Stats for review Flashcards
An educational psychologist has data on 12 different variables collected from students in the graduating high school class of the preceding year, including high school GPA, SAT scores, teacher ratings, and various tests of motivation and personality. She is interested in using these measures to predict success in college. In this instance, the psychologist would use stepwise multiple regression in order to
Select one:
A. develop a predictive equation using all 12 measures.
B. determine the optimal set of measures to use.
C. determine if mean differences on the 12 measures significantly differ from each other.
D. identify any cultural bias in the predictor or criterion measure.
Correct Answer is: B
Stepwise multiple regression is a variation of multiple regression. In multiple regression, one develops an equation that uses two or more predictor variables to predict scores on a criterion (outcome) variable. Stepwise multiple regression involves starting with a large set of predictors and reducing them to a smaller set that provides significant predictive value without providing overlapping information. Specifically, the goal is to get predictors that have high enough correlations with the criterion and low enough correlations with each to be included. If predictors have high correlations with each other, they are basically providing overlapping information and there is no point in including them. The two variations of this technique are forward stepwise multiple regression and backwards stepwise multiple regression. In forward stepwise multiple regression, you choose the predictor with the highest correlation with the criterion, you add one predictor at a time, and then run a significance test to see if the added predictor significantly increases the combined predictive value of the overall equation. The process stops when an added predictor fails to significantly increase predictive value. In backwards stepwise regression, you start with all predictors, and remove predictors, starting with the one that is least correlated with the criterion. This process ends when removal of a predictor causes a significant decrease in the ability of the equation to predict values on the criterion.
Which of the following techniques would be appropriate when multiple predictors will be used to predict a score on a single criterion?
Select one:
A. multiple regression analysis
B. multiple discriminant function analysis
C. principal components analysis
D. linear regression analysis
Correct Answer is: A
When multiple predictors will be used to predict a score on a single criterion, multiple regression is appropriate. Discriminant function analysis is used to determine which continuous variables discriminate between two or more naturally occurring groups.
Multiple discriminant function analysis, an extension of discriminant function analysis, involves using multiple predictors to sort individuals into one of three or more criterion groups.
Principle components analysis, similar to factor analysis, is used to determine the variables or components that account for the total variance in test scores.
When a single predictor is used to predict or estimate a score on a single criterion, linear regression is appropriate.
The use of "pooled variance" in statistics assumes that: Select one: A. the sample sizes are equal B. the sample variances are equal C. the population sizes are equal D. the population variances are equal
Correct Answer is: D
Pooled variance is the weighted average variance for each group. They are “weighted” based on the number of subjects in each group. Use of a pooled variance assumes that the population variances are approximately the same, even though the sample variances differ
Which of the following is NOT generally considered a direct threat to external validity?
Select one:
A. order effects
B. hawthorne Effect
C. interaction between selection and treatment
D. history
Correct Answer is: D
Distinguishing between internal and external threats to validity can be difficult. Indeed, some experts disagree on how to categorize some of them. However, all of the choices except “history” are generally considered to be threats to external validity.
Order effects* (also known as carryover effects) occurs in repeated measures designs, or in studies in which the same subjects are exposed to more than one treatment. For example, in a study on the effects of marital therapy interventions, couples are given relaxation training followed by communication training. If significant improvement occurs, it may be due to relaxation training preceding communication training; therefore, the results could not be generalized to situations in which subjects only receive communication training.
The Hawthorne effect* occurs when subjects behave differently due to the fact that they are participating in research. Obviously this threatens external validity since the results cannot be generalized to real-life situations in which people are not participating in research.
Interaction between selection and treatment* refers to when a treatment has different effects depending on the selection of subjects. For example, studies that only use undergraduate students (as many studies do) might not generalize to non-undergraduate students (* incorrect options).
Finally, history refers to an external event, other than the experimental treatment, that affects scores on the DV. This is primarily considered a threat to internal validity. For example, if a study on the effects of a new treatment for depression began several weeks before the events on “9-11” and concluded several weeks after “9-11,” the results might indicate that the new treatment is not effective. However, this might not be a valid conclusion due to the effects of history.
