Statistics & Research Design Domain Quiz

Type II error (beta)

Stating there is not an effect when one exists (failure to reject null hypothesis when it's false) Rejecting a false null hypothesis is a correct decision.

To increase statistical power, you would:

The ability to reject the null hypothesis is increased by increasing alpha. When the null hypothesis is actually false, increasing the size of alpha also increases power. increase alpha from .01 to .05

construct validity

The extent to which there is evidence that a test measures a particular hypothetical construct. is established when a test measures the intended hypothetical trait

split plot ANOVA

The mixed-design ANOVA is also known as a .... Split-plot is another name for "mixed"; and a researcher would use a split-plot ANOVA when the study uses a mixed design - i.e., it includes both between-groups and within-subjects comparisons.

For ethical reasons, a researcher would be most likely to use which of the following single-subject designs when conducting a study to evaluate the effects of a behavioral treatment for the control of severe self-destructive behaviors?

The multiple baseline design would be an acceptable design in this situation since it does not require withdrawal of the treatment from a baseline once it has been applied to that baseline. When evaluating a treatment to eliminate self-destructive behaviors, a researcher would not want to use a research design that requires removal or withdrawal of a successful treatment during the course of the study.

A type I error occurs when

The results indicate a statistically significant difference when in reality no significant difference exist.

Dr. Bruce Bennett assigns 100 high school students who are either high or low in math aptitude to the traditional instruction, computer-assisted instruction, or combination (traditional plus computer-assisted instruction) group and, after ten weeks of instruction, determines each student's score on a math achievement test. In this study, the independent variable(s) is/are:

This study has two independent variables (type of instruction and math aptitude) and one dependent variable (math achievement test scores). This study is designed to answer the question, "What are the effects of math aptitude and type of instruction on math achievement test scores?"

interaction effects

Two independent variables interact if the effect of one of the variables differs depending on the level of the other variable. the effects of one independent variable at different levels of another independent variable.

Counterbalancing

Which means testing different participants in different orders. For example, some participants would be tested in the attractive defendant condition followed by the unattractive defendant condition, and others would be tested in the unattractive condition followed by the attractive condition.

When using protocol analysis, an individual is asked to:

Protocol analysis was developed by cognitive psychologists as a method for obtaining information about a person's thoughts while solving problems. Protocol analysis involves having the individual "think aloud" while solving a problem while an observer records what the individual says. The observer then analyzes the individual's verbalizations in order to identify the cognitive processes involved in solving the problem.

The Central Limit Theorem makes three predictions about the sampling distribution of means:

(a) if repeated random samples of size N are drawn from the population, as N increases in size, the sampling distribution of means increasingly approaches normal regardless of the shape of the population distribution; (b) the mean of the sampling distribution of means equals the population mean; (c) the standard deviation of the sampling distribution of means equals the population standard deviation divided by the square root of N.

When the correlation between high school students' GPA and amount of time they spend studying each week is ____, this means that about 15% of variability in GPA is accounted for by amount of time spent studying.

0.39 To determine the amount of variability in one variable that is explained by variability in another variable (i.e., the amount of shared variability), you must square the correlation coefficient. Conversely, to determine the correlation coefficient when the shared variability is known, you must calculate the square root of the shared variability.

When a distribution of scores is normally shaped, approximately what percent of scores fall between the mean and the score that is one standard deviation above the mean?

34 When a distribution is normally shaped, approximately 34% of scores fall between the mean and the score that is one standard deviation above the mean. In a normal distribution, approximately 68% of scores fall between the scores that are one standard deviation below and above the mean.

canonical correlation

A correlational technique used when there are two or more X and two or more Y. (Example: The correlation between (age and sex) and (income and life satisfaction)

multitrait-multimethod matrix

A matrix that includes information on correlations between the measure and traits that it should be related to and traits that it should not theoretically be related to. The matrix also includes correlations between the measure of interest and other same-methods measures and measures that use different assessment methods. used to evaluate a measure's construct validity and provides information on the test's convergent and divergent validity.

multitrait-multimethod matrix

A method of evaluating construct validity by simultaneously examining both convergent & divergent evidence by means of a table of correlations between traits & methods

Kruskal-Wallis test

A nonparametric statistical test used to compare three or more unpaired (independent) samples where the outcome is either ordinal or continuous with a skewed distribution. used to analyze rank-ordered data from two or more independent groups.

