Three Experimental Designs:
R O O
R O
· Designs 1-2 (combined), Name: Solomon randomized four-group design
R O X O
R O O
R X O
R O
“R” stands for random assignment to groups
“O” stands for observation or measurement
“X” stands for experimental treatment
A causal-comparative study is research in which researchers look to the past for the cause(s) of a current condition. It is used primarily when researchers are interested in causality, but it is not possible to conduct an experiment.
Correlational researchresearchers are interested in the degree of relationship among two or more quantitative variables.
Longitudinal researchis when researchers repeatedly measure traits of the participants over a period of time in order to trace developmental trends.
Causal-comparative study – ex post facto study – Lung cancer, researchers observe and describe some current condition, non-experimental, researchers look to the past to try and identify the possible causes(s) of the condition.
Correlational study – Researchers look at scores on a college admissions test and GPAs.
Longitudinal study – Researchers could measure the visual acuity of a sample of infants each week for a year to trace their development.
Variables – Is a trait or characteristic with two or more categories
One Variable à GENDER
Two Categories à
Male
Female
Independent Variable – [Predictor] (Stimulus or input) causes changes in the…
Dependent Variable – (Response or output) Criterion (which also means “standard”) “Outcome”
Hypothesis (directional) – Researchers predict which group will be higher or have more of some attribute. (i.e. “It is hypothesized that children who are shown a video with mild violence will be more aggressive on the playground than those who are shown a similar video without violence.”)
Hypothesis (non-directional) – The researcher says there will be a difference but does not predict the direction of the difference (i.e. “It is hypothesized that the child-rearing practices of Tribe A are different from those of Tribe B.”)
Research question – The research question is often stated in the context of some theory that has been advanced to address the problem.
Research hypothesis – Is a prediction of the outcome of a study.
Operational definitions – Is when a researcher operationalizes a variable. Thus, instead of striving for completely operational definitions, researchers try to produce definitions that are adequate to permit a replication in all important respects by another researcher.
Differences between QUALITATIVE and QUANTITATIVE research:
Qualitative research – Researchers tend to use an inductive approach to planning the research. Purposive sample, researchers choose individuals that they believe will be are key informants in terms of social dynamics, leadership positions, job responsibilities, etc. (i.e. interviews, questionnaires)
Quantitative research – Researchers prefer a deductive approach to planning research (from literature for possible explanations). Researchers prefer a random sample in which all participants have an equal chance of being selected. (i.e. Likert Scale, surveys, polls, dealing with numbers)
THE BASIC STRUCTURE OF A RESEARCH REPORT AND WHAT EACH PART IS FOR:
Title page with:
· Title in the header with page number, i.e. This class rocks! 1
· (2 spaces down) Running Head: THIS CLASS ROCKS!
· Center of the page, centered:
This class rocks!
Adam Webb
EDFN 5304
Dr. So-So A. Go-Go
October 43, 2707
· Abstract (100-150 words) describing what your report is about, key elements
· The first page of the report should have the title in the header with a page number, title centered
· Subtitles:
Introduction (centered)
Literature review (background research)
Methodology
Purpose of the study
Participants
Instrumentation
Data analysis
Discussion
Recommendations
Conclusion
References
· Ethical considerations –
-Consider possible harm to participants that might result from their participation
-The primary value is that participants must be protected from both physical and psychological harm.
-Participants have the right to privacy
- Participants have a right to have the data collected about them as individuals kept confidential.
-Almost all researchers agree that participants have a right to knowledge of the purpose of the research before they participate.
-Informed consent: General purpose of the research, what will be done to them during the research, potential benefits, potential harms, the fact that they may withdraw at any time without penalty, even at midstream during the research. This information should be provided in writing, and the participants (or their guardians) should sigh an informed consent form to indicate that they understand it and freely agree to participate.
Inferential statistics – Is to help researchers draw inferences about the effects of sampling errors on the results that are described with descriptive statistics.
· Samples yield statistics
· Populations yield parameters (census)
· Frequency – How often something occurs, distribution of the data
· Frequency polygon – i.e. bell-shaped curve, ‘normal curve.” Displays data in a certain way.
MEDIAN (middle score) –
MODE (most often) – Most frequently occurring
Standard deviation = Normal curve = 34.13% from the mid-point, dispersion = range of standard deviation
· Scales of measurement:
NOMINAL = NAMING (i.e. gender)
ORDINAL = ORDERING or RANK (i.e hierarchical)
INTERVAL = EQUAL INTERVAL WITHOUT AN ABSOLUTE ZERO (i.e achievement tests)
RATIO = EQUAL INTERVAL WITH AN ABSOLUTE ZERO (i.e. weight)
· Pearson product-moment correlation coefficient (Pearson r):
Direct relationship (positive relationship) – Closer to the “line” (i.e. 1.00, -1.00)
Indirect relationship (negative relationship) – Further away from the “line.” (i.e. .89, .59)
· Different types of sampling:
Simple random sample – Everyone gets a fair chance, every member of a population is given an equal chance of being included in a sample.
