Deck 15: Inferential Statistics

Question 1

A statistic follows a known sampling distribution and is used in significance testing.

A) parameter
B) standard
C) test
D) point

Answer 1

C

Question 2

If the empirical results of your independent samples t test allow you to reject the null hypothesis, this means that

A) one group performed significantly differently than the other group.
B) you have no basis to conclude that your experimental treatment was effective.
C) the independent variable had no effect.
D) you were testing the wrong null hypothesis.

Answer 2

A

Question 3

is to as sample is to statistic

A) Descriptive; inferential
B) Population; parameter
C) Inferential; descriptive
D) Parameter; population

Answer 3

B

Question 4

Suppose you perform an experiment that compares the performance of an experimental group and a control group. You find that the mean of the experimental group is higher than the mean of the control group. Does this prove that the treatment enhanced performance?

A) Yes, because the experimental group did better as a whole than the control group
B) No, because you must compare variances, not means
C) No, because the difference between the group could have occurred by chance, even if it was not very likely i.e., less than .05)
D) Yes, because group averages are the traditional measure to use to compare two groups

Question 5

The use of inferential statistics helps us decide whether to reject the null hypothesis by

A) computing the probability that the alternative hypothesis is true.
B) computing the probability that the alternative hypothesis is false.
C) estimating the probability of obtaining observed group differences by chance alone.
D) computing how large a difference between two means has to be in order to be clinically relevant.

Question 6

The mean of the sampling distribution of the mean is

A) equal to 0.
B) equal to 100.
C) equal to the mean of the population.
D) depends on the size of the sample n).

Question 7

Hypothesis testing is

A) a way of determining ultimate truth.
B) a statistical decision making process.
C) the way to determine if our hypothesis has construct validity.
D) all of the above.

Question 8

Hypothesis testing is a type of inferential statistics. The inference is about

A) characteristics of a sample based on information about the population.
B) probabilities of several specific data points.
C) the amount of variability within groups.
D) characteristics of a population based on sample data.

Question 9

The hypothesis is the hypothesis that the research is trying to provide evidence for in hypothesis testing.

A) null
B) population
C) critical
D) alternative

Question 10

Using the mean of a sample to estimate the mean of a population is called

A) interval estimation.
B) point estimation.
C) sample mean estimation.
D) population mean estimation.

Question 11

When the null hypothesis is rejected, this provides support for

A) your theory.
B) the alternative hypothesis.
C) the idea that the independent variable did not have an effect.
D) both 'b' and 'c'.

Question 12

Rather than using a single score as an estimate of the population mean we may choose to identify a range of values that likely contains the mean value. What is this type of estimation called?

A) Interval estimation
B) Point estimation
C) Mean range estimate
D) Probability estimation

Question 13

The standard deviation of a distribution of means sampling distribution) is called

A) the mean deviation.
B) the standard mean deviation.
C) the standard error.
D) the absolute mean deviation.

Question 14

Which of the following statements is TRUE regarding sampling distributions?

A) The only sampling distribution possible is the sampling distribution of the mean.
B) Sampling distributions can be made for any sample statistic.
C) Sampling distributions are not theoretical probability distributions.
D) Sampling distributions can only be created for samples of N = 40+.

Question 15

The sampling distribution of the mean is important for

A) descriptive statistics.
B) determining what type of inferential test is appropriate.
C) determining if a given sample mean is rare in hypothesis testing.
D) determining the mean of a sample.

Question 16

Other factors remaining constant, what happens as you move from a 95% level of confidence to a 99% level of confidence?

A) The 99% interval is wider
B) The 99% interval is more narrow
C) The 99% interval contains fewer values
D) None of the above

Question 17

The independent samples t test discussed in the text is used to determine whether

A) the experimenter administered different treatments.
B) the difference between two group means is statistically significant.
C) the control group performed as expected.
D) the participants were randomly selected from their respective populations.

Question 18

Hypothesis testing is

A) a method of making inferences about population parameters based on sample data.
B) a method that allows you to "reject" or "fail to reject" the null hypothesis.
C) a method that allows you to "tentatively accept the alternative hypothesis" when the null hypothesis is rejected.
D) all of the above.

Question 19

Which of the following factors strongly affects the width of a confidence interval?

