Download Statistical Hypothesis Testing: t-Test & Between-Subjects ANOVA and more Exams Psychology in PDF only on Docsity!
PSYCH STATS MIDTERM 2
If you are using a parametric statistical test, then the hypotheses of the test will be about _______________. A. statistics calculated from samples. B. measures of central tendency or variability of a sample. C. the characteristics of a population such as the population mean. D. either the mode or median of a sample. - C. the characteristics of a population such as the population mean. You are testing a hypothesis about how much time preschool children watch television per day. You hypothesize that the population mean is 212 minutes. Which of the following would be an appropriate null hypothesis for such a study? A. H0: μ = 212 minutes. B. H0: μ ≠ 212 minutes. C. H0: X = 212 minutes. D. H0: X ≠ 212 minutes. - B. H0: μ ≠ 212 minutes. If an experimenter sets α equal to .01, then she is defining a "statistically rare" event as ______________. A. an event occurring more than one time in 100 if the alternative hypothesis is true. B. an event occurring more than one time in 100 if the null hypothesis is true. C. an event occurring one or fewer times in 100 times if the alternative hypothesis is true. D. an event occurring one or fewer times in 100 times if the null hypothesis is true. - D. an event occurring one or fewer times in 100 times if the null hypothesis is true. In statistical hypothesis testing, a rejection region represents the values of a test statistic that have a probability ____________________. A. equal to or less than α if H1 is true.
B. equal to or less than α if H0 is true. C. greater than α if H1 is true. D. greater than α if H0 is true. - B. equal to or less than α if H0 is true. An experimenter tested a sample mean against a hypothesized population mean. He obtained zobs = +2.41. zcrit for a two-tailed test at the .05 level = 1.96. Based on this information, the experimenter should have _____________________. A. accepted H0 and rejected H1. B. rejected both H0 and H1. C. not accepted H0 and accepted H1. D. rejected H0 and accepted H1. - D. rejected H0 and accepted H1. If a difference between a sample mean and a hypothesized population mean is statistically significant, then ___________________. A. the population mean must be larger than the sample mean. B. H0 was not rejected and H1 was not accepted. C. H0 was rejected and H1 was accepted. D. the value of α was incorrectly set. - C. H0 was rejected and H1 was accepted. An experimenter uses a one-sample t test to test a sample mean against a hypothesized population mean. The sample mean was based on 81 scores. The df for this t test are ________________________. A. 82 B. 81 C. 80 D. 79 - C. 80
C. 40; rejected D. 40; not rejected - A. 41; rejected Which of the following situations represents a Type II error in statistical hypothesis testing? A. H1 is true and H0 is not rejected. B. H0 is true and it is not rejected. C. H1 is accepted when it is true and H0 is false. D. H1 is true and H0 is rejected. - A. H1 is true and H0 is not rejected. The value of _____________ is the probability of making a Type II error in a statistical hypothesis test. A. 1−β B. β C. α D. 1− α - B. β An experimenter obtains subjects for her experiment by asking people she knows to participate in her experiment. This form of obtaining subjects is called __________sampling. A. simple random B. convenience C. stratified random D. selective - B. convenience A psychologist was interested in determining the difference in ease between reading materials on a computer screen and on paper. One group of subjects was given a set of materials to read on a computer screen while a second group of subjects was given the same material to read in a printed
booklet. The psychologist measured the time each group took to read the materials. The levels of the independent variable in this experiment are: A. The difference in the ways the material was presented for reading. B. the amount of time each group takes to read the material. C. the ease in reading material from a computer screen. D. the actual material given to the subjects to read. - A. The difference in the ways the material was presented for reading. A psychologist was interested in determining the difference in ease between reading materials on a computer screen and on paper. One group of subjects was given a set of materials to read on a computer screen while the second group of subjects was given the same material to read in a printed booklet. The group reading the material on the computer screen was strongly encouraged to read the material as quickly as possible. The psychologist did not give the same encouragement to the group reading the material in booklet form. In this experiment, the difference in levels of encouragement given one group compared to the other is ______________. A. the independent variable. B. the dependent variable. C. the experimental treatment. D. a confounding variable. - D. a confounding variable. A psychologist was interested in determining the difference in ease between reading materials on a computer screen and on paper. One group of subjects was given a set of materials to read on a computer screen while the second group of subjects was given the same material to read in a printed booklet. Suppose the psychologist found that the mean amount of time to read the material was less for the booklet than for the material presented on the computer screen. In order to decide that the difference in the means was due to the way in which the material was read, the experimenter will need to determine A. how much of a difference in the means might be expected from the effect of the dependent variable. B. how much the modes in each group might bias the results. C. how much of a difference in the means might be expected from the effect of the independent variable. D. how much of a difference in the means might be expecte - D. how much of a difference in the means might be expected from sampling error alone.