F ratio

A test statistic used in the analysis of variance; the ratio between the variability observed between treatment groups and the variability observed within treatment groups.

interval recording

A type of behavior recording procedure in which the observation period is divided into a number of consecutive time intervals and the behavior is recorded as occurring or not occurring in each of the intervals.

ANCOVA (analysis of covariance)

A version of the ANOVA used to increase the efficiency of the analysis by statistically removing variability in the DV that is due to an extraneous variable. When using the this test, each person's score on the DV is adjusted on the basis of his or her score on the extraneous variable. The ANCOVA is a type of analysis of variance that allows the researcher to statistically remove the effects of an extraneous variable. Like other forms of the analysis of variance, it is used when data represent an interval or ratio scale of measurement.

If a teacher adds 10 points to each score in a distribution of scores, this will:

Adding a constant to each score in the distribution affects the distribution's mean (the new mean is the original mean plus the constant). However, adding a constant does not affect the variability of scores - i.e., it does not change the range, standard deviation, or variance.

Factorial ANOVA

An Analysis of Variance used when there are two or more independent variables. When there are two, the ANOVA is called a Two-Way ANOVA, three independent variables would use a Three-Way ANOVA, etc. is appropriate for studies assessing the impact of two or more independent variables on a single dependent variable that is measured on an interval or ratio scale.

Logistic Regression

An algebraic function that is used to relate any and all independent variables to the expected dependent variable.

External validity (generalizability)

Refers to whether the results of a study can be generalized to other situations and other people, controlled by: random sampling, situational control, and cause/effect relationships. focuses on the generalizability of one study to other conditions, individuals, etc.

Pearson r correlation

Closer to 1.0 the more positive the correlation; closer to -1.0 the more negative the correlation (example: rate of speech increases, fluency decreases). A number close to zero shows a weak correlation the appropriate correlation coefficient when both variables are continuous (measured on an interval or ratio scale).

Leptokurtic distribution

Distribution curve is very tall, thin and peaked. (Memory: Leptokurtic leaps tall buildings in a single bound.)

Type I error (alpha)

False positive results ex: reject the null hypothesis when you should accept it Retaining a true null hypothesis is a correct decision.

Platykurtic distribution

Flatter and more spread out than a normal curve. (Memory: 'Plat' sounds like 'flat')

mesokurtic distribution

Having a normal bell shaped curve; a normal distribution of scores

What is multiple correlation coefficient?

It measures the strength of association between the independent (explanatory) variables and the dependent variable (the variable we wish to forecast). Its value varies between 0 and 1; the higher value, the stronger the association. Squaring a correlation coefficient produces a measure of shared variability.

When the number of participants in a research study is too small to permit the use of a completely counterbalanced research design, a researcher would use which of the following?

Latin square design When the number of participants does not permit a completely counterbalanced design a researcher may use partial counterbalancing. The Latin square design is a type of partial counterbalancing that helps determine exactly what sequences of a treatment will be administered to different groups of participants.

Statistical regression is a potential threat to a study's internal validity when:

When participants are chosen for inclusion in a study because of their extreme scores on the pretest, it is likely that their scores will "regress to the mean" on the post-test, regardless of the effects of the treatment. This can make it difficult to ascertain the effects of the independent variable on the dependent variable. regression toward the mean is the phenomenon that arises if a sample point of a random variable is extreme, a future point will be closer to the mean or average

To statistically analyze rank-ordered data obtained from two correlated groups, you would use which of the following?

Wilcoxon Knowing that the full name of this test is the Wilcoxon matched-pairs signed-ranks test would have helped you identify it as the correct response. The Wilcoxon is the appropriate test for rank-ordered data that have been obtained from correlated groups (e.g., groups that have been formed by matching participants on the basis of their scores on a pretest or extraneous variable and then randomly assigning members of each matched pair to one of two groups).

One-way ANOVA

a hypothesis test that includes both one nominal independent variable with more than two levels and a scale dependent variable appropriate for studies assessing the impact of a single independent variable on a single dependent variable that is measured on an interval or ratio scale

attrition

a natural loss of individuals is a threat to a study's internal validity. It occurs when participants who drop out of one group differ in a systematic way from those who drop out of another group and this difference affects the study's results.

