research methods final
1. Describe the simple interrupted time series design.
a. A quasi experimental design in which participants are tested on many occasions, several before and several after the occurrence of the quasi independent variable (13.2.1)
1. What are experimenter expectancy effects, and how do researchers minimize them?
a. A situation in which a researchers expectations about the outcome of a study influence participants reactions. Participants will try to find out what the research is about but by not allowing them to know, this lessens the chance of getting answers that the particpants think the researchers expects. (9.6.1)
1. Explain the rationale behind time series designs.
a. It allows researchers to see whether changes in the dependent variable coincide precisely with the introduction of the quasi independent variable (13.2)
1. Why should researchers never use the one-group pretest-posttest design?
a. It fails to eliminate most threats to internal validity (13.1.1)
1. What is a factorial design? Why are factorial designs used more frequently than one-way designs?
a. It is an experiment design in which two or more independent variables are manipulated. It is used more because They are able to test multiple independent variables. (10.2)
1. If you reject the null hypothesis (and conclude that the independent variable has an effect), what is the likelihood that you made a Type I error?
a. It is depending on what the alpha level is set to. If we reject the null with an alpha level of .01 then there is only a 1% chance of having a type 1 error. (11.2.2)
1. How does the Bonferroni adjustment control for a Type I error?
a. It protects against inflated type 1 error when many tests are conducted by dividing the alpha level by the number of tests. (12.2.1)
1. What is a Type I error? What is so bad about making a Type I error?
a. It will cause researchers to conclude that the independent variable has an effect when it really does not. (12.2)
1. If the IV has absolutely no effect on the DV, will the means of the experimental conditions be the same? Why or why not?
a. It will only differ if there is error variance. (12.3)
1. How do researchers maintain the confidentiality of participants' responses?
a. Leave the participants anonymous, data systems, changing details of the case. (15.8)
1. Does a nonequivalent groups pre-test-posttest design eliminate local history as a potential explanation of the results? Explain.
a. No it does not because since there are multiple groups, something may occur in one group that does not occur in another. (13.1.2)
1. Is the use of single-case studies a new approach to research in psychology? Explain.
a. No, it has a very long history in behavioral research. Only after the 1930s did researchers begin to use larger groups. (14)
1. Why do researchers use factor analysis?
a. To identify the underlying dimensions or factors that account for the relationships that are observed among the variables. (8.5)
1. Why do researchers use deception? Also, why do some people object to the use of deception in research?
a. To prevent participants from learning the true purpose of a study so that their behavior will not be artificially affected. It is objected because they believe lying and deceit are immoral acts. Also because even if deception can be justified it may lead to undesireable consequences. (15.7.1)
1. What are nested designs? What are the key benefits of using nested designs? Also, please say what special problems nested designs create for researchers.
A research design in which participants are drawn from various groups. The responses of participants who come from a single group are not independent of one another causing the problem of nonindependence. It also gives researchers the ability to study variables that operate at different levels of analysis.
1. What are generational (or cohort) effects, and why do they sometimes create a problem in
Differences among people of various ages that are due to the different conditions under which each generation grew up rather than age differences (13.4)
1. In an experiment with 2 independent variables (e.g., A and B), an ANOVA partitions the total variance into four components. What are they?
Error variance, main effect of A, main effect of B, a x b interaction (12.4.5)
1. Imagine that you conducted a factor analysis on a set of variables that were uncorrelated with one another. How many factors would you expect to find? Please also say why.
I would find as many factors as there are variables because if the variables are not at all related, there are no underlying factors that account for their interrelationships.
How does a cross-lagged panel correlation design provide evidence to support a causal link between two variables
It does this by following a correlation calculated at two different times. It does not suggest that one thing directly causes another but it helps show that something may be casually related to another by something such as interest
1. If the calculated value of F is found to be significant for the main effect of an independent variable with more than two levels, what tests does the researcher conduct? Why are such tests not necessary if the independent variable has only 2 levels?
