Term
| A ___ is an entire group sharing certain characteristics or parameters. A ___ is a subset of the group that is used to represent the population and to study to try to infer the population parameter. |
|
Definition
|
|
Term
| ___ sample=asking friends/people you know/easily accessible people to be in the study. |
|
Definition
|
|
Term
| ___ sample=This gives everyone in the population an equal chance of being selected for the sample/selecting participants at random/this is usually best to try to ensure that a sample is representative of the population. |
|
Definition
|
|
Term
| Factors determine whether the sample size of a study is adequate: 1. How many variables are in the study (the more variables the ___ participants needed) 2. ___ is being studied and how many ___ will there be 3. usually, the larger the sample, the ___ the margin of error, however, a really large sample may find a statistically significant difference that is not actually ___ 4. you need fewer people in a ___ subject design than you do in a between-___ design 5. Consider how much ___ a study needs 6. Consider… purpose of the study, previous research, concern about generalizability, variability found for the construct under investigation, research design. |
|
Definition
| more; what; trials; smaller; relevant; single; group; power |
|
|
Term
How can participant selection affect internal validity?
-Participant selection can introduce confounding variables which cannot be ___ for which is a major threat to internal validity. Also, when friends are asked to volunteer, this may introduce ___ into the study.
-Inadequate ___ ___, ___ groups, and ___ selection criteria all pose important threats to the internal and external validity of both experimental and descriptive research
-Another aspect of subject selection that directly affects internal validity is whether subjects are selected on the basis of ___ scores.
-___ or ___? |
|
Definition
| controlled; bias; group composition; overlapping; indefensible; extreme; Volunteered |
|
|
Term
What questions about participant selection criteria should be asked for between-group studies?
-Are the ___ for group considerations clearly defined and defensible? (internal validity)
-Is there ___ between groups on the variable that distinguishes the group? (internal)
-Are the groups comparable on important ___ variables? (internal)
-Have subjects been selected on the basis of ___ scores?(internal)
-Are subjects ___ on important dimensions to the population that the author wishes to generalize? (External validity)
-Is the size of the sample ___ for the purposes of the study?
-Are ___ criteria defined and defensible? (internal) |
|
Definition
| criteria; overlap; extraneous; extreme; comparable; adequate; exclusion |
|
|
Term
| What are the 4 levels of measurement? |
|
Definition
| Nominal, ordinal, interval, and ratio |
|
|
Term
| What kind of variable is this? "Type of hearing loss" |
|
Definition
|
|
Term
| What kind of variable is a pain scale (1-10)? |
|
Definition
|
|
Term
| What kind of variable is Fahrenheit? |
|
Definition
|
|
Term
| What kind of variable is weight? |
|
Definition
|
|
Term
| Make a notecard about instrumental and behavioral measures |
|
Definition
|
|
Term
| A precise measure can be expected to remain reasonably stable if the measurement procedure is repeated with the same ___. An imprecise measure will show more ___ with remeasurement over time. |
|
Definition
|
|
Term
| What are some sources of measurement error? |
|
Definition
(1) characteristics of the examinee
(2) behavior of the examiner-scorer
(3) aspects of the test content
(4) time factors
(5) situation factors |
|
|
Term
| What are the 3 categories of reliability and how are they different from each other? |
|
Definition
| Stability, equivalence, and internal consistency |
|
|
Term
| In practice, the ___ ___ of measurement is an estimate of the standard deviation of observed scores that is used to assess the precision of a given measurement. |
|
Definition
|
|
Term
| Validity is the ___ of a measurement. The validity of a measurement, then, can be defined as the degree to which it measures what it ___ to measure. |
|
Definition
|
|
Term
| refers to the extent to which the results of a particular test, or measurement, correspond to those of a previously established measurement for the same construct (administer the tests relatively close together). |
|
Definition
|
|
Term