The Central Limit Theorem predicts that the sampling distribution of means increasingly approaches:

a normal shape as the sample size increases regardless of the shape of the distribution of scores in the population.

meta-analysis

a procedure for statistically combining the results of many different research studies

situational sampling

a sampling technique in which behavior is observed in a variety of settings

Null Hypothesis (H0)

a statement that the performance of treatment groups is so similar that the groups must belong to the same population; a way of saying that the experimental manipulation had no important effect The level of significance (alpha) determines the location of the boundary between the regions of likely and unlikely values in the sampling distribution. When results are significant at the chosen level of significance, this means that the results are in the region of unlikely values and that the null hypothesis should be rejected.

factor analysis

a statistical procedure that identifies clusters of related items (called factors) on a test; used to identify different dimensions of performance that underlie a person's total score. is used to determine the underlying factors (attributes) that are assessed by set of test items, subtests, or other measures.

multiple regression

a statistical technique that computes the relationship between a predictor variable and a criterion variable, controlling for other predictor variables is used to combine scores on several predictors to predict or estimate performance or status on a criterion that is measured on an interval or ratio scale.

phi coefficient

a statistical test designed to evaluate the association between two categorical variables is appropriate when both variables are true dichotomies (e.g., undergraduate degree/no undergraduate degree and employed/unemployed).

An investigator would use the split-plot ANOVA to analyze the data he has collected for which of the following studies?

a study in which each participant received only one level of Variable A but all levels of Variable B Split-plot is another name for "mixed"; and a researcher would use a split-plot ANOVA when the study uses a mixed design - i.e., it includes both between-groups and within-subjects comparisons.

cluster analysis

a technique used to divide an information set into mutually exclusive groups such that the members of each group are as close together as possible to one another and the different groups are as far apart as possible used to "cluster" or categorize individuals or items.

single-sample chi-square

a test of the difference between expected frequencies and obtained frequencies for one categorical variable

Instrumentation

a threat to internal validity when there are inconsistencies in data collection is a threat to internal validity and refers to any change in tests or other measuring devices administered to participants during the course of the study that confounds the study's results.

Discriminant Function Analysis

allows us to determine the predictive ability of each variable alone and in combination with other variables

A factorial design:

always includes two or more independent variables. A factorial research design is any design that includes two or more "factors" (independent variables). The term "factor" in factorial design refers to independent variables.

static group comparison design

an experimental design with two groups, no random assignment, and only a posttest includes two intact groups - one that receives the treatment and one that does not - and involves evaluating the effects of the treatment by comparing the post-test scores of the two groups.

A researcher investigates the nature of client-therapist interactions during the initial therapy session by having graduate students in psychology assume the role of either the therapist or therapy client and role-play the first session of therapy. The researcher's study is best described as which of the following?

analogue In clinical research, an analogue study is a study in which the conditions are in some way an analogue (approximation) of actual clinical practice. In the situation described in this question, the researcher is studying a phenomenon (therapist-client interactions) under conditions that only resemble or approximate actual clinical conditions.

A psychologist decides to use a single-subject design to assess the impact of an educational intervention designed to increase on-task behavior. When conducting her study, the psychologist will measure the participant's on-task behavior:

at regular intervals during the baseline and the treatment phases of the study. The various single-subject research designs share two characteristics: First, each design includes at least one baseline (no treatment) phase and one treatment phase; and, second, the dependent variable is measured at regular intervals during each phase.

A "normal" distribution is:

bell-shaped. By definition, a normal distribution is bell-shaped and, consequently, is also known as the "bell curve." A normal distribution of scores is symmetrical and bell-shaped.

Which of the following methods of sampling involves selecting units of individuals rather than individuals and either including all individuals in those units or a random sample of individuals in those units in the research study?

cluster sampling As its name implies, cluster sampling involves selecting clusters (units) rather than individuals. It is a useful technique when it is not feasible to identify or obtain access to individuals in the entire population. For example, rather than randomly selecting individual high school students from the population of all high school students, it may be necessary to select a sample of high schools and then include all students in those schools or a sample of students from those schools.

A researcher would use "counterbalancing" to:

control multiple treatment interference Counterbalancing involves administering the treatments (different levels of the IV) in different orders to different groups of participants. It helps control multiple treatment interference (also known as carry-over or order effects) that may result when multiple levels of the independent variable(s) are administered to the same participants.