Samples of convenience – Accidental samples (i.e. students within a classroom)
Systematic sampling – Every “nth” individual is selected
Stratified random sample - Must first divide a population into strata. i.e. men and women.
Cluster sample – Researchers draw on groups (or clusters) of participants instead of drawing individuals. i.e. questionnaires mailed out to members from a certain religion (or, who worship under a certain doctrine, denomination, etc.).
Purposive sampling - Researchers choose certain individuals based on their status within a certain setting. Qualitative researchers doing interviews.
· Sampling error – Error created by random sampling is simply called “sampling error” by statisticians.
· Different types of validity (a matter of degree):
Content validity – Where researchers make judgments of the appropriateness of its contents (instrument).
Face validity – Judgments are made on whether an instrument appears to valid on the face of it.
Concurrent validity coefficient – Collecting the criterion data at the same time as administering the test. i.e. collecting the criterion data at about the same time the test is given.
Predictive validity coefficient – Collected at the beginning of a test. i.e. test scores and a supervisors’ ratings.
Criterion-related coefficient – General term used to describe both types of validity.
Construct validity – Empirical data (based on observation)
· Reliability – A test that yields consistent results.
· Validity is more important than reliability.
Interobserver reliability – More than one observer during a study.
Test-retest reliability – Researchers measure at two different points in time.
Parallel-forms reliability – This is done by administering one form of the test to examinees and about a week or two later, administering the other form to the same examinees, thus yielding two scores per examinee.
Split-half reliability – A researcher administers a test but scores the items in the test as though they consisted of two separate tests. i.e. an odd-even split. A researcher scores all the odd-numbered items and obtains a score for each examinee. Checks for consistency within the test itself. Estimates of internal consistency.
Cronbach’s alpha – (alternative to the split-half method) – One test is
administered. After the test ahs been administered, mathematical procedures are used to obtain the equivalent of the average of all possible split-half reliability coefficients.
Having high internal consistency is desirable when a researcher has developed a test designed to measure a single unitary variable, which is usually the case.
· Instrument – The generic term for any type of measurement device (i.e. test, questionnaire, interview, survey, schedule, or personality scale).
Instrumentation – This is the term used as the heading fore the section of the report where the measurement devices used in the research are described.
· Inductive reasoning – Moves from a set of general principles to a general conclusion (there is a strong and weak inductive reasoning) – Also known as “theory-building.” Example – (strong inductive reasoning): “All observed crows are black” therefore, “All crows are black.” Example – (weak inductive reasoning): “I always eat cereal in the morning” therefore “Everyone eats cereal in the morning.”
· Deductive reasoning – When the logical consequences of the premises and consequently if its corresponding conditional is a necessary truth. A deductive argument is either valid or not valid. Example: “All men are mortal, Socrates is a man, and therefore Socrates is mortal.”
· Abductive reasoning – Charles Sanders Pierce, which comes prior to induction and deduction for which the colloquial name is guessing. Abductive reasoning starts when an inquirer considers of a set of seemingly unrelated facts, armed with the hunch that they are somehow connected. The term abduction is commonly presumed to mean the same thing as hypothesis; however, an abduction is actually the process of inference that produces a hypothesis as its end result.
Teaching, learning, writing & research (when students and we go about reaching & writing)
Deductive & inductive approaches to researching & writing
Deductive researching & writing
· Theory
· Hypothesis
· Observation
· Confirmation
Features:
· More narrow
· More concerned with testing or confirming a hypotheses
Inductive researching & writing
· Observation(s)
· Pattern(s)
· Tentative hypothesis
· Theory
Features:
· Open-ended
· Exploratory
Can deductive and inductive approaches be mixed?
Are these “teachable?” How?
Understanding the three types of logical inference
- Design 1, Name: Pretest-posttest randomized control group design
R O O
- Design 2, Name: Posttest-only randomized control group design
R O
· Designs 1-2 (combined), Name: Solomon randomized four-group design
R O X O
R O O
R X O
R O
“R” stands for random assignment to groups
“O” stands for observation or measurement
“X” stands for experimental treatment
A causal-comparative study is research in which researchers look to the past for the cause(s) of a current condition. It is used primarily when researchers are interested in causality, but it is not possible to conduct an experiment.
Correlational researchresearchers are interested in the degree of relationship among two or more quantitative variables.
Longitudinal researchis when researchers repeatedly measure traits of the participants over a period of time in order to trace developmental trends.