D. sample means do not differ significantly. - A. variances of the populations sampled are equal. The power of a statistical test is defined as the probability of rejecting H0 when it is ________and H1 is __________. A. true; true B. true; false C. false; true D. false; false - C. false; true Suppose a researcher conducts an experiment in which there is great deal of variability in the dependent variable measured. This large variability will ________________. A. increase the probability of a Type I error. B. increase the power of the statistical test used. C. allow the experimenter to use a smaller sample of subjects. D. decrease the power of the statistical test used. - D. decrease the power of the statistical test used. The value of η2 in an experiment provides a measure of the __________________. A. the amount of error variation in the scores. B. effect size of the independent variable. C. effect size of the dependent variable. D. how large a sample of subjects is needed in the experiment - B. effect size of the independent variable. An experimenter summarized the results of a t-test for two independent groups as t(64) = +1.723, p
.05. From this summary you would know that the total number of subjects in the study was (N) ___________ and the null hypothesis was __________. A. 64; rejected
B. 64; not rejected C. 66; rejected D. 66; not rejected - D. 66; not rejected An experimenter uses a within-subjects design to test a research hypothesis. In this design ___________________. A. one group of subjects is created and given both levels of the independent variable. B. two equivalent groups of subjects are created and given separate levels of the IV. C. more subjects are needed than would be needed for a between-subjects design. D. one level of the independent variable is given to one group of subjects. - A. one group of subjects is created and given both levels of the independent variable. An experimenter used a one-factor multilevel design in her research. This design has ________________. A. two independent variables and two levels of each variable. B. one independent variable and three or more levels of that independent variable. C. one independent variable and one level of that variable. D. three or more independent variables. - B. one independent variable and three or more levels of that independent variable. If a sociologist uses a one-factor between-subjects analysis of variance, he or she will obtain the F statistic by dividing __________by___________. A. MSA; MSError B. MSTotal; MSError C. dfA; MSError. D. MSError; MSA. - A. MSA; MSError A mean squared is obtained in a one-factor between-subjects analysis of variance by ____________.
Suppose SSTotal = 185.00, SSA = 80, SSError = 105, dfTotal = 39, dfA = 4, and dfError = 35 in a one-factor between-subjects analysis of variance. MSA for this analysis is then ______________. A. 3. B. 0. C. 20. D. 46.25 - C. 20. A psychologist used a one-factor between-subjects analysis of variance on the scores of an experiment. If the independent variable in this experiment has an effect on the scores, then MSA should be ___________________ MSError and the value of F should be ___________________. A. about equal to; about 1. B. less than; less than 1. C. less than; greater than 1. D. greater than; greater than 1.00 - D. greater than; greater than 1. Suppose an experimenter failed to reject H0 in a one-factor between-subjects analysis of variance. He or she would then conclude that the _________________. A. sample means differ because of the effect of the independent variable. B. sample means differ more than would be expected from sampling error alone. C. variances of each group are equal. D. sample means differ because of sampling error. - D. sample means differ because of sampling error. Multiple comparison tests are used to find which ____ differ significantly from each other in a one-factor multilevel design. A. population variances B. grand means
C. group means D. mean squares - C. group means The ____ in an experiment is the probability of making at least one Type I error when performing statistical tests on an experiment. A. error rate B. relative error frequency C. error probability D. mistake rate - A. error rate Which of the following situations would require the use of a multiple comparison test? A. Four levels of an independent variable are manipulated in an experiment and Fobs is nonsignificant. B. Two levels of an independent variable are manipulated in an experiment and Fobs is nonsignificant. C. Two levels of an independent variable are manipulated in an experiment and Fobs is statistically significant. D. Four levels of an independent variable are manipulated in an experiment and Fobs is statistically significant. - D. Four levels of an independent variable are manipulated in an experiment and Fobs is statistically significant. A researcher reported the results of a one-factor between-subjects analysis of variance as F(2, 60) = 4.63, p < .05. From this report you would know that a total of __________ subjects were used in the experiment and the null hypothesis was __________. A. 62; rejected. B. 63; rejected. C. 63; not rejected. D. 62; not rejected. - B. 63; rejected.