A test measuring verbal fluency is administered to 250 college students, and a split-half reliability coefficient is obtained. If the same test instead had been administered to 250 students aged 12-21, the obtained reliability coefficient probably would have Select one: A. been higher. B. been lower. C. remained about the same. D. moved from negative to positive.
One factor that affects any correlation coefficient, including a reliability coefficient, is the range of scores. If the range of scores is restricted on either or both sets of scores, the correlation coefficient will be lowered. The two sets of scores involved in a split-half reliability coefficient are scores obtained by the same group of individuals on two different halves on the test. Originally, the test was administered to only college students. In the second scenario, the test was administered to a broader range of students.
A psychologist uses a two-group pretest/posttest design to evaluate the effects of a new treatment. She obtains the following data:
PreTest Post Test
Group 1 Mean 13.4, SD 1.2 Mean 19.8, SD 1.5
Group 2 Mean 19.5, SD 1.5 Mean 21.7, SD 1.9
The biggest threat to this study's internal validity is Select one: A. reactivity. B. test x treatment. C. selection. D. history
Correct Answer is: C
In this study the means of the two groups are very different initially (Pretest), which will make it hard to interpret the results. When internal validity is threatened by initial group differences, this threat is called selection. Note that the term selection is misleading because it actually refers to assignment. If assignment was random, we would expect the pretest scores for Groups 1 and 2 to be approximately equal, which they are not, 13.4 and 19.5, respectively.
You are investigating whether there is a relationship between the number of years one has been smoking cigarettes and the number of psychotherapy sessions required to quit smoking. The best statistical method to analyze the results is: Select one: A. chi-square B. Pearson r C. t-test for independent samples D. multiple regression analysis
Correct Answer is: B
In this case, you are attempting to assess the relationship between two variables that are measured on a continuous (interval or ratio) scale. The Pearson r allows you to do this. The Pearson r is the bivariate (i.e., for two variables) correlation coefficient used when variables are measured on an interval or ratio scale.
According to the central limit theorem,
Select one:
A. as sample size increases, the shape of a sample distribution becomes more normal.
B. as the size of a sampling distribution of means increases, its distribution becomes more normal.
C. as sample size increases, the shape of a sampling distribution of means becomes more normal.
D. as sample size increases, the shape of a sampling distribution of means approximates the shape of the population distribution.
Correct Answer is: C
According to the central limit theorem, the shape of a sampling distribution of means approaches normality as sample size increases. The central limit theorem is covered in the Advanced Statistics section of your materials, and you should study it after you have a reasonably solid grasp of the material presented in the rest of the section.
Which of the following is NOT a disadvantage of a repeated measures design? Select one: A. multicollinearity B. autocorrelation C. practice effects D. carryover effects
Correct Answer is: A
A “repeated measures” design, sometimes referred to as a “within-subjects design,” uses more than one measurement of a given variable for each subject. For example, longitudinal studies and pre-test/post-test designs measure the same subjects multiple times. These designs have several disadvantages including: “Autocorrelation”, which means that observations obtained close together in time from the same subjects tend to be highly correlated. This violates the independence of observations assumption made by statistical tests. “Practice effects”, “carryover effects”, and “order effects” all refer to systematic changes in subjects’ performance due to prior exposure to a treatment condition or measurement ( incorrect options) .
However, multicollinearity refers to a problem associated with multiple regression which occurs when two or more predictors are highly correlated with each other.
A psychologist believes that physical exercise can reduce a person's anxiety level, which reduces the strength of substance cravings in people recovering from substance dependence. According to this hypothesis anxiety is a: Select one: A. suppressor variable B. mediator variable C. moderator variable D. criterion contaminator
Correct Answer is: B
A mediator variable is a variable that accounts for or explains the effects of an IV on a DV. That is, the IV affects the mediator variable, which affects the DV. In this example, the IV is exercise, the mediator variable is anxiety, which explains how the DV, substance craving, is reduced.
