Week 7-8: non experimental research, complex designs Flashcards

1
Q

What’s archival research and another name for it ? (old.. to learn..)

A

Can be called secondary research as someone other than the researcher is collecting it. Archival research is old research we use to learn something new

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

What’s the difference between meta analysis and thematic analysis? ( running many .. sum..) ( make sense of.. unrel… by analyzing what? to gain in..)

A

Meta analysis: Taking many studys and running tests/stats on them to summate them together as one

Thematic anaylsis: Make sense of seemingly unrelated material by analyzing qualitative data to gain info/insight on collected data

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

What’s the cohort effect? (different res..)

A

Different researchers get different summations

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

Why doesn’t Elliott like thematic analysis? (i’m not a published author, is it valid?, where are u getting info from?) (3 things)

A

Need published co author first time if not published author
Not subject to rigorous scholar documentation
Ethically harder, very risky as you need quotes from ppls storys

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

What are focus groups how many ppl do they usually have how long are they and what’s their advantages and disadvantages? (groups of ppl discuss..) adv: reveal.. and gain., fast, genuine.. (3 things for advantages) disadvantages: trained..,money, wrong..

A

Focus groups are group interviews to explore what consumers want in a product/thing and what they think about it already. about 8-12 people per group 1.5-2.5 hrs long and recorded

Advantages: reveal and gain insight of perceptions, faster than single interviews, provides genuine group discussion and in-depth answers

Disadvantages: need trained moderater,expensive, can be wrong or misleading information

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

What’s triangulation? (how they correlate)

A

Putting 3 pieces of information/articles together to see how they correlate

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

What is regression? (predictor variables, outcomes)

A

Predictor variables trying to predict the outcomes variables

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

What is total variability?

A

Variability between scores and the mean

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

Why are complex designs necessary? (3 things- effect two things, determine .., measure diff..

A

To control for things taht could affect IV or DV

to determine obscure details
To measure different variables

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

What is a moderator variable it’s criteria and what does it affect?(interferes with.., and effects s and d.. must NOT BE a…)

A

A moderater variable is things that interfere with the relationship between IV and DV so it AFFECTS the strength and direction of relationship

IT MUST NOT BE A CAUSAL RESULT OF IV

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

What is a mediator and it’s criteria and function?

A

Mediated is the way IV impacts the DV and explains the process in which the two variables relate.

MUST BE CAUSAL RESULT OF IV AND CAUSAL EVENT OF THE DV

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

What’s the file drawer problem? (pub bias.., positive results than..)

A

type of publication bias, more likely to submit positive results than negative to publishers

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

What are 4 types of correlation and are they parametric or non parametric??

A
  1. Pearson -parametric
  2. Spearmen-non parametric
  3. Partial correlation-parametric
  4. Kendall’s-tau-non parametric
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What can the 4 correlations do or have? (ties,scales,variance,changes)

A

Kendall’s-tau: can have many ties
Spearmen- can do correlation between likerd scales
Partial correlation- sees variance of multiple variables by isolating variance then taking out to see other variances
Pearson-changes in direction

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

What are the three types of t test and what do they measure? ( WS, BS, SS/D)

A

Within subjects t test- measures two time points making it repeated measures

Between subjects t test- measuring groups once, usually 2 groups a couple factors

Single sample/difference t test: measures to see difference between two things can be time points, knowledge

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

What are the 6 t test assumptions (needs 2.., no sig.., homo!, devil continues, bell curve, no snowball sampling (obser… indep..)

A
  1. Iv needs two independent groups
  2. no significant outliers
  3. homogeneity of variance
  4. DV is continuous
  5. normal distribution
    6,. should have independence of observations- nothing occurred as a snowball
17
Q

What does it mean to have a robust test? (3 things, robust against homo of v.. and norm… d) THInk rules

A

Even if assumptions are broken a robust test will still provide insight to data, such as F tests or T tests which are robust against homogeneity of variance and normal distribution

18
Q

What does F represent? (var..)

A

Variance accounted for and unexplained variance

19
Q

What makes a good research sample

A
  1. equal group sizes
  2. having gender included usually
    3.. no significant outliers or accounting for them if so
  3. large sample by random selection
20
Q

What are main effects?

A

The main factors/things being affected in factorial designs

21
Q

What’s mundane realism and what form of validity is it?

A

External validity, existent to which experiment matches real world

22
Q

What else can a partial correlation be known as?

A

Covariate

23
Q

What’s the advantage of finding main effects over doing many t tests?(2 things)(family,T what?)

A

Wont see T interaction
Increase family wise error rate
See relationship between variables

24
Q

Why do we look at interactions between factorial designs? (2 things) (we think it.., inter..)

A

We think interactions make a difference
Want to see interactions to see how variables correlate

25
Q

What are main effects

A

The main factors being effected in factorial analysis