Reversal (Withdrawal) Design

controls for possibility that observed change in AB design due to historical event or other extraneous factor. treatment withdrawn to see if behavior returns to baseline-- also known as ABA design. Better is ABAB design so that participant ultimately receives benefit of treatment require withdrawal of the treatment during the course of the study.

The denominator term in the F-ratio is reduced in magnitude by:

decreasing within-group variability. Within-group variability is a measure of error; and decreasing within-group variability decreases error and the magnitude of the denominator of the F-ratio

A researcher fears that the results of her study have been biased by aspects of the experimental situation that provided participants with cues about the responses or reactions that were expected of them. This researcher is concerned about which of the following?

demand characteristics Cues in the environment that inform participants about the purpose of the study or indicate what behavior is required of them are referred to as demand characteristics.

Mann-Whitney U test

determines whether 2 uncorrelated means differ significantly when data are nonparametric (memory: the 'u' reminds you of 'uncorrelated') is used to analyze rank-ordered data from two independent groups

A correlation coefficient is a measure of the

direction and strength of the relationship between two variables A correlation coefficient of 1 means that for every positive increase in one variable, there is a positive increase of a fixed proportion in the other. For example, shoe sizes go up in (almost) perfect correlation with foot length. A correlation coefficient of -1 means that for every positive increase in one variable, there is a negative decrease of a fixed proportion in the other. For example, the amount of gas in a tank decreases in (almost) perfect correlation with speed. Zero means that for every increase, there isn't a positive or negative increase. The two just aren't related. Correlation coefficient formulas are used to find how strong a relationship is between data. The formulas return a value between -1 and 1, where: 1 indicates a strong positive relationship. -1 indicates a strong negative relationship. A result of zero indicates no relationship at all.

An organizational psychologist has been hired by a manufacturing company to develop a selection battery that will help the company answer the following question: "What group (assembly-line workers or clerical workers) does the job applicant most closely resemble?" Which of the following multivariate techniques would be useful for this purpose?

discriminant analysis A discriminant analysis (also known as discriminant function analysis) involves using scores on two or more predictors to predict an individual's membership in a criterion group - i.e., it is used when the criterion is measured on a nominal scale. There are several methods for combining predictor scores to estimate performance or status on a criterion. When the criterion (Y variable) is group membership, discriminant analysis is an appropriate method.

To reduce the likelihood that experimenter expectancy will bias the results of a research study, you would use which of the following techniques?

double-blind When a double-blind procedure is used, research participants and the experimenter are "blind" to the experimental conditions - i.e., they do not know what group participants are in. Because the researcher does not know whether individual participants are in the experimental or control group, this reduces the likelihood that he/she will provide cues to participants that could bias the results of the study. Experimenter expectancy refers to the bias that results when the experimenter's expectations about the outcomes of the study influence the actual outcomes (e.g., as the result of cues the experimenter inadvertently provides participants).

The analysis of variance produces an F-ratio, which is calculated by dividing MSB by MSW. The denominator of the F-ratio (MSW) is a measure of which of the following?

error only "Mean square within" is a measure of variability within treatment groups and provides an estimate of the effects of error.

Which of the following would be useful for measuring the strength of the relationship between two continuous variables when their relationship is nonlinear?

eta coefficient Eta is also known as the eta coefficient and the correlation ratio and can be used when the relationship between two continuous variables is nonlinear.

Commonly used behavioral observation techniques include

event recording, is useful for behaviors that occur infrequently, have a long duration, and/or leave a permanent record or other product. interval recording, is useful for behaviors that have no clear beginning or end (e.g., on-task behavior) and involves recording whether or not the behavior occurred during each interval. time sampling, latency recording, used to determine how long it takes for a behavior to begin after a specific event has occurred (e.g., after a verbal demand or request has been made). duration recording, indicates how long a behavior lasts and is useful for behaviors that have a clear beginning and end.

Methods of behavioral sampling include

event sampling, the observer records all instances of a particular behavior during a specified time period interval recording, situational sampling,

A bivariate correlation coefficient of .60 indicates ________ times as much shared variability between variables as does a bivariate correlation coefficient of .30.

four A correlation coefficient of .60 indicates that 36% of variability is shared variability, while a correlation of .30 indicates that 9% of variability is shared variability. Since 36% is four times larger than 9%, this means that a coefficient of .60 indicates four times as much shared variability as does a coefficient of .30.

