Research Methods Flashcards
What is a laboratory experiment?
Takes place in a controlled environment
Where the researcher manipulates the IV
Three ways in which to deal with reliability ?
Split Half
Test Retest
Inter rater
What is experimental validity ?
Extent to which the experimental setup is believable.
Internal validity - what goes on inside the experiment
External Validity - what goes on outside the experiment
If experimental validity is low then the findings will be meaningless.
Three ways of dealing with validity ?
Content validity - extent to which the test covers the whole topic area
Concurrent validity - extent to which the test results conform on some other valid measure.
Predictive - extent to which the test scores can predict future scores.
What is a type one error?
When the level of significance is too high.
You should have accepted the H0 but instead accepted the H1.
Claim IV affected the DV when it didn’t.
What is a type two error?
When the level of significance is too low
You should have accepted the H1 but instead accept the H0
Claim the IV didn’t have an affect on the DV when it did.
What tests are used for experiments ?
Wilcoxon
Mann Whitney
T- test related
T- test unrelated
What tests are used for correlations
Spearmans and Pearson
What tests are used for observation ?
Chi - Squared
Bi nominal
What are degrees of freedom ?
Number of values in a final calculation of a statistic that are free to vary.
Sometimes the researcher will take participants into account minus one.
Define the three different levels of data.
Nominal data - devise categories and tally up frequencies. Advantage - easy to see vague trends that occur. Disadvantage - not objective subjective as to which category.
Ordinal data - performance is ranked in order , no equal intervals. Advantages - no chance of subjective interpretation. Disadvantage - cant see trends immediately. Can’t see individuals scores in relation to each other.
Interval data - data is gather from a safe numerical scale e.g. Height and time. Advantage - objective. Shows performance in relation to each other. Disadvantages - only be used in limited data . Can’t see trends immediately.
What is a correlation co efficient?
Refers to a number between -1 and +1 that states how strong a correlation is between two sets of measurements.
What are Co-Variables ?
Two or more qualities that may vary with each other.
A disadvantage of a correlation?
Doesn’t show a third variable that may affect the study.
Define a hypothesis?
A formal, unambiguous testable statement that a piece of research aims it prove or disprove.