Chapter 3 Three Claims, Four Validities: Interrogation Tools For Consumers Of Research Flashcards

1
Q

What are the three claims??

A
  1. frequency
  2. association
  3. causal
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What do claims do?

A
  • make a statement about variable or about relationships between variables
  • argument someone is trying to make
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What is a variable?

A
  • something that varies, it must have at least two levels (values)
  • *core unit of psychological research (DV)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What is a constant variable?

A
  • something that could potentially vary but that has only one level in the study in question (IV)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What is a manipulated variable?

A
  • we control its levels by assigning participants to the varying levels of the variable
    ex: P1 gets 20mg, P2 40mg etc
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Measured variable?

A
  • researchers record an observation, statement or value
    ex: IQ, BP, Height
    also abstract variables like depression
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Variables can be described in what two ways?

A
  1. Conceptual definition

2. Operational definition

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

What is a conceptual definition of a variable?

A
  • when researchers discuss theory or journalists write about research….(abstract concepts)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is an operational definition of a variable?

A
  • when one turns a concept of interest not a measured or manipulated variable….needed for testing hypotheses via empirical research
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Give a run through example of both variable definitions.

A
  1. conceptual definition: weight gain

2. operational definition: WEIGH THEM

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

How are variables commonly stated as definition wise?

A
  • conceptually
  • to find out the operationalized variable look at how they were measured!
    ex How did they measure “X”.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Describe what a frequency claim is!

A
  • describe a rate or level of something
    ex: More than 2 million US teens Depressed
  • two million= frequency/count
  • they claim how frequent something is
  • claims that mention the % of a variable…the # of people who fit the description or some group lvl
  • do not show an associating between them and it does not claim one caused the other
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Frequency Claims only focus on how many variables? Measured or Manipulated?

A
  • only one variable

- ONLY MEASURED

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

Are Anecdotal claims frequency claims?

A

NO

  • they report a problem but do not say anything about the frequency or rate….
  • no report of the results of a social science study…they just show an illustrative story (no empirical back up)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What is an Association claim?

**also word indicators??*

A
  • argues that one level of a variable is LIKELY to be ASSOCIATED with a particular lvl of another variable
  • also called a correlate
  • linked, association, correlated, pedicured, tied to, is at risk for
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Association claims involve how many variables?Measured , manipulated?

A
at least two
only MEASURED  (this is what separates it from causal claims)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

What are used to see if two variables are related after measuring variables for an association claim?

A
  • descriptive statistics
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

What are the four types of Association Claims?

A
  1. positive associations
  2. negative associations
  3. zero associations
  4. curvilinear associations
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

Explain what a Positive Association is!

  • also called?
  • ex?
  • reped by?
A
  • aka + correlation
  • high scores go with high scores; low scores go with low scores
    Ex: High scores of abnormal fat go with more dementia symptoms
    Ex: Low scores of abnormal fat go with less dementia symptoms
  • scatterplots
20
Q

Explain what a Negative Association is!

  • also called?
  • ex?
  • reped by?
  • what does the negative refer to?
A
  • aka - correlation or inverse association
  • high scores go with low scores, and low scores go with high scores.
  • ex: High rates of cell phone usage tied to low sperm quality
  • scatterplot
  • negative only refers to the slope it does not mean the relationship is bad!
21
Q

Explain Zero association claims!

  • ex?
  • reped by?
A
  • no association btwn the variables
  • cloud of spots that has no slope and therefore a line draw through it would be nearly horizontal which has a slope of zero.
    Ex: ADHD is NOT linked to future drug abuse
  • scatterplot
22
Q

Explain Curvilinear Association claims!

  • ex
  • reped by
A
  • the level of one variable changes its pattern as the other variable increases.
    -ex: Relationships btwn Age and frequency of health care visits
    ( its a u relationship……when your young you visit a lot…as you get older not so much…then it increases once you are elderly)
  • scatterplot
23
Q

What is a prediction in regards to association claims.

A
  • mathematically looking to the future…aka using an association to make our estimates more accurate.
24
Q

Predictions and + /- associations?

