Lecture Notes Research Chaper 1-9

1

Dr. William Kritsonis Educational Research Lecture Notes Chapter 1 – Introduction to Educational Research 1.

Writing daily observations, without interpretation, is an example of description research.

2.

Action research is typically conducted by administrators, teachers, counselors, and other professionals to answer questions to specifically help them solve local problems.

3.

We should trust research findings after different researchers have found the same findings.

4.

Basic research is the development of a solid foundation of reliable knowledge.

5.

Deductive reasoning is the process of drawing a specific conclusion from a set of premises.

6.

The rule of parsimony is the idea that when selecting between two different theories with equal explanatory value, one should select the theory that is the most simple, concise, and succinct.

7.

Research that is done to examine the findings of someone else using the “same variables but different people” is an example of replication research.

2

8.

Empiricism is the idea that knowledge comes from experience.

9.

According to many authorities, the five key objectives of science include the following: exploration, description, explanation, prediction, influence.

10. A

researcher designs an experiment to test how variables interact to influence how well children learn spelling words. The primary purpose of the study is explanation.

11. There

is a set of churches in the U.S. where part of the service involves snake handling. The researcher wants to find out why the people attending these churches do this and how they feel and think about it. The primary purpose of the study is exploration.

12. Characteristics of good theories and explanations include the following: a) It is parsimonious b) It is testable c) It is general enough to apply to more than one place, situation, or person

3

13. Basic assumptions of science including the following: a) Science cannot provide answers to all questions b) It is possible to distinguish between more and less plausible claims c) Researchers should follow certain agreed upon norms and practices Note: Science is not best at solving value conflicts, such as whether abortion is immoral. 14. Orientational

research is focused on collecting information to help a researcher advance an ideological or political position.

15.

The inductive “scientific method” involves observation, data collection, looking for patterns, and theoretical constructs.

16. The

rationalism approach to knowledge generation uses reasoning skills as the primary source.

17. The

deductive method is a scientific method that is a top-down or confirmatory approach to research.

18. The

inductive method is a scientific method that is a bottom-up or generative approach to research.

4 19. The

deductive method focuses on testing hypotheses developed by theories.

20. The

inductive method often focuses on generating new hypotheses and theories.

21. a) b) c)

The following statements are true of a theory: It most simply means “explanation” It answers the “how” and “why” questions It can be a well developed explanatory system

5

Dr. William Kritsonis Educational Research Lecture Notes Chapter 2 – Quantitative, Qualitative, Mixed Research 1.

Mixed research is based on the pragmatic view of reality.

2.

Qualitative research is least concerned about generalizing its findings.

3.

Quantitative research attempts to confirm the researcher’s hypotheses.

4.

A variable is a condition or characteristics that can take on different values or categories.

5.

An independent variable is presumed to cause a change in another variable.

6.

Common characteristics of experimental research include the following: a) it relies primarily on the collection of numerical data b) it can produce important knowledge about cause and effect c) it uses the deductive scientific method Note: Experimental research is rarely conducted in a controlled setting or environment.

6 7.

Qualitative research is often exploratory. Common characteristics of qualitative research include the following: a) it relies on the collection of non-numerical data such as words and pictures b) it is used to generate hypotheses and develop theory about phenomena in the world c) it uses the inductive scientific method

Note: Qualitative research typically is not used when a great deal is already known about the topic of interest.

8.

Experimental research provides the strongest evidence about the existence of cause-and-effect relationships.

9.

Manipulation of the independent variable is the key defining characteristic of experimental research.

10. In

causal-comparative and correlation research, random assignment to groups is never possible and the researcher cannot manipulate the independent variable.

11. Manipulation

of the independent variable is the defining characteristics of experimental research.

12. A

positive correlation is present when two variables move in the same direction.

7 13. Mixed

method research uses the qualitative paradigm for one phase and the quantitative paradigm for another phase.

14. Mixed

model research uses both qualitative and quantitative research within a stage or across two of the stages in the research process.

15. Historical

research is done to understand an event from the past.

16. Experimental

research occurs when the researcher manipulates the independent variable.