Causal-comparative study – ex post facto study – Lung cancer, researchers observe and describe some current condition, non-experimental, researchers look to the past to try and identify the possible causes(s) of the condition.
Correlational study – Researchers look at scores on a college admissions test and GPAs.
Longitudinal study – Researchers could measure the visual acuity of a sample of infants each week for a year to trace their development.
Variables – Is a trait or characteristic with two or more categories
One Variable à GENDER
Two Categories à
Male
Female
Independent Variable – [Predictor] (Stimulus or input) causes changes in the…
Dependent Variable – (Response or output) Criterion (which also means “standard”) “Outcome”
Hypothesis (directional) – Researchers predict which group will be higher or have more of some attribute. (i.e. “It is hypothesized that children who are shown a video with mild violence will be more aggressive on the playground than those who are shown a similar video without violence.”)
Hypothesis (non-directional) – The researcher says there will be a difference but does not predict the direction of the difference (i.e. “It is hypothesized that the child-rearing practices of Tribe A are different from those of Tribe B.”)
Research question – The research question is often stated in the context of some theory that has been advanced to address the problem.
Research hypothesis – Is a prediction of the outcome of a study.
Operational definitions – Is when a researcher operationalizes a variable. Thus, instead of striving for completely operational definitions, researchers try to produce definitions that are adequate to permit a replication in all important respects by another researcher.
Differences between QUALITATIVE and QUANTITATIVE research:
Qualitative research – Researchers tend to use an inductive approach to planning the research. Purposive sample, researchers choose individuals that they believe will be are key informants in terms of social dynamics, leadership positions, job responsibilities, etc. (i.e. interviews, questionnaires)
Quantitative research – Researchers prefer a deductive approach to planning research (from literature for possible explanations). Researchers prefer a random sample in which all participants have an equal chance of being selected. (i.e. Likert Scale, surveys, polls, dealing with numbers)
THE BASIC STRUCTURE OF A RESEARCH REPORT AND WHAT EACH PART IS FOR:
Title page with:
· Title in the header with page number, i.e. This class rocks! 1
· (2 spaces down) Running Head: THIS CLASS ROCKS!
· Center of the page, centered:
This class rocks!
Adam Webb
EDFN 5304
Dr. So-So A. Go-Go
October 43, 2707
· Abstract (100-150 words) describing what your report is about, key elements
· The first page of the report should have the title in the header with a page number, title centered
· Subtitles:
Introduction (centered)
Literature review (background research)
Methodology
Purpose of the study
Participants
Instrumentation
Data analysis
Discussion
Recommendations
Conclusion
References
· Ethical considerations –
-Consider possible harm to participants that might result from their participation
-The primary value is that participants must be protected from both physical and psychological harm.
-Participants have the right to privacy
- Participants have a right to have the data collected about them as individuals kept confidential.
-Almost all researchers agree that participants have a right to knowledge of the purpose of the research before they participate.
-Informed consent: General purpose of the research, what will be done to them during the research, potential benefits, potential harms, the fact that they may withdraw at any time without penalty, even at midstream during the research. This information should be provided in writing, and the participants (or their guardians) should sigh an informed consent form to indicate that they understand it and freely agree to participate.
- Basic statistics:
Inferential statistics – Is to help researchers draw inferences about the effects of sampling errors on the results that are described with descriptive statistics.
· Samples yield statistics
· Populations yield parameters (census)
· Frequency – How often something occurs, distribution of the data
· Frequency polygon – i.e. bell-shaped curve, ‘normal curve.” Displays data in a certain way.
- Measures of central tendency:
MEDIAN (middle score) –
MODE (most often) – Most frequently occurring
Standard deviation = Normal curve = 34.13% from the mid-point, dispersion = range of standard deviation
· Scales of measurement:
NOMINAL = NAMING (i.e. gender)
ORDINAL = ORDERING or RANK (i.e hierarchical)
INTERVAL = EQUAL INTERVAL WITHOUT AN ABSOLUTE ZERO (i.e achievement tests)
RATIO = EQUAL INTERVAL WITH AN ABSOLUTE ZERO (i.e. weight)
· Pearson product-moment correlation coefficient (Pearson r):
Direct relationship (positive relationship) – Closer to the “line” (i.e. 1.00, -1.00)
Indirect relationship (negative relationship) – Further away from the “line.” (i.e. .89, .59)
· Different types of sampling:
Simple random sample – Everyone gets a fair chance, every member of a population is given an equal chance of being included in a sample.
Samples of convenience – Accidental samples (i.e. students within a classroom)
Systematic sampling – Every “nth” individual is selected
Stratified random sample - Must first divide a population into strata. i.e. men and women.
