Chapter 9: Introduction to Simple Experiments Flashcards

1
Q

What does an experiment mean?

A

that researchers manipulated at least one variable and measured another

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

A variable is manipulated when the researchers assign participants to?

A

one level or another of the variable

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

Measured variables take the form of records of ___ or _____ such as (3)

A

behaviour or attitudes

L> self report, behavioural or physiological measures.

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

What is the manipulated variable called?

A

IV

L> researcher has some independence in assigning ppl to different levels of this variable

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

Levels are also called what?

A

conditions

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

The measured variable is called?

A

DV
L> how a participant acts on the measured variable depends on the lvl of the IV….researchers have less control over the DV

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

On a graph typically where are the IV and DV’s placed?

A

x-axis: IV

y-axis: DV

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

When manipulating an IV researchers need to make sure that they are varying what?

A

only one ting at a time….aka just the potential causal force or treatment

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

How do researchers control of third variables/nuisance variables ?

A

by holding all other facts constant between the levels of the independent variable

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

Any variable held constant by a researcher is called what?

A

control variable

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

Are control variables really variables?

A

no because they do not vary

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

What do control variables allow researchers to do?

A

separate one potential cause from another and thus eliminate alt explanations…..they establish internal validity

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

Three rules for causation?

A
  1. covariance ( are lvld of the IV associated with the distinct levels of the DV)
  2. temporal precedence ( does the causal variable before the effect variable in time )
  3. internal validity ( are there alt explanations for the results)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

If IV’s did not vary a study could not establish what?

A

covariance

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

How are experiments always set put to look for covariance?

A

because they manipulate an IV and because every IV has at least two levels

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

Control group?

A

a level of IV that is intended to represent no treatment or neutral condition

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

If an experiment has a control group what are the other levels of the IV called?

A

treatment groups

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

Placebo group?/Placebo control group?

A
  • when the control group is exposed to an inert treatment such as a sugar pill
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

All experiments need a comparison group so that the researchers can do what?

A

compare one condition to another …..the control group does not need to be a control group

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

What is a strong advantage of experimental designs?

A

ability to establish temporal precedence by controlling which variable comes first ..they ensure the cause comes before the effect.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

What makes experiments superior to correlational designs?

A

temporal precedence

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

What is the most important validity when it comes to causal claims?

A

internal validity….have to ensure that the proposed causal variable and not other factors is responsible for influencing the DV

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

Confounds?

A

alt explanations…..aka confused as to what is causing the change in DV

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

Design Confound?

A

refers to a second variable that happens to vary systematically along with the intended IV and therefore is an alt explanation for the results

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
Q

When an experiment has a design confound it has poor what?

A

internal validity….and cannot support a causal claim

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
26
Q

Systematic variability?

A

occurs with the IV

L> did experimenters work differently with the varying groups

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
27
Q

Unsystematic variability?

A

random/haphazard….. experimenters treated all the groups the same when manipulating the iV

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
28
Q

Unsystematic variability can lead to what?

A

it can obscure the DV (make it hard to detect differences)

L> its not a design confound

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
29
Q

Selection effect?

A

occurs when the kinds of participants at one level of the V are systematically different from the kinds of participants at the other level of the IV.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
30
Q

Selection effects are an example of a confound in which the alt explanation is related to ?

A

the types of participants placed in each level of the IV.

31
Q

When can selection effects occur?

A

they occur when experimenters allow participants to choose which level of the IV they want to be in.
L> if experimenters assign one type of person to one condition and another type of person to another condition.

32
Q

Variability in motivation becomes a confound only when what?

A

the more motivated folks are all in one group that is when the variability is systematic

33
Q

Random assignment is used to what?

A

to avoid selection effects …so each participant has an equal chance of being in an IV group…Assigning participants at random to different levels of the IV

34
Q

Random assignment can often result in a fairly ___ distribution.

A

even
L> it systematize the types of participants who end up in each level of the IV ….it spreads differences out evenly….so groups become virtually equally before the IV is applied

35
Q

Random assignment does not always work well when the sample size is small or large?

A

small

36
Q

Matched group design?

A

researchers first measure the participants on a particular variable that might matter to the DV then they match participants up set by set (take participants with in a certain level) and within that matched set, randomly assign one of them to each groups in the study. (makes the groups more even)

37
Q

Matched group design has an advantage of randomness…. it prevents selection effects. This method ensures that the groups are ___ on some important variable before the manipulation of the IV.Downside?

A

equal

L> requires an extra step

38
Q

Independent groups design?

A

different groups of participants are placed into different levels of the IV
- also called between subjects designs or between groups design

39
Q

Within groups design?

A
  • there is only one group of participants and each participant is present with all levels of the IV
  • also called within subjects design
40
Q

what are the two types of independent group designs?

A

post-test only design and pretest/posttest designs

41
Q

Posttest only design?(3)

A
  • simplest independent groups design
  • participants are randomly assigned to IV groups and are tested on the DV once
  • meet all three rules of causation
42
Q

Pretest/posttest designs?

A

participants are randomly assigned to at least two groups and are tested on the key DV twice…once before and once after exposure to the IV

43
Q

Pretest/posttest designs are used to evaluate what?

