliseconds) for a visual stimulus for and for an auditory stimulus. This is an example of ________.
descriptive statistics
A researcher counts the number of faculty and the number of students who stop at a stop sign on campus. This is an example of______.
descriptive statistics
Central Limit Theorem
-sample size of 30 or greater will result in a normal distribution
What happens to the SE when the sample size increases?
SE decreases
Based on the effect size conventions, d = 0.60 is a A) large effect size B) small effect size C) medium effect size
C.) medium effect size
A researcher selects two samples of 25 people each. In the first sample the population mean was 32 and the variance was 8. In the second population the mean was 4 and the variance was 8. Which sample has the largest standard error of the mean.
None, the samples will have the same standard error.
Calculation for SE
SD/ square root of sample mean
Which of the following defines the expected differences between a population mean and the mean of a sample randomly drawn from it?
SE (standard error)
A therapist is investigating the impact of a new treatment for depression compared to an old one. What would be the alternative hypothesis?
The new treatment produces different results than the old one.
A therapist is investigating the impact of a new treatment for depression compared to an old one. Which would accurately represent the null hypothesis?
The new treatment produces results that are similar to the old treatment
If all possible random samples of size=10 are selected from a population of scores that is normally distributed with mean of 80 and SD of 10, what is the expected shape of the distribution of sample means?
The sample means will form a normal distribution because the parent population is normal
If all the possible random samples of size= 30 from a population, then what is the shape of the expected distribution of sample means?
The sample means will form a normally distributed distribution
A researcher says dogs have a high IQ compared to cats, but those results were just unique to that sample and doesn't reflect what would happen in the population. What error is being made?
Type 1 error
You just completed a study in which you conducted that female students has significant higher GPAs than male students. It is possible that you are making a ______ error,
Type 1 error
What information can measures of effect size give us that hypothesis testing alone does not? a. the magnitude of the difference between populations b. the probability there's a difference between populations c. the true means for each population d. the true standard deviations for each population
a. the magnitude of the difference between populations
In a frequency distribution for a person's age, the height of the bar or curved line represents? a. the number of people of a particular age b. the age of the individual c. the average age of individuals d. none of the above
a. the number of people of a particular age
A z-score of z=2.00 indicates a position in a distribution that is ___________.
above the mean by a distance equal to 2 standard deviations
A researcher is interested in the political orientation of UCA students. He distributes the survey to 50 students. What is the population?
all UCA students
The type of treatment used in a research study describes the _______.
independent variable
The term "inferential" in inferential statistics is appropriate because we ________.
infer about the characteristics of a population based only on a sample
Hypothesis testing is a(n)
inferential method for determining whether a population parameter has a particular value
Most often, when you arrive at a conclusion about your study's hypothesis, the last step in the statistical analysis requires ________.
inferential statistics
Testing hypotheses is generally done through some form of _______.
inferential statistics
What term is used to denote statistical procedures that use sample data to make conclusions about the larger population from which the sample was taken?
inferential statistics
The variability between the third and first quartile is considered as __________.
interquartile range
Based on the effect size conventions, d = 0.99 is a
large effect size
The larger the level of confidence, the ____ precise the interval estimate.
less
If there is less variability of scores in your population, then you would expect_______.
less sampling error
If there is less variability of scores in your population, you would expect____.
less sampling error
What can a box plot tell us about the minimum score?
lowermost vertical line