Its not necessary for tests in which there are only 2 levels because the significant f test tells us that the 2 means differ significantly and we can look at the means to understand the direction and size of the difference between them (12.5.1)
1. What is multiple regression analysis?
Regression analyses in which more than one predictor variable is used to predict the dependent, outcome, or criterion variable.
1. When do researchers use regression analysis?
They are used to extend the findings of correlational research. These equations are used to provide us with a mathematical description of how the variables are related and allow us to predict on variable from the others.
1. Why do researchers use multi-level modeling?
They us it to combat the issues that are presented with nested designs. It allows them to tease apart the influences by analyzing variable operating at all levels of the nested structure simultaneously.
1. How many independent variables are involved in a 3 x 3 factorial design? How many levels are there of each variable? How many experimental conditions are there? Draw the design.
a. 2 independent variables are used in a 3x3. Each variable has 3 levels. 9 conditions. (10.2.1)
1. How many main effects and interactions can be tested in a 2 x 2 design, a 3 x 3 design, and a 2 x 2 x 3 design?
a. 2x2= two main effects and one interaction, 3x3= two main effects, 2 interactions, 2x2x3= three main effects and 3 interactions (10.3.3)
1. What is a cost-benefit analysis? What factors should be considered when doing a cost-benefit analysis of a proposed study?
a. A method of making decisions in which the potential costs and risks of a study are weighed against its likely benefits. Basic knowledge, improvement of research or assessment techniques, practical outcomes, benefits for researchers, benefits for research participants. (15.2.1)
1. Distinguish between one-tailed and two-tailed t-tests.
a. A one tailed test has the entire alpha level in one tail whereas a two tailed test has half of the alpha level in each tail. (11.3)
1. What is the purpose of the Institutional Review Board?
a. To ensure maximum protection for participants (15.2.3)
1. Discuss the relative advantages and disadvantages between within-subjects designs and between-subjects designs.
a. Advantage of within subject designs is that it is more powerful than a between subject design. They also require fewer participants. But, order effects can happen when participants behavior is affected by the order in which they participate in the various conditions of the experiment. Practice effects and fatigue effects can also happen. (9.3)
1. What are demand characteristics? Also, should demand characteristics be eliminated or strengthened in an experiment? Either way, please also say why.
a. Aspects of a studys procedure that inadvertently indicate to participants how they are expected to respond. They should be eliminated because authentic responses are needed for the research to get true results. (9.6.2)
1. Why do researchers use ANOVA rather than t-tests to analyze data from experiments that have more than two groups?
a. Because it analyzes differences between all condition means in an experiment simultaneously rather than testing the difference between each pair of means. (12.2.1)
1. When a longitudinal design reveals a change in behavior over time, why can we not conclude that the change is due to development?
a. Because it could be from impaired memories and the researcher could be misled into concluding that memory generally declines in old age. This causes a problem because people who are of different ages today may differ in ways that have nothing to do with age. (13.4)
1. Why may researchers not offer potential participants large incentives (e.g., a large amount of money) to participate in research?
a. Because it may influence how a participants acts and attract the wrong people (15.3.2)
1. Looking at the table of critical values, you will see that, for any particular degree of freedom, the critical value of t is larger when the alpha level is .01 than when it is 05. Please briefly explain why.
a. Because that means that the null hypothesis is only rejected 1% of the time so the value needs to be even stronger for it to reject the hypothesis whereas .05 it is more likely to reject the hypothesis. (12.1)
1. In analyzing the data from an experiment, why is it not sufficient simply to examine the condition means to see whether they differ?