A) sample size
B) sample mean
C) population mean
D) population size

Question 20

When the null hypothesis is rejected,

A) you are stating that there is only one population of research participants.
B) you are stating that the independent variable had no effect on the dependent variable.
C) you are stating that nothing null) was found.
D) you are saying that your finding is statistically significant.

Question 21

Suppose you conduct an experiment and find that the probability of obtaining your results by chance alone was 3% .03). Your decision, if your research is like most psychological research, should be to

A) reject the null hypothesis.
B) accept the null hypothesis.
C) reject the alternative hypothesis.
D) use a different dependent variable.

Question 22

Jessica hypothesizes that her manipulation of temperature in an auditorium will increase the number of students who doze off in a lecture. She is interested in a hypothesis.

A) two tailed
B) uniform
C) directional research
D) preconceived

Question 23

Changing the alpha level from .05 to .01 would

A) decrease the risk of a type I and a type II error.
B) increase the risk of a type I and a type II error.
C) decrease the risk of a type I error and increase the risk of a type II error.
D) increase the risk of a type I error and decrease the risk of a type II error.

Question 24

When considering the decisions errors that can be made in hypothesis testing, one must balance the dangers of Type I versus Type II errors. Usually statistical testing is biased toward avoiding errors.

A) mathematical or computational
B) Type I
C) Type II
D) decisional

Question 25

Dr. Mai conducts a test of a new anti-malaria drug in Africa and concludes that he should reject the null hypothesis because his probability value was .04. He concludes, therefore, that his drug works. In reality, however, it does not work. Dr. Mai has committed a error.

A) logical
B) Type I or false positive)
C) Type II or false negative)
D) statistical

Question 26

Stan is conducting a class research project in which he randomly assigns participants to two groups: one group of participants remains sober during the study and the other group of participants consumes 2 ounces of 75 proof alcohol. The dependent or outcome variable is manual dexterity. What statistical test should Stan use to determine whether the two groups differ in manual dexterity after the manipulation?

A) independent samples t test
B) correlated t test
C) chi square
D) two-way analysis of variance

Question 27

To determine the dose-related effects of amphetamine on maze running, Dr. Symon randomly assigns his rats into four groups. The first group receives no amphetamine, the second group receives 0.5 mg/kg, the third group receives 1.0 mg/kg, and the fourth group receives 2 mg/kg. What initial statistical test should Dr. Symon use to examine the effects of the drug?

A) independent samples t-test
B) one-way repeated measures analysis of variance
C) one-way analysis of variance
D) two-way analysis of variance

Question 28

In statistical testing, the significance level is a statement of

A) the probability
B) the degree of difference between group means.
C) the degree of difference between group standard deviations.
D) the difference between statistical and therapeutic significance of results.
E)g., .05) at which the researcher would consider a sample result to be rare enough to reject the null hypothesis and accept the alternative hypothesis .

Question 29

When the test statistic falls within the region of the sampling distribution the research would the null hypothesis.

A) test; accept
B) critical; reject
C) critical; accept
D) test; reject

Question 30

Regarding the decision to use either a directional or nondirectional alternative hypothesis, most researchers

A) prefer to use directional because of the increase in statistical power.
B) use nondirectional alternative hypotheses because this allows you to reject the null if your finding occurs in the opposite direction from your prediction. That is, it allows you to discover something new.
C) typically use nondirectional alternative hypotheses if the significance level is .05 and directional if it is .01.
D) have no convention at all in practice because there are pros and cons to each choice.

Question 31

A type I error occurs whenever

A) we correctly reject a false null hypothesis.
B) we incorrectly reject a true null hypothesis.
C) we incorrectly fail to reject a false null hypothesis.
D) we correctly fail to reject a false null hypothesis.

Question 32

Dr. Yung tests a new anti-malaria drug in an Asian population and concludes that he cannot reject the null hypothesis, and must conclude he does not have sufficient evidence to conclude that the drug works. In reality, the drug does work. Dr. Yung has committed a error.

A) logical
B) Type I false positive)
C) Type II false negative)
D) statistical

Question 33

Although the change decreases statistical power, you can decrease the risk of making a Type I error simply by

A) examining extraneous variables.
B) making your significance i.e., alpha) level smaller
C) adding more dependent variables to your study.
D) adjust your degrees of freedom.
E)g., change it from .05 to .01).