17. The following includes examples of quantitative variables: a) age, temperature, income, height b) grade point average, anxiety level, reading performance Note: Remember, gender, religion, ethnic group are not quantitative variables 18. A

constant is the opposite of a variable.

19. Causal-comparative

research is the type of nonexperimental research in which the primary independent variable of interest is categorical.

20. Religion

variable.

can best be described as a categorical

8

21. In

research, something that does not “vary” is called a constant.

22. When

interpreting a correlation coefficient expressing the relationship between two variables, it is very important to avoid jumping to the conclusion of causality.

23. A

researcher studies achievement by children in poorly funded elementary schools. She/he develops a model that supports parent involvement as an important variable. She/he believes that parent involvement has an impact on children by increasing their motivation to do school work. In the model, greater parent involvement leads to higher student motivation, which in turn creates higher student achievement.

Student motivation is what kind of variable in this study? Answer: Mediating or intervening variable. 24. The

strongest evidence for causality comes from the experimental research method.

25. Which correlation is the strongest? a) +10 b) -.95 c) +.90 Answer d) -1.00

9

Dr. William Kritsonis Educational Research Lecture Notes Chapter 3 – Developing Research Questions and Proposal Preparation 1.

A good qualitative problem statement conveys a sense of emerging design.

2.

The “tool” function of theory is to suggest new relationships and make new predictions.

3.

The statement of purpose in a research study should identify the intent or objective of the study.

4.

Why is the statement “What are the effects of extracurricular activities on cognitive development of school age children” not a good statement of a quantitative research question?

Answer: Because the statement was not specific enough to provide an understanding of the variables being investigated. 5. A qualitative research question asks a question about some process, or phenomenon to be explored; is generally an open-ended question.

10

6. In developing a research idea, the following flowchart is recommended: Research topic, research problem, research purpose, research question, hypothesis. 7.

It is essential to evaluate the quality of internet resources because information obtained via the internet ranges from very poor to very good.

8. Steps included in planning a research study include the following: a) Identifying a researchable problem b) A review of current research c) Developing a research plan Note: Conducting a meta-analysis of the research is not included in planning a research study. 9. Sources of researchable problems can include: a) Researchers’ own experiences b) Practical issues that require solutions c) Theory and past research 10. A

key characteristic of past research that guides researchers in new research questions is that studies typically generate more research questions than they answer.

11. Making

predictions is a function of theory.

11

12. A review of the literature prior to formulating research questions allows the researcher to do the following: a) To become familiar with prior research on the phenomenon of interest b) To identify potential methodological problems in the research area c) To develop a list of pertinent problems relative to the phenomenon of interest 13. Sometimes

a comprehensive review of the literature prior to data collection is not recommended by grounded theorists.

14. Issues of values and morality such as the correctness of having prayer in schools can’t be empirically research. 15. The following are databases containing information to be used during the literature review: a) ERIC b) PsychINFO c) SocioFILE 16. Computer

database searches can be done with a computer with CD-Rom drive, at the library, and online.

17. The feasibility of a research study should be considered in light of the following: a) Cost and time required to conduct the study b) Skills required of the researcher c) Potential ethical concerns

12

18. A formal statement of the research question or “purpose of research study” generally is made after the literature review and will help guide the research process. 19. The

following qualitative research purpose statement is well stated:

The focus of the present study was to explore distressing and nurturing encounters of patients with caregivers and to ascertain the meanings that are engendered by such encounters. The study was conducted on one of the surgical units and the obstetrical/gynecological unit of a 374-bed community hospital. 20. Which of the following quantitative research questions is superior? a) “What is the effect of participation in various extracurricular activities on academic performance?” b) “What effect does playing high school football have on students’ overall grade point average during the football season?”

13

21. A statement of the quantitative research question should include the following: a) Extend the statement of purpose by specifying exactly the question(s) the research will address b) Help the research in selecting appropriate participants, research methods, measures, and materials c) Specify the variables of interest 22. The

research participants are described in detail in the method section of the research plan.

23. Research

hypotheses are statements of predicted relationships between variables. Research hypotheses are stated such that they can be confirmed or refuted.