A

whether random assignment made the groups equal….especially when group sizes are on the small time.
L> allowing researchers to be sure no selection effects are occurring…..

44
Q

Pretest/posttest designs work well to track what in regards to participants?

A

how those in the experimental groups have changed over time.

45
Q

Posttest only designs are the most basic designs and its combination of ____ and ____ a lose it to lead to powerful causal conclusions. The pretest/posttest design adds a ____ to the most basic independent groups design.

A

random assignment and manipulated variable

pretesting

46
Q

Types of within groups designs?

A
  • concurrent measures design

- repeated measures designs

47
Q

concurrent measures design?

A

participants are exposed to all the levels of an IV at roughly the sam time and a single attitudinal or behavioural preference is the DV
ex: taste test

48
Q

Repeated measures designs?

A

participants are measured on a DV more than once that is after exposure to each level of the IV

49
Q

Whats the principle advantage of within groups design?

A

ensures that participants in the two treatment groups will be equivalent after all they are the same participants.

50
Q

What occurs in within groups designs when all participants are exposed to all IV groups?

A
  • other variables are kept constant…….it treats each participant as his or her own control…
51
Q

Can matched group designs be sued in within groups designs?

A
  • yes
  • carefully match sets of participants on some key control variable and assign each member of a set to a different group.
52
Q

Within groups designs gives more or less power to notice differences between conditions?

A
  • more
53
Q

Power?

A

ability of a sample to show a statistically sig result when something is truly going on in the population

54
Q

Order effects in within groups designs ? (carryover effects, practice effects)

A
  • threaten internal validity
  • aka participants performance at later levels of the IV might be caused not by the experimental manipulation but rather by the sequence in which the conditions were experienced. It can lead to practice fatigue, boredom or some other contamination that carries over from one condition t the next
55
Q

Counterbalancing?

A
  • present the levels of the IV to participants in different orders…..when this is used any order effects should cancel each other out when all of the data are collected.
56
Q

To counterbalance conditions in a within groups design what must be done?

A

participants must be split into groups and each group receives one of the condition orders….which is done through random assignment

57
Q

Full counterbalancing?

A

when a within groups experiment has only two r three levels of an IV experimenters use this…..in which all possible condition orders are represented.

58
Q

With full counterbalancing as the the number of conditions increase what is the issue?

A
  • the number of possible orders needed for full counterbalancing increases dramatically.
59
Q

Partial counterbalancing?

A
  • only some of the possible conditions orders are represented. (within groups)
60
Q

How is partial counterbalancing is done?(2)

A
  • present the conditions in a randomized order for each subject
    L> latin square: a formal system of partial counterbalancing that ensures that each condition appears in each position at least once.
61
Q

Disadvantages of within groups designs?(3)

A
  1. order effects (usually controlled for efficiently via counterbalancing)
  2. when people see all levels of the IV ad then change the way they would normally act
  3. demand characteristics: when an experiment contains cues that lead participants to guess its hypotheses….and participants try to be “good participants”….answering how they think the experimenters want them to
62
Q

Within group designs are similar to pretest/posttest how? Difference?

A
  • they both test participants twice..before and after
  • in within groups: participants are exposed to all levels of the IV
  • prettest/posttest: levels of an IV is not normally the central IV of a study…and pretest and post-test cannot be counterbalanced
63
Q

Interrogating causal claims with construct validity?

A
  • DV: how well it was measured

- IV: how well the researchers manipulated them

64
Q

Manipulation checks?

A
  • collect empirical data on the construct validity of their IV. It is an extra DV that researchers can insert into an experiment to help them quantify how well an experimental manipulation worked.
65
Q

Manipulation checks:

L> Pilot study?

A
  • a simple study using a separate group of participants that is competed before (sometimes after) the study of primary interest is conducted. They confirm the effectiveness of their manipulations.
    L> establishes construct validity
66
Q

Theory testing?

A

standard for evaluating these operational variables

67
Q

External validity?

A

can the causal claim generalize to to other people, places and times

68
Q

External validity?

L> participants?

A
  • how they are recruited
    L> random sampling: randomly gathering a sample from a population…
    (internal validity: ask about random assignment …randomly assigning each participant in a sample into one experimental group)
69
Q

Many experimenters decide to sacrifice real world representativeness for?

A

internal validity

70
Q

Running an experiment on a relatively homogenous sample means that ____ is less likely to obscure the effect of the IV.

A

unsystematic variability

71
Q

Statistically significant?

A
  • whether the difference between means obtained in the study is stat sig. When the difference is stat sig it is unlikely to have been obtained by chance from a population in which nothing is happening. ….it suggests that covariance exists between the variables in the population the sample was drawn from
72
Q

Effect size?

A

larger the effect size the more important and stronger the causal effect is
L>evaluating the covariance
L> correlation coefficient r
L> standardized d

73
Q

What does standardized d represent?

A

how far apart two experimental groups are on the DV
- group overlap
L> larger= IV caused DV
L> small= lots of overlap between two experimental groups.

74
Q

Conventions for effect size d?

A
  1. 20= weak/small
  2. 50= moderate/medium
  3. 8=stronge/large