a. Because we may not know for sure if the independent variable caused the difference so further analysis should be conducted. (11.1)
1. Discuss the pros and cons of using nonhuman animals in behavioral research.
a. Cons- mistreted, not properly housed, against their will Pros- contributed to important research, handled with care, break through for animal health as well
1. Distinguish between a longitudinal design and a cross-sectional design.
a. Cross sectional designs compare groups of different ages at a single point in time whereas longitudinal studies a group overtime (13.4)
1. Distinguish among deontology, skepticism, and utilitarianism as approaches to making decisions.
a. Deontology is An ethical approach maintaining that right and wrong should be judged according to a universal moral code. Skepticism is an ethical approach that denies the existence of concrete and inviolate moral codes. Utilitarian is an ethical approach maintaining that right and wrong should be judged in terms of the consequences of ones actions. (15.1)
1. Discuss the advantages and disadvantages of single-case experimental designs, relative to group designs.
a. Disadvantages- fluctuating responses, looseness of using visual inspection. Advantages- simplicity of visuals, better control (14.2.4)
1. When are tests of simple main effects used, and what do researchers learn from them?
a. Effect of one IV at a particular level of the other IV. How the independent variables influence each other. (12.5.2)
1. What is the name of the statistic used in an ANOVA?
a. F test (12.4.4)
1. If the calculated value of t is less than the critical value, do you reject or fail to reject the null hypothesis? Please also say why.
a. Fail to reject the hypothesis because the difference is not significant enough to say there was an effect. (11.2.5)
1. How do researchers analyze the data from single-case experiments?
a. Graphic analysis, the visual inspection of graphs of the data to determine whether the independent variable affected the participants behavior (14.2.4)
1. Distinguish between an independent variable and a subject variable.
a. Independent variables are being manipulated in an experiment whereas subject variables are not experimentally manipulated and reflect existing characteristics of the participants. (9.2.2)
1. Distinguish between an independent variable and a participant (or subject) variable.
a. Independent variables can be manipulated by the researchers while the participant variable is a characteristic of the participants that are not able to be manipulated. (10.4)
1. Which of these types of variance (interparticipant or intraparticipant) is more closely related to error variance in group experimental designs? Also, please say why.
a. Interparticipant variance because it is not the kind of variability that behavioral researchers are trying to understand. It is closely related to the differences in participants. (14.1.1)
1. What is the difference between interparticipant and intraparticipant variance?
a. Interparticipant variance is variability among the responses of the participants in a particular experimental condition whereas intraparticipant variance is variability among the responses of a participant when tested more than once in a particular experimental condition. (14.1.1)
1. Which type of these types of variance is of primary interest to researchers who conduct single-case experiments?
a. Intraparticipant variance (14.1.1)
1. Distinguish between nomothetic and idiographic approaches to behavioral science
a. Nomothetic approach is research that seeks to establish general principles and broad generalizations, often contracted with the idiographic approach. Idiographic approach is research that describes, analyzes and attempts to understand the behavior of individual participants. (14)
1. What are order effects, and how does counterbalancing help research deal with them?
a. Order effects may occur when participants responses are affected by the order in which they receive the levels of the independent variable which may lead researchers to conclude that a particular level of the independent variable had an effect when really the effect was produced by administering levels of the independent variable in a particular order. Counterbalancing fixes this by having different participants receive the levels of the independent variable in different orders. (9.3)
1. Explain the difference between rejecting the null hypothesis and failing to reject the null hypothesis. Also, please say in which case the experimenter concludes that the independent variable has an effect on the dependent variable.
a. Rejecting the null hypothesis means that the independent variable effected the dependent variable or that there was a change somewhere in the experiment. Failing to reject the null hypothesis means that the null hypothesis was correct and there was no change with the dependent variable. (11.2.1)
1. Which type of error do researchers usually regard as more serious, Type I or Type II? Please also say why.
a. Researchers try to lower their chances of getting a type 1 error because then they know if there was really no effect with the experiment. (11.2.2)
1. What are four primary reasons that behavioral researchers use case studies?
a. Study operant processes in humans and nonhumans, study effects of various schedules of reinforncement and punishment, study psychophysiological processes and brain activity, study sensation and perception(14.2.5)
1. An ANOVA for a one-way design partitions the total variance in a set of data into two components. What are they?
a. Systematic variance and error variance (12.4)
1. What is an interaction?
a. The combined effect of two or more independent variables such that the effect of one independent variable differs across the levels of the other independent variables. (10.3.2)
1. What is a main effect?
a. The effect of a particular independent variable, ignoring the effects of other independent variables in the experiment. (10.3.1)
1. Distinguish between the null hypothesis and the experimental (or research) hypothesis.
a. The null hypothesis is the hypothesis that the independent variable will not have an effect. The experimental hypothesis Is that the independent variable will have an effect on the dependent variable. (11.2.1)
1. According to the principle of informed consent, what must participants be told before soliciting their agreement to participate in a study?