24. Hypotheses

in qualitative research studies usually are often generated as the data are collected, interpreted, and analyzed.

25. A research plan should be detailed, given to others for review and comments, and sets out the rationale for a research study.

14

26. The Method section of the research plan typically specifies the following: a) The research participants b) The apparatus, instruments, and materials for the research study c) The planned research procedures 27. The Introduction section of the research plan supplies the following information: a) Gives an overview of the prior relevant studies b) Contains a statement of the purpose of the study c) Concludes with a statement of the research questions and, for quantitative research, it includes the research hypothesis 28. The following are sources for research ideas: a) Everyday life b) Practical issues c) Past research d) Theory

15

Dr. William Kritsonis Educational Research Lecture Notes Chapter 4 – Research Ethics 1. Ethics is the set of principles and guidelines that help us to uphold the things we value. 2.

A description of the purpose of the research is necessary in obtaining informed consent.

3. When doing research, the following need to be obtained: a) Informed consent form the parent or guardian b) Consent from the child if he or she is capable 4. If there is deception in a study, the participants may need to be debriefed. The use of deception must be outweighed by other benefits of the study. 5.

Having full anonymity rather than just confidentiality cannot be done in qualitative studies conducted in the field.

6.

Utilitarianism is the primary approach that is used by the Institutional Review Board to assess the ethical acceptability of a research study.

16

7. Deontological approaches emphasize that ethical issues should be judged on the basis of some universal code. 8.

Telling participants they must continue until the study has been completed is not an ethnical guideline for conducting research with humans.

9.

Ethical skepticism emphasizes research ethics should be a matter of the individual’s conscience.

10. Confidentiality

means that the participant’s identity, although known to the researcher, is not revealed to anyone outside of the researcher and his or her staff.

11. Misrepresenting

and creating fraudulent data is dishonest. Misrepresenting data can be difficult to detect. Breaking confidentiality should be avoided.

12. Ideally,

the research participant’s identity is not known to the researcher. This is called: Anonymity.

13. Utilitarianism is the primary approach used by the federal government and most professional organizations. 14. Confidentiality

is when the participants are not revealed to any one but the researcher and staff.

15. Research

participants must give informed consent before they can participate in a study.

17

16. There are three basic approaches that people tend to adopt when considering ethical issues in research. These include the following: a) Ethical skepticism b) Deontology c)Utilitarianism 17. Debriefing

is the term that refers to a post-study interview in which all aspects of the study are revealed, reasons for the use of deception are given, and the participant’s questions are answered.

18. Research

ethics are a set of principles to guide and assist researchers in deciding which goals are most important and in reconciling conflicting values when conducting research.

19. IRB

is an acronym for Institutional Review Board.

20. When it is necessary to engage in a good amount of deception to conduct a scientifically valid study, the researcher should consider the following: a) Debriefing b) Dehoaxing c) Desensitizing 21. Duplicate

publication is the act of publishing the same data and results in more than one journal or publication.

22. Concerning

“authorship” in educational research, intellectual ownership is predominantly a function of creative contribution.

18

23. Partial

publication refers to publishing several articles from the data collected in one large study.

24. According

to the American Education Research Association (AERA), participant’s submitting manuscripts for publication have the freedom to withdraw.

Dr. William Kritsonis Educational Research Lecture Notes

19

Chapter 5 – Standardized Measurement and Assessment 1. Assumptions underlying testing and measurement include the following: a) Various approaches to measure aspects of the same thing can be useful b) Present-day behavior predicts future behavior. c) Testing and assessment benefit society Note: Error is always present in the measurement process. 2.

Systematic effort is associated with validity.

Concurrent evidence is a type of criterion-related validity. Predictive evidence is a type of criterion-related validity. 3.

4.

If a test measures a single construct then the items should correlate with the total score.

5.

Professor Kritsonis develops a test of emotional intelligence. Convergent and discriminant evidence occurs when the test correlates highly with another

20

test of emotional intelligence and is uncorrelated with self-efficacy. 6.

An ordinal scale is used to rank order people, objects, or characteristics.

7.