Question 34

A result that is statistically significant might not have significance. That is, it might not be important in a real world context.

A) pragmatic
B) empirical
C) sensible
D) practical

Question 35

Dr. Beckworth is interested in the effects of tutoring on success in calculus. She also knows that gender is an important issue in math success, so she factors that in as a second independent variable. She randomly assigns males and females to tutoring and no tutoring groups. She studies calculus success in the following four groups of participants: males who have received tutoring, females who have received tutoring, males who have not received tutoring, and females who have not received tutoring. What statistical test should she use to examine her results?

A) independent samples t test
B) t test for correlation coefficient
C) one-way analysis of variance
D) two-way analysis of variance

Question 36

Which of the following is NOT a measure of effect size.

A) Cohen's d
B) eta squared η²)
C) chi-square χ²)
D) omega squared ώ²)

Question 37

In psychological experiments, the generally accepted rule is that the difference between groups is statistically significant if it would have happened by chance only of the time at most.

A) 50 percent
B) 25 percent
C) 5 percent
D) 0 percent

Question 38

A Type I error is known as a and a Type II error is known as a .

A) false positive, false negative
B) false negative, false positive.
C) sample error, population error.
D) population error, sample error.

Question 39

While increasing statistical power is an advantage of directional alternative hypotheses, which one of the following is a disadvantage?

A) Directional hypotheses are hard to use
B) When using directional alternative hypotheses you cannot reject the null if the outcome is large but in the opposite direction of the prediction
C) Directional hypothesis leads to an increase in degrees of freedom
D) There are no disadvantage to using directional hypotheses.

Question 40

is defined s the number of values that are free to vary.

A) degrees of freedom
B) levels of freedom
C) measures of freedom
D) points of freedom

Question 41

Justine conducted an analysis of variance test to determine if children playing video games were more aggressive than those who played either a racing game or a word game. The results of her test are as follows: F2, 47) = 14.80, p = .02. What can you conclude from these findings?

A) her results were not significant
B) her overall result was statistically significant
C) she should conduct post-hoc tests
D) both 'b' and 'c' are true

Question 42

Colin has always heard the saying "blondes have more fun" and he wants to see if it's true. He's not sure what "have more fun" means, so he just decides to find out if blondes are happier. He randomly samples blondes, brunettes, and redheads on his campus and administers a validated happiness scale to each. He conducts 3 separate independent samples t tests on the dependent variable of happiness. What did Colin do wrong?

A) there is no need to conduct the t tests - he can simply compare the sample means of the three groups to see which ones are different
B) a one-way ANOVA would have told him which pairs of means were significantly different.
C) Conducting multiple t tests is inappropriate because it will inflate the risk of a Type I error beyond .05; he should have conducted an ANOVA and conducted appropriately adjusted post-hoc tests
D) nothing; his procedure and analysis are correct

Question 43

What is the main difference between a one-way and a two-way analysis of variance?

A) a one-way analysis of variance is used when you have one independent variable and a two-way analysis of variance is used when you have two independent variables
B) one-way is used when you have matched groups and two-way is used when you have independent groups
C) one uses a one-way when working with an odd number of independent variables and a two-way when working with an even number
D) in a two-way, you compute the F ratio using two different methods, and take the F that is larger

Question 44

How many null hypotheses are tested in a two-way analysis of variance?

A) 1
B) 2
C) 3
D) 4

Question 45

According to the steps of hypothesis testing provided in your text, if you are using an independent samples t test, which of the following describes your procedure:

A) State your null and alternative hypotheses, determine the degrees of freedom, calculate your t test score, reject the null hypothesis if the p value is greater than the significance/alpha level.
B) Calculate your t test score, determine the degrees of freedom, run the statistical program and get the p value, reject the null hypothesis if the p is greater than the alpha level.
C) Select your significance level, determine the degrees of freedom, calculate your t test score, get the critical t value, reject the null hypothesis if the calculated t value is less than the critical t value.
D) State the null and the alternative hypotheses; set the alpha level; conduct the statistical test and obtain the p value based on your empirical data; compare your p value to the alpha level and make a decision 1. reject the null versus 2. fail to reject the null); last, interpret findings. .