a. The purpose of the research, expected duration, and procedures. Their right to decline to participate and to withdraw once it has begun. The foreseeable consequences of declining or withdrawing. Reasonably foreseeable factors that may be expected to influence their willingness to participate. Any prospective research benefits. Limits of confidentiality. Incentives for participation. Whom to contact for questions about the research and researchers rights. (15.3.1)
1. How do quasi-experimental designs differ from true experiments? Under what circumstances would a researcher use a quasi-experimental rather than an experimental design?
a. The researcher cannot assign participants to conditions and cannot manipulate the independent variable. It is used in real world questions when things cant be addressed within the narrow strictures of experimentation (13.1)
1. A well-designed experiment possesses what three characteristics?
a. The researcher must vary at least one independent variable to assess its effects on participants responses, must have the power to assign particpants to the various experimental conditions in a way that ensures their initial equivalence, must control all extraneous variables that may influence participants responses. (9.1)
1. What is program evaluation? Why do program evaluators rely heavily on quasi-experimental designs in their work?
a. The use of behavioral research methods to assess the effects of programs on behavior. They use these because these types of programs are usually not under researchers control so they must use quasi experimental approaches to evaluate their effectiveness. (13.6)
1. Describe a 2 x 2 x 3 factorial design. How many independent variables are involved, and how many levels are there of each variable? How many experimental conditions are in a 2 x 2 x 3 factorial design?
a. There are 3 independent variables, the first independent variable has 2 levels, the second IV has 2 levels, the third IV has 3 levels. There are 12 conditions. (10.2.2)
1. In general, how much mental or physical risk is permissible in research?
a. There should only be under minimal risk to participants (15.6)
1. What advantage do experiments have over descriptive and correlational studies?
a. They allow researchers to draw conclusions about cause and effect relationships. (9.1)
1. Discuss the trade-off between internal validity and external validity. Also, please say which is more important, and why.
a. They are inversely related, the higher internal validity tends to produce lower external validity and vice versa. Internal validity is more important because if it is weak then they cannot draw confident conclusions about the effects of the independent variable. (9.8)
1. What is the rationale behind the ABA design?
a. To attempt to demonstrate that an independent variable affects behavior (14.2.1)
1. Distinguish among treatment variance, confound variance, and error variance. Also, which is worse - confound variance or error variance - please also say why.
a. Treatment variance is the portion of the total variance in a set of scores that is due to the independent variable. Confound variance is the portion in total variance that is due to extraneous variables that differ systematically between the experimental groups. Error variance is the variance left over after taking away variance of the dependent variable. Confound variance is worse because it needs to be eliminated at all costs because it is impossible for researchers to distinguish treatment variance from confound. (9.4.1)
1. Distinguish between a Type I error and a Type II error.
a. Type 2 error is when the null hypothesis is false and they fail to reject the null hypothesis. Type 1 error is when the null hypothesis is true and the null hypothesis is rejected. (11.2.2)
1. Under what circumstances is an ABA design relatively useless as a way of testing the effects of an IV?
a. When the IV produces permanent changes in a participants behavior, changes that do not reverse when the IV is removed (14.2.1)
1. If you want to have 20 participants in each experimental condition, how many participants will you need for a 2 x 3 x 3 completely randomized factorial design? How many participants will you need for a 2 x 3 x 3 repeated measures factorial design?
a. You would need 360 participants. Repeated you would only need 20. (10.3.3)
1. How many levels of the IV are there in an ABACADA design?
three
1. How many conditions are there in the simplest possible experiment?
two