Exam 2 Homework Questions Flashcards
If you want to know that a test measures some underlying psychological construct, what type of validity evidence would you want to collect?
Construct Validity
If you correlate scores from your test with some other valid measure that assesses the same set of abilities, what type of validity evidence are your collecting?
Criterion Validity
Cronbach’s Alpha is used to calculate what?
Internal Consistency Reliability
Two trained professionals observe the behavior of children in a classroom. They each rate observed behaviors using the same form and the number of items that were rated the same is calculated. This is an example of which type of reliability?
Interrater
The maximum level of validity possible is equal to what?
The square root of the reliability coefficient
What would the inter-rater reliability be for a 50 item measure in which the number of agreements between Rater 1 and Rater 2 was 45?
0.90
If data are not reliable or not valid, the results of any test or hypothesis…
are inconclusive
Which of the following is concerned with monitoring estimates of present performance and predictions of future performance?
Predictive Validity
This type of validity is determined by the association between the test scores and some specified present or future criterion.
Criterion Validity
This explores the question “how do I know that the test, scale, instrument, etc. measures what it is supposed to?”
Validity
The treatment variable in an analysis is called the…
Independent Variable
The actual or measured score is called _______
The observed score
This is the level of measurement where outcomes are based on some underlying continuum where it is possible to speak about how much more a higher performance is than a lower one:
Interval
What is the key to establishing Criterion Validity?
Quality of Criterion
The correlation between scores from time 1 and time 2 is called:
Test-Retest Reliability
This is the difference between the observed and true scores:
The Error Score
Only this level of measurement has a true zero
Ratio
In terms of the reliability of test scores, there are multiple elements to each person’s score. The score that is actually recorded is the…
Observed Score
High school class rank is highly correlated with college GPA. This is an example of what type of validity?
Predictive Validity
The outcome variable in an analysis is called the…
Dependent Variable
What is the annotation for the experimental population?
Mu 1
What is the annotation for the general population?
Mu2
Optimally, it is possible to generalize you results from ________ to _________.
Your sample/A Larger Population
What type of hypothesis posits a difference between groups where the difference is specified?
Directional hypothesis
Which of the following is an example of a nondirectional hypothesis?
There is a relationship between a high-fat diet and weight gain.
Which of the following is an example of a directional hypothesis?
There is a positive relationship between a high-fat diet and weight gain.
Which of the following means “before the fact”?
A priori
What test would you want to use to test a nondirectional research hypothesis?
Two-tailed Test
If there is no difference between sample and population values, you will have:
No sampling error
A hypothesis is best defined as ______________.
An educated guess
A statement that postulates a relationship between variables is referred to as a ___________.
Research hypothesis
The null hypothesis refers to the ___________, whereas the research hypothesis refers to the __________.
Population/Sample
A sample is best defined as ________________.
A smaller group selected from a given population
What test do you use to measure a directional research hypothesis?
A One-Tailed Test
Null hypotheses refer to the following:
The Population
The group you actually collect data from for your study is known as the __________.
Sample
Which of the following is a measure of how well a sample approximates the characteristics of a population?
Sampling error
If you were to hypothesize that test scores from classroom A will be higher than test scores from classroom B, you have a:
Directional research hypothesis
In order to help ensure generalizability, which of the following should be true about your sample?
It is representative
A smaller difference between the sample statistic and the population parameter means that you will have:
A Lower Sampling Error
Research hypotheses refer to the following:
The sample
Which of the following is a nondirectional test?
A two-tailed test
To calculate a z score, you:
Subtract the mean from the raw score and divide this difference by the standard deviation
Which of the following is a characteristic of the normal curve?
Mean, median, and mode are the same
If a distribution has a mean of 25 and a standard deviation of 2, what value would be -4 standard deviations from the mean?
17
What type of standard score has M=0 and SD=1?
Z-Score
In a distribution with a mean of 100 and a standard deviation of 15, what is the probability that a score will be 115 or higher?
16%
The fact that the tails of a normal distribution never touch the horizontal axis relates to the following property:
Asymptotic
If you want to calculate a z score for a test where your raw score was 24, what other information must you know?
Mean and standard deviation
Which of the following is true of z scores that fall above the mean?
They are positive
T scores and z scores are both considered what type of score?
Standard Score
When we want to infer from a sample to the population, what assumption must be met?
Population is normally distributed
What is the T score for a z score of -1?
40
Under the normal curve, approximately what percent of scores fall between -1 and -2 standard deviations below the mean?
14%
What two scores would divide a normal distribution such that 64.26% of the general population falls within them if the mean is 100 and the standard deviation is 15?
85 to 115
If a distribution has a mean of 1000 and a standard deviation of 100, how many standard deviations is 600 from the mean?
-4
What is the basis for the normal curve?
Probability
What characteristic of the normal curve deals with skewness?
Mean, median, and mode
z scores which fall above the mean will be ________________.
Positive
Under the normal curve, if a z score of 1.65 included 45% of the area above the mean, what percent remains above 1.65 on the X axis?
5%
A score that is three standard deviations above the mean would have a z score of:
3
This percentage of scores fall on either side of the distribution:
50%
When you accept a false null hypothesis, you are making a ______________.
Type II Error
What does 1 - β represent?
Power
If you want to examine the difference between the average scores for students on a pre-test/ post-test measure, which statistical technique should you select?
Dependent Samples T-test
How well a statistical test can detect and reject a null hypothesis when it is false refers to ______.
Power
If you want to examine the difference between the average scores of two unrelated groups, which of the following statistical techniques should you select?
Independent Samples T-Test
After you compare the obtained value with the critical value, you:
Reject the null hypothesis if the obtained value is more extreme than the critical value
After you provide a statement of the null hypothesis, you:
Set the significance level
p < .05 means that there is less than 1 chance in ____ that any differences found were not due to the hypothesized reason.
20
The significance level is also known as ________________.
Type I Error
Power is equal to:
The value of the type II error subtracted from 1
Type II error is related to a factor such as _________________.
Sample size
The degree of risk you are willing to take that you will reject the null hypothesis when it is actually true is called ______________.
Significance Level
As compared with a 95% confidence interval, a 99% confidence interval would result in:
A wider range of values in the confidence interval
If the obtained value is greater than the critical value, what should you do?
Reject the null hypothesis
When you reject the null hypothesis when there is actually no difference between groups or relationships between variables, you are making a:
Type I error
The level of chance or risk that you were willing to take is expressed as …
A significance level
A(n) ____________ difference is due to some systematic influence and not due to chance.
Significant
Which of the following is a statement of equality?
Null hypothesis
What is the error that cannot be controlled called?
Chance