A nominal scale is the simplest form of measurement.

8.

Aptitude tests focus on information acquired through the informal learning that goes on in life.

9.

A test accurately indicates participants’ scores on a future criterion used to indicate high-school GPA scores. This test would clearly have predictive validity.

10. If

a softball coach calculates batting average, he or she would use a ratio scale.

11. Most

of the outcome/dependent variable characteristics and attributes measured in educational research probably exist at the ordinal level of measurement.

12. Anxiety

enduring for months or years is most clearly an example of a psychological trait.

13.

The following are examples of Intelligence Tests: a) Wechsler Scales b) Stanford-Binet

21

c) Slosson 14. Reliability is simply known as consistency or stability. 15.

An ordinal scale is a rank-order scale of measurement.

16.

The following are types of reliability measures: a) Test-retest b) Content c) Internal consistency

Note: Split-half is not a type of reliability.

17.

The measure of consistency of test scores over time describes test-retest reliability.

18.

Test-retest reliability refers to the consistency of test scores over time.

19.

Criterion-related validity refers to a judgment of the extent to which scores from a test can be used to infer, or predict, the examinees’ performance in some activity.

20.

The following is the correct order of the four levels of measurement: Nominal – Ordinal – Interval – Ratio

21.

Validation is the process of gathering evidence supporting inferences based test scores.

22

22.

In evaluating tests and assessments, “reliability” refers to the consistency of results.

23.

Validity of a test designed to measure a construct such as self-esteem is best described as follows: Scores from the test have a relatively strong and positive correlation with other tests of the same construct (i.e., with other measures of self-esteem) but much lower correlations with tests of different constructs.

24.

Equivalent forms of reliability refers to the consistency of a group of individuals’ scores on two equivalent forms of a test designed to measure the same characteristic.

25.

Achievement tests are designed to measure the degree of learning that has taken place after a person has been exposed to a specific learning experience.

26.

Content validity evidence refers to how well the particular sample of behaviors used to measure a characteristic reflects the entire domain of behaviors that constitutes that characteristic. Dr. William Kritsonis Educational Research Lecture Notes Chapter 6 – Methods of Data Collection

23

1. A rating scale should have somewhere from 4 to 11 points. 2.

What is the problem(s) with this set of response categories to the question “What is your current age?” 1-5 5-10 10-20 20-30 30-04 (Both 1-5 and 5-10 are problems)

3.

In educational research, we should mix methods in a way that provides complementary strengths and nonoverlapping weaknesses. This is known as the fundamental principle of mixed research.

4. Questionnaires can address events and characteristics taking place as follows: a) In the past (retrospective questions) b) In the present (current time questions c) In the future (prospective questions) 5. The following are principles of questionnaire construction: a) Consider using multiple methods when measuring abstract constructs b) Use multiple items to measure abstract constructs c) Avoid double-barreled questions

24

6. The following are methods of data collection: a) Questionnaires b) Interviews c) Observations Note: Experiments are not a method of data collection. 7. Secondary/existing data may include the following: a) Official documents b) Personal documents c) Archived research data 8.

An item that directs participants to different follow-up questions depending on their response is called a contingency question.

9.

Secondary data refers originally collected at an earlier time by a different person for a different purpose.

10. Researchers

use both open-ended and closed-ended questions to collect data. Open-ended questions provide qualitative data in the participant’s own words.

11. Open-ended

questions provide primarily qualitative

data. 12. Concerning

observations, it is often not possible to determine exactly why the people behave as they do.

13. Qualitative

observation is usually done for exploratory purposes. It is also called naturalistic observation.

25

14. When constructing a questionnaire it is important to do each of the following: a) Use natural language b) Understand your research participants c) Pilot your test questionnaire Note: Do not use “leading” or “loaded” questions. 15. Another

name for a Likert Scale is a summated rating

scale. 16. The six major methods of data collection that are used by educational researchers include the following: a) Observation b) Interviews c) Questionnaires Note: Checklists are not one of the six major methods. 17. The

interview guide approach is when the specific topics are decided in advance but the sequence and wording can be modified during the interview.

