Ch3 Flashcards
The degree of differences within a set of test scores or among the values of a psychological attribute
Variability
Psychology is about variability in the behaviour of individuals
True
The behavioural sciences are largely about understanding differences among people, including differences among people in different groups or differences among people in different conditions
True
Variability is at the heart of research on the application of research in the behavioural sciences
True
Individual differences are also fundamental to psychological measurement. As described earlier measurement is based on the simple, but crucial assumption that psychological differences exist, and can be detected through well design measurement processes.
True
The existence and detection of individual differences lie at the heart of test, construction and test evaluation. Psychometric concepts, such as reliability and validity are entirely dependent on the ability to quantify the differences among people
True
All research in psychology and all scientific applications of psychology depend on the ability to measure individual differences
True
To quantify psychological differences, we begin by assuming that scores on a psychological test or measure will ( or at least can) vary from person to person or from time to time.
True
Then, taken from a group of people or a different points in time from the same individuals, instead of test, scores is called a “distribution of scores.”
True
A key element in most behavioural research is to quantify precisely the amount of the variability within a distribution of scores
True
Variance is a statistical way of quantifying, variability or individual differences in a distribution or set of scores.
True
Covariance is a way of quantifying the connection between variability in one set of scores and variability in another set of scores
True
Many fundamental concepts in psychological measurement, emerge from the detection and description of distributions of test scores
True
The most basic facet of a distribution of scores is “central tendency”
What is the “typical” score in the distribution or what is the score that is most representative of the entire distribution? Mean is the most common
The arithmetic “mean” represents the “typical” score in a distribution of scores.
Measurement rests on the concept of variability
If our measures are to be useful than they need to be sensitive to psychological viability ( they must reflect the differences in people’s standing on a psychological attribute)
We must be able to quantify the variability within a distribution of scores
The variance and the standard deviation reflect variability as the degree to which the scores in distribution deviate from the mean of the distribution
The numerator of the variance is sometimes called the sum of a squared deviations about the mean.
Sum of squares
As an index of variability, the standard deviation has the advantage of reflecting variability in terms of squared deviation scores.
The variance and standard deviation are fundamental elements of many psychometric concepts. Their interpretation is not always clear.
The size of the variance and consequently the size of the standard deviation is determined by two factors
- The degree to which the scores in a distribution differ from each other‘s.
- The metric of the scores in the distribution.
The dramatic difference in the two variances arises largely because of the dramatic difference in the metrics of the two sets of a scores
Considering the nature of variance and the factors that affect its size, there are four factors to consider when interpreting a variance or standard deviation
Neither one can ever be less than zero
At a minimum they can be zero, which indicates that the score is in the distribution do not vary at all
Mathematically and conceptually it is impossible to have a negative variance or standard deviation
There is no simple way to interpret a variance or standard deviation as large or small
The variance of a distribution of scores is most interpretable and meaningful when it is put into some kind of context
The distribution with the larger variance has a greater the liability, then the distribution with a smaller variance
True
The importance of variance and standard deviation lies, mainly in their effects on other values that are more directly interpretable
The variance and standard deviation or fundamental components of many psychoment concepts and procedures , for example, variance and standard deviation are key to concepts, such as the correlation, coefficient, the reliability, coefficient, confidence, intervals, and test bias
It distributions shape can be quantified in terms of its amount of skew.
True
Perfectly symmetrical distribution has a skew value of 0
True
Asymmetrical or “skewed distributions” have skew values below or above 0.
Distributions with relatively few values above the mean are “positively skewed” and have skew values greater than 0.
Distributions with relatively view values below the mean are ”negatively skewed” and have skew values below 0.
The more dramatically skewed or asymmetric a distribution is the larger it’s skew value will be (above or below 0).
Positive or direct association
High score in both variables
We are looking for two types of information:
Association between two variables ( between two distributions of scores)
- The direction of the association ( do people who Upton relatively high scores on one variable tend to obtain relatively high scores on the other?) if so, then, we say that the two variables have a positive or direct association.
However, if people who obtain relatively high scores on one variable tend to obtain relatively the lowest scores, on the other, we say the two variables, have a negative or inverse association.
Contd- Type of information that even like to know about the association between two variables
- The magnitude of the association.
Are two variables, very strongy associated, or only the weekly associated
Strong associations either positive or negative indicate a high level of consistency between two variables week associations indicate inconsistency.
A scatterplot represents the association between two variables, in terms of an upward or downward trend of points
And upward trend (going from lower left to upper right) indicates that the relatively high scores on one variable tend to go along with relatively high scores on the other variable
Then a scatter plot has a downward trend, going from upper left to lower right then relatively high scores on one variable tend to go along with relatively those scores on the other variables
Class absences and lower GPA
Is scatterplot that has no clear up or downward trend indicates inconsistency between variables 
Scatterplots can be extremely useful when trying to understand the association between two variables
Covariance begins building a bridge between the concept of variability and an interpretable quantitative index of covariability
In contrast, covariance is computed from the variability among scores into different distributions
The covariance represents the degree of association between the variability in the two distributions of scores
The correlation coefficient is intended to provide an easily interpretable index of linear association
True
Like the Covariance a correlation coefficient reflects the “direction” of the association between two variables 
A correlation with a value that lies between 0 and +1, tells us that there is a positive association between the two variables. In contrast, the correlation be the value that lies between 0 and -1 tells us that there is a negative association between the two variables.
The great benefit of a correlation is that it reflects the magnitude of the association between two variables, much more clearly than does the Covariance.
A correlation that is close to 0 reflects a weak association
The correlation coefficient is an important part of reliability theory
The Pearson correlation is most appropriate for two variables that are on an interval or ratio scale of measurement
Total test score variance will depend solely on item variability and the correlation between item pairs. This issue is an important facet of reliability theory.
Dichotomous or binary items
Behavioural observations that have been scored dichotomously
Tests based on binary items are typically scored by summing or averaging responses across items
True
The mean of a binary item is equal to the proportion of positively valenced answers