Ch 3: Research Methods and Study Design (Princeton Review)

Question 1

What is the independent variable in an experiment?

Answer 1

The variable being manipulated by the research team.

Question 2

What is the dependent variable in an experiment?

Answer 2

The variable being measured.

Question 3

To obtain rigorous results, the researchers must create an ___________ definition, a specification of precisely what they mean by each variable.

Answer 3

operational

p. 38

Question 4

Define experimental group.

Answer 4

The group of study participants that receives the treatment or intervention.

p. 39

Question 5

Define the control group.

Answer 5

The group of study participants that is purposely excluded from receiving the treatment or intervention.

Question 6

Why is assigning a control group one of the most important aspects of impaired experimental design?

Answer 6

Because without one, a study is not experimental and causal relationships cannot be drawn.

Question 7

What is a confounding variable?

Answer 7

A variable other than the treatment that could potentially explain an experimental result.

Question 8

What is the placebo effect?

Answer 8

The phenomenon that believing treatment is being administered can lead to a measurable result.

Question 9

What is meant by a double blind study?

Answer 9

That neither the person administering treatment nor the participants truly know if they are assigned to the treatment or control groups.

Question 10

If it is not equally likely for all members of a population to be sampled for an experimental study, this is known as …

Answer 10

…sampling bias.

Question 11

The concept of construct validity most usually applies to __________ instruments such as surveys.

Answer 11

psychometric

Question 12

What is psychometrics?

Answer 12

The study of how to measure psychological variables.

Question 13

What is the difference between a between-subjects design and a within-subjects design?

Answer 13

In a between-subjects design, the comparisons are made between subjects from one group to another. In a within-subjects design, the same group is compared at different points in time.

Question 14

What is meant by “mixed methods” research?

Answer 14

Any combination of different research techniques, such as within-subjects and between-subjects, or qualitative and quantitative.

p. 42

Question 15

What is a type I error?

Answer 15

A false positive.

Question 16

What is a type II error?

Answer 16

A false negative.

Question 17

What type of error, type I or II, is worse?

Answer 17

Scientists over the years have generally agreed that it is better to incorrectly conclude that there is no effect (type II error) then to falsely suppose the veracity of a result that does not actually exist (type I error). One way to remember this distinction is to think of type I error as predominant, because it is a graver problem in hypothesis-testing. Much like the legal concept of “innocent until proven guilty”, it is better to reason from a point of skepticism.

p. 42

Question 18

Scientists generally start with the ____ __________: they assume that there is no causal relationship between the variables and any effect that they measure, and if there is one, is due to chance. Then they see whether evidence from the experiment suggests that the null hypothesis is true or false. Taking this position and reasoning in this way places the “burden of proof” on the ____________ hypothesis, the proposition that variations in the independent variable causes changes in the dependent variables.

Answer 18

null hypothesis

experimental

Question 19

The truth about statistics is that whatever point you choose as the threshold to indicate that the results are not due to chance, will inherently be _________.

Answer 19

arbitrary

p. 43

Question 20

Conventionally, social scientists have decided that if the probability of an observed difference is found to be 5% (or 0.05) or less, this constitutes a significant difference. By convention, scientist can ______ ___ ____ __________ when the p value is less than 0.05.

Usually, __ or more participants are necessary to meet the mathematical criteria needed to conduct statistical tests.

Answer 20

reject the null hypothesis

30

p. 43

Question 21

There are many, but name some examples of threats to INTERNAL validity.

Answer 21

Impression management (e.g. Hawthorne Effect – type of reactivity in which individuals modify an aspect of their behavior in response to their awareness of being observed)

Confounding variables (alternative explanations for results)

Lack of a control group*

Lack of reliability of measurement tools

Sampling bias - selection criteria is not random, or population is not normally distributed

Attrition effects - participants fatigue or drop out of study

Demand characteristics - participants interpret what the experiment is about and subconsciously respond in ways that are consistent with the hypothesis

• example of this found in practice questions
  p. 45

Question 22

Name the four main threats to external validity.

Answer 22

Experiment doesn’t reflect real world – laboratory set ups that don’t translate to the real world, lack of generalizability

Selection criteria - too restrictive of inclusion/exclusion criteria for participants (sample is not representative)

Situational effects – presence of laboratory conditions changes outcome

Lack of statistical power - sample groups have high variability; sample size is too small

p. 46

Question 23

In general, non-experimental designs tend to offer the benefit of observing phenomena in a more naturalistic setting, often improving ________ ________. The trade-off is reduced control of the variables of interest, which tends to reduce the internal validity.

Answer 23

external validity

p. 47

Question 24

correlational studies are a type of non-experimental design. They explore the relationship between two quantitative variables. The most common type of correlation is the Pearson correlation. Explain this concept.

Answer 24

A Pearson correlation assigns a number from -1 to +1 one to a pair of variables. If the value is negative the two variables are negatively correlated. On the other hand a positive value represents a positive correlation meaning that as one variable increases the other also increases, and vice versa.

Question 25

When two variables are found to be positively correlated, this does not imply that one variable causes the other. What are some other possible explanations?

Answer 25

The causal relationship could go in either direction (A causes B or B causes A, or some third variable could be responsible for both.

p. 47

Question 26

what is an ethnographic study?

Answer 26

It’s a qualitative method in which researchers immerse themselves completely in the lives, culture, or way of life of the people they are studying.

p. 47

Question 27

What is an intervallic measurement, and what type of study does this get used for?

Answer 27

Intervallic simply means pertaining to intervals.
This type of measurement is utilized for longitudinal studies.

p. 48

Question 28

What qualifies as an observational study?

Answer 28

Any study in which individuals are observed and outcomes measured with no attempt to control the outcome.

Question 29

Name as many types of non-experimental designs as you can.

Answer 29

Correlational
Ethnographic 
Twin 
longitudinal 
case study 
phenomenological 
survey 
archival 
biographical 
observational 

p. 50-51

Question 30

Variables which are measured along a continuum tend to be __________ in nature, whereas most categorial variables tend to be qualitative.

Answer 30

quantitative

(Review this many times; this seems counterintuitive to me.)

p. 59

Question 31

Define external validity.

Answer 31

The extent to which experimental results can be applied to real-world situations.

p. 384