18. The following are major methods of data collection: a) Questionnaires b) Interviews c) Secondary data d) Focus groups

26 19. A

question during an interview such as “Why do you feel that way?” is known as a probe.

20. A census taker often collects data through interviews. 21. A

researcher becomes a complete participant when they place themselves (as a member) in the group that is being studied.

22. The following are major methods of data collection: a) Questionnaires b) Focus groups c) Secondary data Note: The correlation method is not a major method of data collection. 23. The

informal conversational interview allows the questions to emerge from the immediate context or course of things.

24. When

conducting an interview, asking “Anything else? What do you mean?, Why do you feel that way?,” etc, are all forms of probes.

25. Avoid

using multiple items to measure a single construct when constructing a questionnaire.

27

Dr. William Kritsonis Educational Research Lecture Notes Chapter 7 - Sampling

28 1.

When each member of a population has an equally likely chance of being selected, this is called an equal probability selection method.

2.

A technique for yielding a simple random sample requires numbering all the elements of a sampling frame and then using a random number table to pick cases from the table.

3. The following are true about stratified random sampling: a) It involves a random selection process from identified subgroups. b) Disproportional stratified random sampling is especially helpful for getting large enough subgroups samples when subgroup comparisons are to be done c) Proportional stratified random sampling yields a representative sample Note: Proportions of groups in the sample that always match their population proportions is not a true representation of stratified sampling.

4.

The more categories or breakdowns you want to make in your data analysis, the larger the sample needed.

29 5.

To determine how many people to include in the original sampling, use the desired sample size/proportion likely to respond.

6.

EPSEM is an equal probability selection method. By using this method, every individual in the population has an equal chance of being selected.

The following EPSEM are examples of the equal probability selection method: a) Simple random sampling b) Systematic sampling c) Proportional stratified sampling d) Cluster sampling using the PPS (Probability proportional to size) technique 7. The following are forms of nonrandom sampling: a) Snowball sampling b) Convenience sampling c) Quota sampling d) Purposive sampling 8.

A large sample based on a simple random sampling will give a more “accurate” representation of the population from which a sample has been taken.

30

9.

Sampling in qualitative research is similar to purposive sampling in quantitative research.

10. Cluster

sampling would generally require the largest sample size.

11. The

Census Bureau takes a complete population count every ten years.

12. Convenience

sampling is a method used when people are available, volunteer, or can be easily recruited.

13. Quota

sampling involves the researcher determining the appropriate sample sizes for the groups identified as important, and then taking convenience samples from those groups.

14. Negative-case

sampling is used in qualitative research that involves selecting cases that disconfirm the researcher’s expectations and generalizations.

15. How

many participants will be needed for a research study with a population of 120,000? Answer: 384

16. In

using the Snowball nonrandom sampling technique, the researcher asks the research participants to identify other potential research participants.

31 17. Proportional

stratified sampling is one of the most efficient random sampling techniques.

18. If

we took 500 people attending a school in Houston, divided them by gender and then took a random sample of males and a random sampling of the females, the variables on which we would divide the population is called the stratification variable.

19. A

parameter is a number calculated with complete data and quantifies a characteristic of the population.

20. Sampling

with replacement is a type of sampling in which each member of the population selected for the sample is returned to the population before the next member is selected.

21. The

following are examples of random sampling techniques: a) Convenience sampling b) Quota sampling c) Purposive sampling Note: Cluster sampling is a nonrandom sampling.

22. Simple

random sampling would usually require the smallest sample size because of its efficiency.

23. The

Probability proportional to size or PPS is a technique used when selecting clusters of different sizes.

32

24. Sampling

is the process of drawing a sample from a population.

25. It

is recommended to use the whole population rather than a sample when the population size is 100 or less.

26.

The following are random sampling technique: a) Purposive sampling b) Quota sampling c) Convenience sampling

Note: Cluster sampling is a nonrandom sampling technique. 27. Random

sampling is the best way to select a group of people for a study if the researcher is interested in making statements about the larger population.

28. A

sample is a set of elements taken from a larger population according to certain rules.