In the context of research design, external validity refers to the researcher's ability to:

generalize the results of the study to other individuals, settings, and conditions Two standards are used to judge the validity of a research study - internal and external validity. External validity refers to the ability to generalize the results of a study to groups, settings, and conditions other than those used in the study. Random selection of participants from the population is one factor that helps ensure adequate external validity in terms of generalizability to other individuals.

An extraneous variable is a variable that is irrelevant to the purpose of a research study but confounds a study's results because it:

has a systematic effect on the study's dependent variable. An extraneous variable is a variable that is not relevant to the purpose of the study but has a systematic effect on the dependent variable and, as a result, can make it difficult to ascertain the effects of the independent variable on the dependent variable.

A researcher would use an ABAB design rather than an AB design in order to control which of the following threats to his study's validity?

history The use of an ABAB design helps determine whether or not an observed change in the dependent variable is due to the independent variable or to an external event (history). Specifically, if the participant exhibits the same change after the independent variable is administered the second time that he/she exhibited after it was administered the first time, that change can be assumed to have been caused by the independent variable rather than by history.

The least squares criterion is used for:

identifying the line of best fit in a regression analysis The least squares criterion is used to locate the regression line in a scatterplot so that the amount of error in prediction is minimized when using the regression line or its equation to predict criterion scores. you want to have the least squares criterion associated with regression analysis

LISREL (linear structural relations analysis) would be the appropriate method of analysis if your causal model:

includes both measured (observed) attributes and latent traits. In contrast to path analysis models, which predict the causal relationships among measured attributes only, LISREL models incorporate both measured attributes and latent traits.

An investigator is studying the impact of stress on the ability to perform a complex mental rotation task. The investigator is trying to eliminate all confounds to the experiment so that he can conclude that increased stress causes decrements in processing speed. What type of validity is the investigator trying to establish?

internal validity The researcher in this experiment is trying to establish a causal relationship between two variables - stress level and processing speed. Internal validity focuses on the causal relationship between independent and dependent variables.

An investigator uses a factorial ANOVA to assess the effects of two independent variables on a dependent variable and obtains significant main and interaction effects. When interpreting the results of her study, the investigator should:

interpret the main effects with caution since the interaction is significant. When the interaction is significant, this means that the effects of one independent variable differ for different levels of another independent variable. Thus, it is not possible to conclude that the independent variable has consistent main effects. For example, a study might find that, overall, Teaching Method #1 is superior to Teaching Method #2 (i.e., there is a main effect of teaching method). However, there might also be an interaction between teaching method and level of self-esteem - for example, Teaching Method #1 might be more effective for students with high and moderate self-esteem, while Teaching Method #2 is more effective for students with low self-esteem. In this situation, the main effect of teaching method would have to be interpreted with caution. Main effects refer to the effects of one independent variable on the dependent variable when considered alone, while interaction effects refer to the effects of one independent variable at different levels of another independent variable.

Which of the following behavioral observation techniques would be most useful for evaluating the extent to which a student remains on-task while his teacher is talking?

interval recording Interval recording is useful for behaviors that have no clear beginning or end (e.g., on-task behavior) and involves recording whether or not the behavior occurred during each interval.

Logistic regression

is a multivariate technique used to identify the combination of predictors that most accurately categorizes individuals into criterion groups.

multiple baseline design

is a single-case design that involves comparing the effects of an intervention across two or more settings, behaviors, or participants.

Diffusion

is a threat to a study's validity when participants in one group (often a no-treatment control group) benefit from the intervention administered to another group - i.e., when participants in the control group inadvertently learn about the treatment or are accidentally exposed to it.

Latin square design

is a type of counterbalanced design that is used to control carryover effects.

t-test for dependent (related) samples

is the appropriate test when the two means to be compared are related, which would be the case when they have been obtained from the same group of participants.

t-test for independent samples

is used to compare the means obtained by two unrelated groups.