A
  • if we know the level of one variable we can more accurately guess or predict the level of the other variable.
  • ex: Heavy cell phone usage tied to poor sperm quality. If we known the amount of cell usage we can predict sperm quality.
25
Are predictions from association claims perfect?
- no usually they are off via certain margin
26
When it comes to association claims and predictions, what makes them stronger/more accurate?
- if there is a strong relationship btwn two variables = more accurate prediction - even if there is a slight association it helps us make predictions vs if we did not know about the association.
27
With predicting association claims (+/-) if we know absolutely nothing about an association what will our predictions be based on?
- average values
28
Associations help us make predictions by reducing what?
the size of our prediction error
29
Can Zero association claims help us make predictions?
- NO - we cannot predict the lvl of one variable from the level of the other therefore our best bet is to guess the mean or avg.
30
Explain what a causal claim is! - the variables ____ - can be what three classifications - words that indicate causal ? - how are these held in comparison to other claims - tentative language that still means causal?
- argue that one of the variables is responsible for CHANGING the either - the variables covary - can be +, - or curvilinear - cause, enhance, curb - hold these to higher standards - could, may seem, suggest, possible,potential
31
What are the three steps to go from an association claim to a causal one?
1. establish two variables are correlated (cannot have a zero relationship.....the cause variable and the outcome v) 2. must show that the causal variable came first and the outcome v came last 3. establish no other explanation exists for the relationship
32
What are the four big validities?
1. Construct 2. External 3. Statistical 4. Internal
33
Valid claim??
- reasonable, accurate and justifiable | * never just say tis valid...we must specify the type
34
What two validates apply to interrogating frequency claims?
- Construct and External validity
35
Frequency Claim: | - Construct Validity ?
- how well did they measure their variables L> how well did the study measure or manipulate a variable - must establish that each variable has been measured reliably (similar scores on repeated testings) ad that the different lvld of a variable accurately correspond to the true differences.
36
Frequency Claim: | - External Validity?
- how well the results of the study generalize to or represent people and contexts besides those in the study itself! - ensure that participants rep the population they are suppose to
37
What are the three types of validity that apply to interrogating Association Claims?
1. Construct 2. External 3. Statistical
38
Association Claim: | - Construct Validity?
-assess each variable - how well were they measured L> if well we can trust the conclusions
39
Association Claim: | - External Validity?
- can the association generalize to other populations? other contexts, times, places?
40
Association Claim: | - Statistical Validity?
- statistics are sued to describe data and estimate the probability that results can or cannot be attributed to chance - extent to which stat conclusions are accurate and reasonable
41
Association Claim: - Statistical Validity? L> What two types of errors does good statistical validity minimize?
1. Type I Errors: based on results concluding there is an association btwn 2 variables when there is none. (false alarm) 2. Type II Errors: based on results conclude that there is one association when there is one. (Misses)
42
Covariance??
- As "A" changes, "B" changes
43
What are the three rules for Causation?
1. Covariance 2. Temporal precedence: one variable came first in time before another variable EX: Music lessons enhance IQ...Music lessons must be proven to come first before IQ gains 3. Internal Validity (third variable rule): a study should be able to rule out alternative explanations for the association.
44
How do researchers attempt to support a causal claim?
- experiment! L> gold standard of psychological research L> manipulate the variable they think is the cause and measure the variable they think is the effect. - Manipulated variable: IV -measured variable : DV
45
How do experiments provide temporal precedence and internal validity for causal claims?
- by manipulating one variable and measuring the other one can ensure that by manipulating the causal variable it came first. -can control for alt explanations (ensure internal v) L> ex: Random assignment: ensure participants are as similar as possible.
46
Causal Claims: 1. Does debt stress really cause health problems? 2. Do family meals really curb eating disorders? * * are these right or wrong ?
``` 1. A)Covariance: established! (positive association) B)Temporal Precedence: NO C) Internal Validity? NO...alt explanations are possible. 2. A) Covariance: YES B) Temporal Precedence: NO C) Internal Validity: noooooo ```
47
Causal Claims: 1. External Validity 2. Construct Validity 3. Statistical Validity
1. do the results generalize? 2. interrogate both the manipulated and measured variable (how well they were measured) L>operationalizing manipulated variables one needs to create a specific task or situation that will represent each lvl. 3. evaluate how well the design of the study allowed researchers to minimize the probability of making the relevant conclusion mistake a false alarm. How strong is the association?Is the difference statistically significant