A moderator variable is similar to a mediator variable, but a moderator variable only influences the strength of the relationship between two other variables, it doesn’t fully account for it. For example, if a job selection test has different validity coefficients for different ethnic groups, ethnicity would be a moderator variable because it influences the relationship between the test (predictor) and actual job performance (the criterion) but it does not fully account for the relationship.
A suppressor variable reduces or conceals the relationship between variables. For example, the K scale in the MMPI-2 is a suppressor variable because it measures defensiveness, which can suppress the scores on the clinical scales. The K scale is, therefore, used as a correction factor for some of the clinical scales.
Criterion contamination is the artificial inflation of validity which can occur when raters subjectively score ratees on a criterion measure after they have been informed how the ratees scored on the predictor.
A colleague of yours is interested in studying the effects of aging on IQ scores. He consults with you for some ideas regarding how to proceed with this research. Which of the following types of research designs would you recommend? Select one: A. longitudinal B. cross-sectional C. cross-sequential D. multiple baseline
Correct Answer is: C
The colleague is interested in conducting developmental research, in which the effects of development (e.g., aging) on a dependent variable (in this case, IQ scores) are investigated. Longitudinal, cross-sectional, and cross-sequential are all types of developmental research designs. Of these, cross-sequential research is the strongest from a scientific point of view. Cross-sequential research is a combination of cross-sectional and longitudinal research. In cross-sequential research, as in cross-sectional research, subjects are divided into age groups (e.g., young, middle-aged, and old). And, as in longitudinal research, subjects are assessed repeatedly on the dependent variable over time. Because cross-sequential research combines the methodology of the two strategies, it is not associated with the limitations of one or the other.
A factorial design, unlike a two group design:
Select one:
A. allows more independent variables to be studied
B. requires a larger sample
C. shows the effect of an independent variable on the dependent variable
D. cannot detect a curvilinear relationship between variables
Correct Answer is: A
In a two group design, one group is exposed to a treatment and another, control group, is not exposed or gets a different treatment. The results of both groups are tested in order to compare the effects of treatment. A factorial design is a design with more than one independent variable. In this design, the independent variables are simultaneously investigated to determine the independent and interactive influence they have on the dependent variable. The effect of each independent variable on the dependent variable is called a main effect and in a factorial design there are as many main effects as there are independent variables. An interaction effect between two or more independent variables occurs when the effect that one independent variable has on the dependent variable depends on the level of the other independent variable.
At least three levels must be used to predict a curvilinear relationship.
A 10-year-old child is administered the WISC-III and obtains a score of 140 Full Scale IQ. If she is retested at the age of 16, her IQ score will most likely be: Select one: A. higher B. lower C. the same D. impossible to predict
Correct Answer is: B
This question was a little tricky in that it appears to be about the reliability of IQ scores over time, when it is really a statistics question. The WISC-III does have very good reliability over time and, if the IQ score was in the normal range, we could predict that it would stay the same over time. However, a score of 140 on the WISC-III is extremely high (classified as “very superior”) and would, therefore, likely be lower upon retesting due to regression to the mean – which is the tendency of extreme scores to be less extreme upon retesting.
All of the following are measures of variability except: Select one: A. variance B. standard error C. range D. standard deviation
Correct Answer is: B Variability represents the amount of difference found in responses from a population or sample on a topic being investigated. Variance*, range*, and standard deviation* all reflect the variability in the data (* incorrect options). Standard error (of measurement) is not a measure of variability. It is a statistic indicating the amount of difference in results that is accounted for by flaws or "noise" in the instrument used to measure a variable.
While studying the use of journaling in the treatment of depression, a researcher finds only individuals with good writing ability benefit from journaling. Writing ability is a(n): Select one: A. outcome variable B. mediating variable C. moderator variable D. feedback variable
Porrect Answer is: C
The strength of the relationship between the independent and dependent variables is affected by a moderator variable. Writing ability is moderating the effects of journaling on the treatment of depression.
Outcome variable* is another term for dependent variable. A mediating variable* is affected by the independent variable and affects the dependent. It is responsible for an observed relationship between an independent variable and a dependent (outcome) variable. A feedback variable* is an unrelated term (* incorrect options).