A research participant's score on the dependent variable is the amount of time (minutes) it took him or her to complete a task. When assigning scores to participants, the researcher discovers that three of the 60 participants did not complete the task, and he assigns them the maximum amount of time given to participants to work on the task. The best measure of central tendency for the data collected in this study would be which of the following?

median The mean is affected by the magnitude of every score in a distribution, but the median is not. Consequently, in this situation, the median would not be affected by the magnitude of the three missing scores and, therefore, would be a more accurate measure of central tendency. Ordinarily, the best measure of central tendency for interval or ratio data is the arithmetic mean. However, in the situation described in this question, the mean would not be the most accurate measure because the distribution of data includes three scores that are estimates (rather than actual measures) of the value of interest

A psychologist compares the effectiveness of three brief interventions for obsessive-compulsive disorder by randomly assigning adults who have received this diagnosis to one of the three interventions and measuring their symptoms prior to the beginning of treatment and one week, one month, and six months following treatment. The psychologist is using which of the following types of research design?

mixed Type of treatment is a between-groups variable in this study since each participant is assigned to one of the three interventions. In contrast, time is a within-subjects variable since all participants are being evaluated on the dependent variable at four different times. When a study includes both between-groups and within-subjects variables, it is referred to as a mixed design.

Campbell and Stanley (1966) identify which of the following as a direct threat to a study's external (but not internal) validity?

multiple treatment interference Anything that threatens a study's internal validity will also threaten its external validity, but this question is asking about a factor that threatens external validity only. Of the threats listed, only multiple treatment interference is listed by Campbell and Stanley as a direct threat to external validity.

To analyze the relationship between gender and Holland's six occupational themes, the appropriate statistical test would be which of the following?

multiple-sample chi-square The multiple-sample chi-square test is appropriate for studies that include two or more variables and the data to be analyzed represent a nominal scale.

When reviewing the data from her study's two treatment groups, a researcher discovers that the standard deviations of the two groups differ. If the researcher is planning to use the t-test for independent samples to analyze her data, this is:

not likely to be a problem as long as the two groups have the same number of participants. When groups are equal in size, a violation of the assumption of homogeneity of variances will probably not substantially affect the results of the t-test.

As a behavioral observation technique, event sampling (recording) is useful for behaviors that:

occur infrequently or have a long duration. Event sampling involves observing a behavior each time it occurs and is useful for behaviors that occur infrequently, have a long duration, or leave a permanent record.

To test the validity of a model that describes the causal relationships among a set of variables, you would use which of the following techniques?

path analysis used to test causal hypotheses or models. Path analysis and other structural equation modeling techniques are used to determine if sample data fit a predefined model that indicates the direction of the causal links between variables.

When a distribution of scores is flatter than the normal distribution, it is referred to as:

platykurtic "Platy" means flat or broad, and a platykurtic distribution is flatter than the normal distribution

To determine the degree of association between gender and reaction time (as measured in seconds), you would use which of the following bivariate correlation coefficients?

point biserial The point-biserial correlation coefficient is appropriate when one variable is a true dichotomy (e.g., gender) and the other is measured on an interval or ratio scale (in this case, reaction time is measured on a ratio scale).

linear regression

quantifies the relationship between one or more predictor variable(s) and one outcome variable. ... For example, it can be used to quantify the relative impacts of age, gender, and diet (the predictor variables) on height (the outcome variable).

A teacher converts students' raw scores on a 200-item test to percent correct scores. The converted scores represent which scale of measurement?

ratio Percent correct scores represent a ratio scale of measurement - i.e., they have the properties of order, equal intervals, and an absolute 0 point. Consequently, it is possible to conclude that someone who obtains a score of 50% got twice as many items correct as someone whose score is 25%.

F ratio

ratio of the "Mean square between" is the numerator of the F-ratio and provides a measure of variability due to a combination of treatment plus error. divided by... "Mean square within" is a measure of variability within treatment groups and provides an estimate of the effects of error.

main effects

refer to the effects of one independent variable on the dependent variable when considered alone

face validity (content validity)

refers to simply whether the test looks as though its measuring what its supposed to

A researcher makes a Type II error when he/she:

retains the null hypothesis when it is false Retaining a false null hypothesis is referred to as a Type II error.

When using a "multiple-baseline" design, a researcher will:

sequentially apply a treatment to different behaviors or participants When using the multiple-baseline design a treatment is sequentially applied to different baselines - i.e., to different behaviors, to the same behavior in different settings, or to the same behavior performed by different individuals. The multiple-baseline design is a type of single-subject design.

To analyze the data collected in a study that included a single independent variable and three dependent variables, a researcher would use a MANOVA (multivariate analysis of variance) rather than three separate one-way ANOVAs because:

she wants to reduce the probability of making a Type I error. If three separate ANOVAs were conducted at a level of significance of .05 each, the "experimentwise error rate" (probability of making a Type I error) would be increased to approximately .15. By conducting a single MANOVA at the .05 level, the experimentwise error rate remains at .05.