Question 46

Justine decides to test the effects of playing violent video games on aggressiveness in 10-year old boys. She decides to have all boys play the three different types of video games in a randomized counterbalanced order. The levels of the within-subjects independent variable are violent, exciting but not violent, and neither exciting nor violent. After playing each video game each child takes a test designed to measure their level of aggression. What is the appropriate type of statistical test for Justine to use?

A) one-way analysis of variance
B) two-way analysis of variance
C) one-way repeated measures analysis of variance
D) two-way mixed model analysis of variance

Question 47

Kirsten runs an experiment for her research methods class in which she studies vocabulary learning in one group of introductory-level French students. At the start of the semester, she assesses these students' knowledge of French vocabulary; she does another assessment at the end of the semester. What statistical test should she use to see whether her group of French students significantly increased their knowledge of French vocabulary?

A) independent samples t test
B) one-way repeated measures analysis of variance
C) one-way analysis of variance
D) two-way analysis of variance

Question 48

You read the following information in the results section of a paper: F2, 15) = 6.36, p > .05. What can you conclude from this statement?

A) that the result was significant
B) that there were 15 participants in the study
C) that an analysis of variance test was used
D) that the researchers should conduct a post-hoc test

Question 49

If the p value associated with the F ratio in the analysis of variance indicates a significant difference in performance across three conditions,

A) we will need to conduct post hoc tests to determine which pairs) of group means is/are significantly different.
B) we need to examine the individual sample group means to see which groups differ significantly.
C) each group differs significantly from all of the others.
D) there are no significant individual group differences.

Question 50

Suppose one experimenter decides to test a treatment with only one experimental group and one control group, while another experimenter tests different levels of the same treatment with three different groups of participants. How will this affect the way in which the two experimenters conduct their statistical analysis?

A) this will not make a difference in how they analyze their data
B) the first should use a lower significance level than the second
C) the second should analyze differences in groups means while the first should analyze differences in group variability
D) the first would conduct a t test, while the second would start with an analysis of variance and if significant) then conduct post hoc tests to determine which groups are significantly different.

Question 51

A three-way ANOVA tests null hypotheses.

A) 3
B) 4
C) 6
D) 7

Question 52

A three-way ANOVA has independent variables.

A) 3
B) 6
C) 9
D) 12

Question 53

Which of the following significance tests would be used to test the significance of a regression coefficient?

A) ANCOVA
B) t test
C) Pearson's r
D) Chi Square

Question 54

What is stated by the null hypothesis for the chi-square test for contingency tables?

A) there is a relationship between the two categorical variables
B) there is no relationship between the two categorical variables
C) both variables have the same frequency distribution
D) the two variables have different frequency distributions

Question 55

The p value associated with a F ratio in the analysis of variance tells us whether there is a significant difference in performance across all of our groups of participants; however, if there are 3 or more groups it does NOT tell us

A) which specific groups) performed significantly better or worse.
B) whether that difference between any two of the means is statistically significant.
C) Both A and B are correct
D) Neither A nor B is correct.

Question 56

When performing a t test for correlation coefficients the null hypothesis would state that

A) there is no correlation between the two variables in the population.
B) there is a significant correlation between the variables in the population.
C) the correlation between the two variables is not equal to zero.
D) the observed correlation between the two variables in the sample is zero.

Question 57

is a variation of ANOVA that allows us to identify and remove the effects of a third variable and increase statistical power.

A) MANOVA
B) ANCOVA
C) Bonferroni
D) Factorial ANOVA

Question 58

The purpose of a post hoc test is to

A) determine which specific treatment conditions are significantly different.
B) determine whether or not a Type I error was made in the ANOVA.
C) determine whether or not a complete ANOVA is justified.
D) to determine the magnitude of an effect.

Question 59

What kind of effect can you examine with a two-way analysis of variance that you could not examine if you conducted multiple one-way analyses?

A) the way in which each treatment effect increases as you add more independent variables
B) the interaction effect of the two ndependent variables
C) the degree to which either independent variable alone changes performance on the dependent variable
D) which groups) performed significantly better or worse than other groups)