Chapter 4 Flashcards
Reliability
reliability means that a measurement will produce the same
what is the three ways to test reliability ?
Test-Retest Reliability, Internal Consistency Reliability ,Interrater Reliability
Test-Retest Reliability
Conduct the same test at a different time with the same participants to see if you obtain the same results
Internal Consistency Reliability
Examines how well the questions (items) relate to each other
Interrater Reliability
Look at if other researchers, who use the same methodology will achieve the same results. These researchers can be part of your research team
Validity
A synonym for validity would be accuracy. Results that are considered “valid” are representative of the real world
Internal Validity
means that we are certain that the changes in the IV caused the response in the DV and there are no alternative explanations
Construct Validity
is the degree to which this operationalized construct represents the true theoretical nature of the variable
Face Validity
Face validity implies that if something appears or looks valid, then it is valid
Content Validity
The content of the measure captures all the neccessary aspects of the construct and nothing more.
Concurrent Validity
Scores on the measure are related to ther measure of the same or very similar constructs
Discriminatory Validity
Scores on the measure are no related to other measures that capture theoretically different constructs
Predictive Validity
Scores on the measure predict behaviour on a criterion measured in the future
Reactivity
is when the participant is aware he/she is being observed and as a result changes his/her behaviour in some way (in other words they “react” to your presence”)
What are the four measurement scales?
Nominal (most basic)
Ordinal
Interval
Ratio (most advanced)
Nominal Scale
It is important to note that there is no rank or order in nominal scales. Number may assigned to represent these categories (Example: 1 = female; 2 = male 3 = prefer not to say)
Ordinal Scale
The ordinal scale is used when there is a bit more information about the data. In this case, we can determine that this is some sort of order or rank to the data. However, we cannot quantify what the difference is
Interval scale
The interval scale allows us to identify the order and quantify the difference between the elements. However, in the interval scale, the zero is arbitrary. It is a fake zero. (Ex: Temperature)
Ratio Scale
The ratio scale is the same as the interval scale, except that in the ratio scale the zero is real. In other words, it makes a total absence of something. Ratio and Real.
Discrete data
data cannot be divided into parts
Continuous data
data can be divided into parts
Central Tendency
Mode, Median, Mean
what is the symbol for mean?
is X (called x bar) or M (for mean)
Range
Range is the difference between the largest score and smallest score
What are two additional scales of measurement?
Continous or discrete data.
Chronbach’s alpha
an indicator of internal consisstency reliability assesed by examing the average correlation of each item (quesiton) in a measure with every other question
Pearson product- moment correlation coeefiicient
A type of correlation coeeficent use with interval and ratio scale data. In addition to providing information on the streagth of relationship between two vairables, the Peasron product- moment correlation coeeficient indicates the direction ( positive or negatve of the relationshi
