EPPP Questions Research and Statistics

EPPP Questions Research and Statistics R squared is the: a. coefficient of multiple determination b. coefficient of stability c. coefficient of internal consistency d. silver character on "Star Wars" - a. coefficient of multiple determination When data points are widely scattered around a regression line, this indicates: a. low homoscedasticity b. low correlation coefficient c. low heteroscedasticity d. high heteroscedasticity - b. low correlation coefficient Heteroscedasticity - The scatter is uneven (unequal) at different points on the regression line. For example, there might be high variability around the regression line at low X (predictor) values and low variability around the line at high X values. It is different amounts of scatter, but not high scatter A psychologist in a hospital is conducting research designed to assess the effects of a new drug on the social behavior of psychotic patients. Which of the following would be the best way to decrease experimenter bias in this type of study? a. randomized block design b. a Solomon four-group design c. counterbalancing d. a double-blind study - d. a double blind study Which of the following is a measure of "amount of variability accounted for"? a. Cohen's d b. F-ratio c. alpha d. eta squared - d. eta squared Alpha - Level of significance set by a researcher prior to analyzing data Cohen's d - Used as an index of effect size, but it is a measure of the mean difference between two groups. F-ratio - Statistic calculated when using the analysis of variance The eta coefficient would be used to a. estimate the strength of a nonlinear relationship between two continuous variables b. estimate the strength of the relationship between two rank-ordered variables c. estimate the strength of the relationship between two dichotomous variables d. estimate the strength of the relationship between a dichotomous variable and a continuous variable - a. estimate the strength of a nonlinear relationship between two continuous variables. The most common correlation coefficient - Pearson r Pearson r - Used to measure the relationship between two continuous variables that are related in a linear way Note: eta is used when there is a nonlinear relationship Phi Coefficient - Can be used to measure the correlation between two dichotomous variables (i.e, variables that can take one of two values) Point-Bisceral Correlation - Used to measure the correlation between a dichotomous variable and a continuous variable. Spearmena's rho - Used to measure the correlation between two sets of ranked data You have conducted a study to assess the relationship between salary and job performance, and you find a significant correlation between these two variables. You assistant tells you that the data fail to take into account a $25.00 cost of living raise that every empoyee received. You should: a. assume the correlation will not be affected b. not be concerned since the added amount is too small to make a significant difference c. decide that the raise invalidated the research d. reanalyze the data after the raises have been added to the current salaries. - a. assume the correlation will not be affected Note that you are adding a constant to each score in one of both data sets does not change the relationship A psychological researcher would like to determine what variables best distinguish between patients who benefit from psychotherapy and patients who do not. To identify these variables, the research would most likely use which of the following? a. canonical correlation b. factor analysis c. MANOVA d. discriminant function analysis - d. Factor Analysis - Used to reduce variability in a set of variables to a smaller set of unobserved variables, or factors. For example, factor analysis might be used to confirm a theory that score differences on a variety of intelligence measures can be explained in terms of two factors, verbal intelligence and performance intelligence. Discriminant function analysis - Used to identify variables that distinguish between two or more existing or naturally occurring groups. It would involve collecting data on a variety fo measures and determining which combination of them best predict differences between groups. Canonical Correlation - Technique for assessing the relationship between two sets of variables: used to assess the relationship between multiple predictor and multiple criterion variables MANOVA - -Used in research studies to evaluate the effects of one or more independent variables on multiple (two or more) dependent variables -a type of ANOVA used when two or more dependent variables are included in the study -all of the dependent vairables should be measured on a ratio or interval scale A researcher inquires about the subjects' performance expectations and beliefs about the purpose of the study at the conclusion of the experiment. The researcher finds the subjects actual performance is consistent with their beliefs about expectations when analyzing data. The results of the study may be confounded by: a. changing criteria b. carryover effects c. demand characteristics d. the Hawthorne Effect - c. Demand Characteristics Demand Characteristics - Unintentional cues in the experimental environment or manipulation that affect or account for the results of the study. Subjects may have acted in ways consistent with their expectations rather than simply in response to the experimental manipulation Hawthorne Effect - Occurs when research subjects act differently because of the novelty of the situation and the special attention they receive as research participants. Carryover Effects - Occur in repeated measures designs when the effects of one treatment have an impact on the effects of subsequent treatments. Which of the following is NOT a disadvantage of repeated measures designs? a. practice effects b. carryover effects c. autocorrelation d. multicollinearity - d. multicollinearity Repeated Measures Design AKA - within-subjects design Repeated Measures Design - An experiment using a within-groups design in which participants respond to a dependent variable more than once, after exposure to each level of the independent variable. Disadvantages of Repeated Measures Design - -autocorrelation -practice effects -carryover effects -order effects Autocorrelation - -Means that observations obtained close together in time from the same subjects tend to be highly correlated -When the dependent variable is repeatedly administered to the same subjects, the correlation between measurements of the dependent variable is referred to as autocorrelation . Practice Effects - Improvements in performance resulting from opportunities to perform a behavior repeatedly so that baseline measures can be obtained. order effects - A problem in research design when the results of the study are attributed to the sequence of tasks in the experiment rather than to the independent variable. Multicollinearity - A problem associated with multiple regression which occurs when two or more predictors are highly correlated with each other. Excessive variability in a behavior over time can make it difficulty to obtain accurate information about the effects of an intervention on that behavior. Such variability poses the biggest threat for which of the following research designs? a. split plot b. Solomon four-group c. Factorial d. single-subject - d Single Subject Note that the target behavior is measured at regular intervals throughout the baseline and treatment phases. IF the behavior changes often in strength, intensity, or frequency, it would be difficult to obtain a clear baseline reading or determine if the intervention is having the desired effect Which of the following best describes the use of confidence intervals? a. calculate the test's mean b. calculate the standard deviation c. estimate true scores from obtained scores d. calculate the standard error of measurement - c. estimate true scores from obtained scores Confidence Intervals - Allow us to determine the range within which an examinee's true score one a test is likely to fall, given his or her obtained score Standard Error of Measurement - -The standard deviation of test scores you would have obtained from a single student who took the same test multiple times -tells us how accurately an obtained score on a test estimates someone's true score on that test, if a true score were possible to obtain. -reliability of a test Which of the following would increase the power of a statistical test? a. use of a two tailed test b. increase in alpha c. decrease in alpha d. decrease in sample size - b. Increase in alpha Power - The probability of rejecting the null hypothesis when it is false. OR also said as the probability of correctly identifying that a difference exists. Things that would decrease the test's power - -decreasing alpha - decreasing sample size -use of a two tailed test A percentile rank is