Reading...
Play button
Play button
Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
20 Cards in this Set
- Front
- Back
|
__ variable can be measured but cannot be manipulated or controlled by the researcher . In a study assessing relationship b/t gender and beer consumption both variables are _____ b/c researcher can't control gender or consumption
|
Organismic
|
|
|
In a factor matrix, the factor loading for Test A and Factor II is .70. This means that which of the following is true.
A. 70% of variability in Test A is accounted for by factor II B. 49% of variability in Test A is acct for by factor II C. only 70% of variability in Test A is acct. for by the factor analyiss D. only 49% of variability in Test A is acct for by the factor analysis |
B. 49% of variability in Test A is acct for by factor II
A factor loading is the correlation coefficient for a test and an identified factor. It can be interpreted by squaring it to obtain a measure of shared variability. When factor loading is .70 this means 49% of variability in test is accounted for by that factor. |
|
|
To calculate an effect size (Cohen's d) you need what?
|
the means of the experimental and control groups.
The effect size is an index of treatment effects. Cohen's d indicates the magnitude of the effect of a tx in terms of the difference b/t the means of the tx and control groups. It is calculated by subtracting the mean of the control group from the mean of the tx group and dividing the result by a pooled standard deviation or by the control gp SD. |
|
|
Item response curve provides these three pieces of information about an item
|
its difficulty, ability to discriminate b/t those who are high and low on characteristic being measured and the probability of answering the item correctly by guessing.
|
|
|
It terms of item response theory, the slope (steepness) of the item response curve indicates the item's:
A. Difficulty B. Discriminability C. Reliability D. Validity |
Discriminability - the steeper the slope of the item response curve, the better its ability to discriminate b/t examinees who are high and low on the characteristic being measured.
|
|
|
To use the Taylor-Russell tables to evaluate a new selection test, you need info about which of the following
A. Predictor cutoff, criterion cuttoff and hit rate B. Base rate, hit rate and selection ratio C. Base rate, selection ratio, and validity coefficient D. Base rate, hit rate, and predictor cutoff |
C. Base rate, selection ratio and validity coefficient
Taylor-Russell tables are used to estimate a predictor's "positive hit rate" |
|
|
_________ variable influences the nature of the relationship between the IV and DV
|
Moderator variable.
|
|
|
A _______ variable explains (is responsible for) the relationship between an IV and DV
|
Mediating (intervening) variable
|
|
|
First individuals who are brought to the attention of the investigator (i.e., the people who are manifesting the disease or other characteristic of interest).
|
Probands (index cases)
|
|
|
In factor analysis rotating the factors has what effect
|
It changes the factor loading for the variables and the eigenvalues for each variable.
But the total eigenvalues remains the same. Purpose of rotation is to facilitate interpretations of the factors. |
|
|
________ is used to test the veracity of hypotheses about the causal relationship among a set of variables that are believed to measure or reflect latent traits.
|
LISREL or linear structural relations analysis which is a complex multivariate technique .
It assumes that there are both unidirectional and bidirectional relationships b/t latent traits and that measured variables reflect both latent traits and the effects of measurement error. |
|
|
Calculation of the utility of a training program in terms of dollar value includes which of the following:
A. T x d x C B. T - d x C C. T x C - d D. T + C + d |
T x d x C (part of formula for calculating utility)
Utility refers to the cost effectiveness of training and can be calculated using the formula T x N x d x SD - N x C where $U = utility measured in terms of dollars, T is number of years duration of programs effects on performance, N is number of people trained, d is effect size of program, c is per person cost of training |
|
|
In a ____________ skewed distribution, the mean is larger than the median which is larger than the mode
|
Positive - here distribution of scores is extended by a few outliers on the positive end. Median is always middle score so eliminate those answers.
B/c the mean is affected more than the other measures of central tendency by outliers it will be the largest number in a positively skewed distribution. |
|
|
In a ______ skewed distribution of scores, the mode is larger than the median which is larger than the mean
|
Negative
|
|
|
_________ is a multivariate technique that evaluates the viability of a causal model for a set of variables
|
Path analysis - characterized as a causal model technique. First step is to develop a causal modelt then PA is used to verify that model.
|
|
|
Autocorrelation would most likely be a problem when an investigator uses which of the following research designs
A. Between group B. Latin square C. Solomon four group D. Time series |
D. Time series - only this answer involves non-independent observations. It involves measuring the same people repeatedly before and after the intervention is applied.
Autocorrelation is a problem whenever observations are not independent. |
|
|
____ refers to probability that a test will correctly identify people without the disease from pool of people without disease
|
Specificity - calculated by
true negatives/ true negatives + false positives |
|
|
_______ refers to probability that a test will correctly identify those with disease from pool of those with disease
|
Sensitivity calculated by true positives/ true positives + false negatives
|
|
|
_______ probability that a person identified by the test as having the disease actually has the disease
|
Positive predictive value calculated by true positives/ true positives + false positives
|
|
|
_____ probability that a person indentified by the test as not having the disease actually does not have it
|
Negative predictive value calculated by
true negatives/ true negatives + false negatives |