Research participants act as their own no-treatment "controls" in which of the following types of research?

single-subject In research, a control group is a comparison group that does not receive treatment or, alternatively, receives a standard treatment. In single-subject research, a participant's behavior during the baseline (no treatment) and treatment phases is compared. Thus, when using single-subject designs, participants act as their own no-treatment controls.

An analysis of covariance (ANCOVA) is used to:

statistically control variability in the dependent variable due to the effects of an extraneous variable. When using the ANCOVA, the extraneous variable is the "covariate" and its effects on the dependent variable are statistically removed so that it is easier to detect the effects of the independent variable on the dependent variable. The ANCOVA is used to statistically remove the effects of an extraneous variable on the dependent variable.

A researcher would use which of the following techniques when her goal is to evaluate the cause-and-effect or predictive relationships between measured variables and latent factors?

structural equation modeling Structural equation model is used to explore or confirm hypothesized relationships between both measured and latent variables

Trend analysis is a type of analysis of variance that is used when:

study's independent variable is quantitative. Trend analysis is a type of analysis of variance that is used to evaluate linear and nonlinear trends. Trend analysis is used when a study involves a quantitative independent variable, and the researcher wants to determine the shape of the relationship between the independent and dependent variables. The results of the trend analysis indicate whether or not there is a statistically significant linear or nonlinear (quadratic, cubic, quartic) trend.

An educational psychologist conducts a study to assess the effects of an educational program designed to improve the academic performance of children who have been diagnosed as mildly intellectually disabled. To do so, the psychologist matches 30 children with mild intellectual disability on the basis of their IQ test scores and then randomly assigns the members of each matched pair so that one member is assigned to the experimental group and the other is assigned to the control group. She then administers the program to the children in the experimental group and, following completion of the program, administers an achievement test to all children and calculates a total correct score for each child. To assess the effects of the treatment on achievement test scores, the psychologist should use which of the following?

t-test for dependent (related) samples The t-test for dependent (related) samples is used when the data are collected from two correlated groups, which is the case when matching has been used to assign participants to groups. This study includes one independent variable that has two levels (program and no program); the data to be analyzed represent a ratio scale of measurement (total number of correct items); and matching was used to control an extraneous variable (IQ score).

To assess the effectiveness of a behavioral intervention on the caloric intake of young women with anorexia nervosa, you obtain a sample of women who have just received this diagnosis and determine the average number of calories each woman consumes each day during the week before and the week after the intervention is applied. To analyze the data you obtain, you will use which of the following statistical tests?

t-test for dependent samples The t-test for dependent (related) samples is the appropriate test when the two means to be compared are related, which would be the case when they have been obtained from the same group of participants. There are several versions of the t-test, but each is used to compare two means.

When designing a research study, an investigator would be concerned about the impact of pretest sensitization on his study's external validity if:

taking the pretest changes how the participants react to the treatment. Pretest sensitization occurs when the administration of a pretest "sensitizes" participants to the purpose of the research study and, as a result, alters their reaction to the treatment. In this case, the results of the study cannot be generalized to situations in which a pretest is not administered prior to delivery of the treatment. Pretest sensitization (also known as an interaction between testing and treatment) is a potential threat to a study's external validity whenever a study includes administering a pretest.

Analysis of Covariance (ANCOVA)

tests 2 or more groups while controlling for extraneous variables that are called covariates is used to statistically remove the effects of an extraneous variable on the dependent variable.

Squaring the multiple correlation coefficient (R) produces a measure of the:

the amount of variability shared by three or more variables. The multiple correlation coefficient indicates the degree of association between three or more variables. Like any other correlation coefficient, it can be squared in order to obtain a measure of shared variability.

internal validity

the degree to which the effects observed in an experiment are due to the independent variable and not confounds focuses on the causal relationship between independent and dependent variables.

When using stepwise multiple regression, the addition of predictors to the equation is usually based on:

the magnitude of R-squared When using stepwise multiple regression, each predictor is retained in the equation as long as it contributes significantly to the total amount of variability in the criterion that is explained by the combined predictors. The proportion of explained variability is measured by R-squared.

convergent validity

the measure should correlate more strongly with other measures of the same constructs

Event sampling

the observer records all instances of a particular behavior during a specified time period

The correlation between two variables is equal or close to zero when, in a scatterplot:

the range of Y scores at each value of X is equal to the total range of Y scores The correlation for two variables is zero when scores on one variable are not related to scores on the other variable. This is the only answer of those given that describes a lack of correlation between X and Y. When the range of Y scores at each value of X equals the total range of Y scores, the scattergram for X and Y is rectangular in shape, indicating a correlation of (or near) zero.

