click below
click below
Normal Size Small Size show me how
Research Methods1
Stack #86981
Question | Answer |
---|---|
Bias | Distortion of data by experimenter, instrumentation, participants or procedures. |
Blinding | Experimenter in contact w/ subjects ignorant of participants category and/or partcipant is ignorant of category. |
Cohort | Group of individuals moving through some process as a group. |
Dependent variable | Data mesured in research study. |
Randomization | Choosing group in such a manner that the participant has an equal chance of being in either group. |
Reliability | Stability or repeatability. |
Test-retest reliability | the stability of a test determined by administering the test, waiting an interval and re-administering the test and correlation test results. |
Validity | Relates to a test measuring what it has been designed to measure. |
Type 1 error | Rejecting the null hypothesis when it is true; claiming the effect exists when it does not. |
Type 2 error | Accepting the null hypothesis when it is not true |
Threats to Internal Validity | Instrumentation, History, mortality, maturation |
Threats to External Validity | Interaction of history, Hawthorne effect, multiple treatment interference |
Parametric | assumptions based on mean; powerful |
Nonparametric | based on median; less powerful & performed second |
Anova | deals w/ multiple groups |
Ancova | deals w/ nuisance variables impact dependent variables |
Simple random sampling | Each individual is randomly assigned to a group; purest form |
Stratified random sampling | used when characteristics of a population exhibit established proportions |
Cluster sampling | gives everyone within a population an equal chance of being chosen for the study; subject to sampling error |
Consistency | if two explanatory statements are contradictory, then one must be false |
Confirmation | once an explanatory statement is made, other events can also be explained;One unsuccessful prediction and the statement is disproved. |
Controlled Observation | changing in variable A produces a change in variable B |
Generality | findings must be able to explain more than the specific items/subjects being studied |
Central Tendency | mode, mean (prefered measure), median |
Variability | Sd, variance, correlation |
Wilcoxon signed rank test | data is multidirectional |
Wilcoxon Ranked Sum Test | equivalent to the Student t- test |
Kruskal-Wallis Test | equivalent to the one-way analysis of variance |