| Does a measure/test predict later performance on a related criterion? Based on comparisons between two different measures assess participants with both measures -one administered immediately, the other administered at a future time |
|
Definition
|
|
Term
| The extent to which the elements within a measurement procedure are relevant and representative of the construct that they will be used to measure |
|
Definition
|
|
Term
| Based on clinician’s judgment of how well a test appears to accomplish its purpose |
|
Definition
|
|
Term
| A ___ effect occurs when the observer does not actually affect the subject's performance but does affect the recording of the subject's behavior. That is, the expectancies of the observer serve to bias his or her measurement of the subject's behavior |
|
Definition
|
|
Term
| Factors that might influence the behavior of research subjects: (1) biosocial attributes, (2) psychosocial attributes, (3) situational variables, (4) modeling effects, (5) self-fulfilling prophecies |
|
Definition
|
|
Term
| ___ statistics describe or summarize the sample using measures of central tendency (mean, median, mode), association, measures of dispersion (range, variance, standard deviation), and visual representation of data (table, pie chart, scatterplot, graph, line graph); Also known as summary statistics |
|
Definition
|
|
Term
| ___ statistics serve to analyze the data in ways that assist the researcher to assign meaning to the results and infer findings from a sample to a population. This allows a researcher to draw conclusions and tell a quantitative story. “How does this sample relate to the population as a whole?” |
|
Definition
|
|
Term
| graphically describes the relationship between two variables. It will reveal the direction of the relationship. Positive= when one variable increases the other variable increases as well. Negative=when one variable increases the other variable decreases. They can demonstrate how strongly or loosely correlated two variables are. |
|
Definition
|
|
Term
| used to display percentages of data |
|
Definition
|
|
Term
| is used to illustrate the frequency of categorical variables. |
|
Definition
|
|
Term
| show distribution frequency of continuous variables such as scores on a standardized test. This is numerical data. |
|
Definition
|
|
Term
| Histogram presents ___ data whereas bar graph shows ___ data. The ___ is drawn in such a way that there is no gap between the bars. |
|
Definition
| numerical; categorical; histogram |
|
|
Term
| Computing a large number of correlations increases the Possibility of ___ ___ |
|
Definition
|
|
Term
| correlation coefficients??? |
|
Definition
|
|
Term
| The likelihood that the statistical test will detect a difference/change/effect if one exists between two hypotheses aka probability that a test will reject a false null hypothesis |
|
Definition
|
|
Term
| the likelihood that an apparent difference/change/effect is due to sampling error (not the variable difference/change under study) |
|
Definition
|
|
Term
| the real-world importance of the difference/change, taking into account practical concerns |
|
Definition
|
|
Term
| Difference between groups under comparison: The greater the difference, the ___ the p-value |
|
Definition
|
|
Term
| Degree of sampling and measurement error: The lower the error, the ___ the p-value |
|
Definition
|
|
Term
| Sample size: The larger the sample, the ___ the p-value |
|
Definition
|
|
Term
| Way to compare two studies that used different measurement tools because mean differences are not directly comparable |
|
Definition
|
|
Term
| ___ ___: Calculation converts mean difference between groups to a standard unit of difference |
|
Definition
|
|
Term
Interpretation of Cohen’s d - based on Cohen’s suggestion:
value of ___ is small
value of ___ is medium
value of ___ is large
value of ___ is very large |
|
Definition
|
|
Term
-Positive d-value means the average posttest score is ___ than average pretest
-Negative mans the average posttest is ___ than pretest
-The further away from zero, the ___ the effect (positive or negative) |
|
Definition
|
|
Term
| ___ tests are used when the 2 populations compared do not have an approximately normal distribution and/or when the outcome is an ordinal or nominal variable. |
|
Definition
|
|
Term
| ___ tests are used when the data are normally distributed. They require sufficiently large samples (at least 10 in each group) and they include t-test, ANOVA, z-test |
|
Definition
|
|