An assumption underlying the use of regression analysis is that:

the relationship between X and Y is linear. Regression analysis is used to predict Y from a single X, and an assumption is that the relationship between X and Y is linear (i.e., the relationship can be described by a straight line).

In the context of bivariate correlational techniques, "homoscedasticity" refers to:

the same range of Y scores at different values of X Homoscedasticity is one of the assumption for use of the Pearson r and most other correlation coefficients. This assumption is met when the range of Y scores is about the same at every value of X. Homoscedasticity and heteroscedasticity are illustrated in the Statistics and Research Design chapter of the written study materials. Knowing that "homo" means the same or similar may have helped you identify the correct answer to this question even if you aren't familiar with the term "homoscedasticity."

statistical regression

the statistical tendency for extreme scores or extreme behavior to be followed by others that are less extreme and closer to average

"Sampling error" refers to:

the tendency of sample statistics to vary from population parameters due to the effects of random error. Sampling error is due to chance variations that can be expected in samples that have been randomly drawn from the population. Sampling error refers to the discrepancies between sample values and corresponding population values (parameters) that are due to chance factors in the selection process. Note that, by definition, sampling error is random, not systematic.

On the basis of the results of the t-test a psychologist uses to analyze the data she collects, the psychologist concludes that her results are "significant at the .01 level." This means that:

there is a 1% chance that she will incorrectly reject the null hypothesis. Significance at the .01 level means that there is a 1% chance that the obtained value (e.g., the mean or the difference between means) could have occurred by chance alone given the value specified in the null hypothesis. In other words, there is a 1% probability that the null hypothesis will be incorrectly rejected (that a Type I error will be made). Because the results are statistically significant, the psychologist will reject (not retain) the null hypothesis. The level of significance (alpha) determines the location of the boundary between the regions of likely and unlikely values in the sampling distribution. When results are significant at the chosen level of significance, this means that the results are in the region of unlikely values and that the null hypothesis should be rejected.

A researcher reports that she calculated a Cohen's d of .50 for the data she collected in a study that compared two brief treatments for generalized anxiety disorder. This means that:

there was a difference of one-half standard deviation between the means of the two groups. A Cohen's d of .50 indicates that one group obtained a mean that is one-half standard deviation higher than the mean obtained by the other group. Cohen's d is a measure of effect size. It indicates the difference between the means of two groups in terms of standard deviations.

For her dissertation research project, a graduate student administered a measure of state anxiety to a group of college students on five consecutive days before and after the students participated in a stress reduction workshop. The graduate student used which of the following research designs?

time-series The study described in this question involved measuring the dependent variable repeatedly before and after administration of the independent variable. The time-series design is a type of within-subjects design that involves evaluating the effects of an intervention by comparing multiple quantitative observations of participants before and after they are exposed to the intervention.

Autocorrelation would most likely be a problem when an investigator uses which of the following research designs?

time-series time-series design involves non-independent observations -- i.e., it involves measuring the same people repeatedly before and after the intervention is applied.

path analysis

type of research in which a researcher hypothesizes a theoretical causal model and then empirically tests the model used to test a model of the causal links among a set of variables.

The scattergram for scores on a measure of test anxiety and a measure of math achievement reveals that students with moderate levels of anxiety obtain the highest achievement scores, while students with low and high levels of anxiety obtain lower achievement scores. If the Pearson r is used to measure the degree of the association between test anxiety and math achievement scores, the resulting correlation coefficient will:

underestimate the relationship between the variables In this situation, the relationship between the variables is nonlinear (i.e., the assumption of linearity has been violated). As a result, the Pearson r will underestimate the relationship between test anxiety scores and math achievement scores. To identify the correct answer to this question, you have to recognize that the question is describing a nonlinear relationship between anxiety and math achievement and know that an assumption underlying the use of the Pearson r is that the relationship between variables is linear.

t-test for a single sample

used to compare an obtained sample mean to a known population mean.

divergent validity (discriminant validity)

uses measurement approaches that differentiate one construct from others that may be similar