29. Determining the sample interval (represented by k), randomly selecting a number between 1 and k, and including each kth element in the sample are the steps for systematic sampling. 30. Purposive sampling is a technique that involves selecting a convenience sample from a population with a specific set of characteristics for the research study.

33

Dr. William Kritsonis Educational Research Lecture Notes Chapter 8 – Validity of Research Results

34

1.

When an extraneous variable systematically varies with the independent variable and influences the dependent variable it is called a confounding variable.

2. A statistical relation of X and Y is insufficient evidence for inferring causality. 3.

A school district examines a program that uses mentors to help very poor readers improve their reading performance. The children in the program are at the 4th percentile at pretest. At posttest they are around the 20th percentile. While it is possible that the program made the difference, another reason for the change in scores could be regression artifact.

35

4.

A group of researchers do a study where children from particular classrooms are assigned to treatment or control conditions. After the study, the researcher finds out that the students in the control group are higher achievers than those in the experimental group. He/she found not treatment effect. The failure to find an effect may be due to a differential selection effect.

5.

A researcher examines a program looking at the effects of mentoring on poor readers’ reading achievement. He/she looks at two different schools. One serves as the control and the other experimental group. Both schools had reading achievement that was around the 50th percentile. During the time that the mentoring program is in place in the experimental group, a statewide reading initiative is started in randomly selected schools. The experimental, but not the control school is involved in the initiative. At the end of the year, the experimental group does better than the control. From the information presented here, a likely threat to the internal validity of the study is selection-history effect.

6.

Internal validity refers to the degree to which the researcher can infer that the relationship between two variables is causal.

36 7.

Statistical conclusion validity refers to the ability to infer that the independent and dependent variables are related and that the measured strength of the relationship is accurate.

8.

An extraneous variable that systematically varies with the independent variable and also influences the dependent variable is known as a confounding variable or third variable.

9.

Investigator triangulation is the use of multiple observers to allow cross-checking of observations to make sure that the investigators agree with what took place.

10. A

verbatim is the lowest inference descriptor of all because it uses the participant’s own words.

11. Maturation

refers to physical or mental changes that may occur within individuals over time, such as aging, learning, boredom, hunger, and fatigue.

12. External

validity refers to the extent to which the results of a study can be generalized across time.

13. Interpretive

validity accurately portrays the meanings given by the participants to what is being studied.

37 14. Reflexivity

is a strategy where the researcher actively engages in critical self-reflection about his or her potential biases and predispositions.

15. The following are considered criteria for inferring causality: a) Evidence that the independent and dependent variables are related b) Evidence that the relationship between the variables being investigated is not due to a confounding extraneous variable c) Evidence that changes in variable A occur before changes in variable B 16. Data

triangulation is the use of multiple data sources to help understand a phenomenon that is used to promote qualitative research validity.

17. Selection-history

effect may happen when different comparison groups experience a different history event.

18. Third

variable is another term that refers to a confounding extraneous variable.

19. Instrumentation

refers to any systematic change that occurs over time in the way in which the dependent variable is assessed.

38 20. Population

validity describes the ability to generalize from the sample of individuals on which a study was conducted to the larger target population of individuals and across different subpopulations within the larger target population.

21. The following strategies are used to promote qualitative research validity: a) Peer review b) Theory triangulation c) Extended fieldwork Note: Random assignment is not a strategy used to promote qualitative research validity. 22. Multiple

operationalism is the use of several measures of a construct.

23. Maturation

is a physical or mental change that occurs in participants over time that affects their performance on the dependent variable.

24. Attrition

generally occurs in research where some participants do not complete the study.

25. Differential

attrition occurs when the people dropping out from one group are different from the others in their group or from the people in the comparison group.

39

26. Internal

validity refers to the ability to infer that a casual relationship exists between 2 variables.

27. Methods

triangulation is a strategy used to promote qualitative research validity that uses multiple research methods to study a phenomenon.

28. Descriptive

validity refers to the factual accuracy of an account as reported by the researcher.

29. Three

threats to internal validity include the following: a) Maturation b) Instrumentation c) History Note: Temporal change is not a threat to internal validity.

