question 2 Flashcards

1
Q

how can a test be reliable and not valid? and not valid unless reliable?

A

a test can be reliable and not valid and not the other way around, because a test can do what it does over and over, but still not do what it suposed to do

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

explain what would a test be if it valid and

not reliable

A

If a test cannot do anything consistently, then it can’t do one thing consistently

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

when testing an hypothesis, what is important to test to ensure that the outcome is both reliable and valid?

A

because if you get a null result, you will never know that the tool is not measuring what it is supposed to measure or if the hypothesis is faulty

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

describe the differences between content, criterion and construct validity, with examples

A

content looks on the face of a test within an area/universe. is stats test content reflect stats book?
predictive=how well test predicts outcome how well GRE test predicts a good graduate??
content validity is when test asses an underlying theory

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

How are validity and reliability used in research?

A

your experiment will always be in doubt

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What’s the overlap between statistics and validity/reliability?

A

statistics revolves around outcomes being measured, you need to reliability and validity to make sense of how behaviors/test scores/rankings/ratings are assessed.interpretation of data has consequences so statistics don’t mean anything unless we are confident that we know what we are looking at.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

why can we not use the null hypothesis in research reports?

A

because it implied, and cannot be directly tested

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

what does not finding validity evidence mean?

A

your test is not doing what it should, and you need to redo the questions

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

what does not finding the criterion validity means?

A

need to re examine the NATURE OF ITEMS

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

what does not finding the construct validity means?

A

need to take a CLOSER LOOK @ THE UNDERLYING THEORY

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

why is NH a starting point?

A

because it is a statement of that states that given no other information, thisis what I will say. UNBIASED& OBJECTIVE

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

how is the normal curve and probability related?

A

the normal curve visually represents what possible outcomes (likehood) we can get in a given situation.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

How do I know whether a distribution is negatively skewed?

A

when the scores are in the upper range

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

How do I know whether a distribution is positively skewed?

A

when the scores are in the lower range

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

How do I know whether a distribution is not skewed?

A

when the ditribution has equal lenght of tails and everyone scored the same.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

when do I use a bar/column chart?

A

to compare TWO CATEGORIES

17
Q

when do I use a line chart

A

to show a TREND

18
Q

When do I use a pie chart?

A

to show different PROPORTIONS

19
Q

difference between column and bar chart

A

bar: CATEGORIES ON Y(VERTICAL)
VALUES ON X (HORIZONTAL)
column CATEGORIES ON X (VERTICAL)
VALUES ON Y (HORIZONTAL)

20
Q

What does the coefficient of determination represent? if you have the value of the correlation (r) how do you get the value of the coeeficient of determination?

A

the percentage of variance in one variable that is accounted for by the variance in the other variable. The larger the absolute value of r, the more the 2 variables share (strongly related). if we sqaure r we find out exactly how much the variance in one variable is accounted for in the other variable