Cluster sample – Researchers draw on groups (or clusters) of participants instead of drawing individuals. i.e. questionnaires mailed out to members from a certain religion (or, who worship under a certain doctrine, denomination, etc.).
Purposive sampling - Researchers choose certain individuals based on their status within a certain setting. Qualitative researchers doing interviews.
· Sampling error – Error created by random sampling is simply called “sampling error” by statisticians.
· Different types of validity (a matter of degree):
Content validity – Where researchers make judgments of the appropriateness of its contents (instrument).
Face validity – Judgments are made on whether an instrument appears to valid on the face of it.
Concurrent validity coefficient – Collecting the criterion data at the same time as administering the test. i.e. collecting the criterion data at about the same time the test is given.
Predictive validity coefficient – Collected at the beginning of a test. i.e. test scores and a supervisors’ ratings.
Criterion-related coefficient – General term used to describe both types of validity.
Construct validity – Empirical data (based on observation)
· Reliability – A test that yields consistent results.
· Validity is more important than reliability.
Interobserver reliability – More than one observer during a study.
Test-retest reliability – Researchers measure at two different points in time.
Parallel-forms reliability – This is done by administering one form of the test to examinees and about a week or two later, administering the other form to the same examinees, thus yielding two scores per examinee.
Split-half reliability – A researcher administers a test but scores the items in the test as though they consisted of two separate tests. i.e. an odd-even split. A researcher scores all the odd-numbered items and obtains a score for each examinee. Checks for consistency within the test itself. Estimates of internal consistency.
Cronbach’s alpha – (alternative to the split-half method) – One test is
administered. After the test ahs been administered, mathematical procedures are used to obtain the equivalent of the average of all possible split-half reliability coefficients.
Having high internal consistency is desirable when a researcher has developed a test designed to measure a single unitary variable, which is usually the case.
· Instrument – The generic term for any type of measurement device (i.e. test, questionnaire, interview, survey, schedule, or personality scale).
Instrumentation – This is the term used as the heading fore the section of the report where the measurement devices used in the research are described.
· Inductive reasoning – Moves from a set of general principles to a general conclusion (there is a strong and weak inductive reasoning) – Also known as “theory-building.” Example – (strong inductive reasoning): “All observed crows are black” therefore, “All crows are black.” Example – (weak inductive reasoning): “I always eat cereal in the morning” therefore “Everyone eats cereal in the morning.”
· Deductive reasoning – When the logical consequences of the premises and consequently if its corresponding conditional is a necessary truth. A deductive argument is either valid or not valid. Example: “All men are mortal, Socrates is a man, and therefore Socrates is mortal.”
· Abductive reasoning – Charles Sanders Pierce, which comes prior to induction and deduction for which the colloquial name is guessing. Abductive reasoning starts when an inquirer considers of a set of seemingly unrelated facts, armed with the hunch that they are somehow connected. The term abduction is commonly presumed to mean the same thing as hypothesis; however, an abduction is actually the process of inference that produces a hypothesis as its end result.
Teaching, learning, writing & research (when students and we go about reaching & writing)
Deductive & inductive approaches to researching & writing
Deductive researching & writing
- General to specific; “top-down” approach to research
· Theory
· Hypothesis
· Observation
· Confirmation
Features:
· More narrow
· More concerned with testing or confirming a hypotheses
Inductive researching & writing
- “Bottom-up” approach; Opposite way from deductive; moves from specific observations to broader generalizations and theories
· Observation(s)
· Pattern(s)
· Tentative hypothesis
· Theory
Features:
· Open-ended
· Exploratory
Can deductive and inductive approaches be mixed?
Are these “teachable?” How?
Understanding the three types of logical inference
- Deductive reasoning
- Finding the effect with the cause and the rule.
- Deductive reasoning is supported by deductive logic
- For example:
- All apples are fruit.
- All fruits grow on trees.
- Therefore all apples grow on trees.
- Or
- All apples are fruit.
- Some apples are red.
- Therefore some fruits are red.
- The first premise may be false yet anyone accepting the premises is compelled to accept the conclusion.
- Abductive reasoning
- Finding the cause with the rule and the effect.
- Constitutes according to Peirce the “first stage” of scientific inquiries (CP 6.469) and of any interpretive processes.
- “Abduction” is the process of adopting an explanatory hypothesis (CP 5.145) and covers two operations: the selection and the formation of plausible hypotheses. As process of finding premises, it is the basis of interpretive reconstruction of causes and intentions, as well as of inventive construction of theories.
- Inductive reasoning
- Finding the rule with the cause and the effect.
- Strong induction (i.e.):
- All observed crows are black.
- Therefore:
- All crows are black.
- Weak induction (i.e.):
- I always hang pictures on nails.
- Therefore:
- All pictures hang from nails.