30. Ecological

validity refers to the ability to generalize the results of a study across settings.

31. Sampling

error is not a direct threat to the internal validity of a research design.

Note: Direct threats to the internal validity of a research design include history, testing, and differential selection.

40

32. Reactivity

refers to the alteration in performance due to being aware that one is participating in a study.

33. Replication

logic is the idea that the more times a research finding is shown with different sets of people, the more confidence we can place in the findings and in generalizing beyond the original participants.

Dr. William Kritsonis Educational Research Lecture Notes Chapter 9 – Experimental Research

41

1. Analysis of covariance is a statistical technique that can be used to help equate groups on specific variables. 2.

To determine whether noise affects the ability to solve math problems, a researcher has one group solve math problems in a quiet room and another group solve math problems in a noisy room. The group solving problems in the noisy room completes 15 problems in one hour and the group solving problems in the quiet room completes 22 problems in one hour. In this experiment, the independent variable is the noise level in the room and the dependent variable is the number of problems solved.

3.

The posttest-only design with nonequivalent groups is likely to control historical threats to internal validity.

Note: Differential selection, additive and interactive effects, and differential attrition will not control threats to internal validity. 4.

When all participants receive all treatment conditions, the study is susceptible to order effects and carryover effects.

5.

A researcher is interested in the effects of a preschool program on later school performance. Because the researcher is concerned that socio-economic-status (SES) is a potential variable in the study, the researcher picks

42

children to study who are only from low SES homes. The control technique used in this study is matching. 6.

An interaction effect is described as follows: The effect of one independent variable (on a DV) depends on the level of another independent variable.

7.

Analysis of covariance refers to a statistical method that can be used to statically equate groups on a pretest or some other variable.

8. Random technique is not a way to manipulate an independent variable. 9.

The pretest-posttest control group design permits a comparison of pretest scores to determine the initial equivalence of groups on the pretest before the treatment variable is introduced into the research setting.

10. Counterbalancing

is chosen to control for such things as order and carryover effects.

11. The

group that receives the experimental treatment condition is the experimental group.

12. The

random assignment technique is available to the researcher to control both known and unknown variables.

43 13. The

group that does not receive the experimental treatment condition is the control group.

14. There are a number of ways in which confounding extraneous variables can be controlled. Random assignment is the best technique for controlling confounding extraneous variables. 15. It is best to use a list of random numbers or a computer randomization program for randomly assigning participants to groups in an experimental study. 16. The following are related to counterbalancing: a) Carryover effect b) Order effect c) Sequencing effects 17. A cell is a combination of two or more independent variables in a factorial design. 18. The posttest-only control-group design and pretestposttest control-group design do an excellent job of controlling for rival hypotheses that threatened the internal validity of an experiment.

19. Manipulating the independent variable by varying the type on the independent variable that is presented to the

44

different comparison group is known as the type technique. 20. The order effect occurs from the order in which the treatment conditions are administered. 21. The following describes this method of manipulating the independent variable in an educational experiment: a) An independent variable is manipulated using the presence or absence technique b) The researchers varies the amount of the independent variable that is administered c) The researcher varies the type of the independent variable 22. Randomly assigning research participants to groups is the best method for controlling confounding extraneous variables. 23. In an experimental research study, the primary goal is to isolate and identify the effect produced by the independent variable. 24. Repeated measures design is one where all participants participate in all experimental treatment conditions.

25. Factorial design is one in which two or more independent variables are simultaneously studied to

45

determine their independent and interactive effects on the dependent variable. 26. Posttest-only design with nonequivalent groups occurs when one group of research participants is administered a treatment and is then compared, on the dependent variable, with another group of research participants who did not receive the experimental treatment. 27. Main effect refers to the influence of a single independent variable. 28. Carryover effect occurs when performance in one treatment condition is influenced by participation in a prior treatment condition. 29. The following are possible in a factorial design with two independent variables: a) There is only one main effect present b) There are two main effects present c) There are two main effects and an interaction effect present 30. Factorial design based on a mixed model is where different participants are randomly assigned to the levels of one independent variable but participants take all levels on another independent variable.

46