Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

Statistics 2000 > Chapter 4 > Flashcards

Chapter 4 Flashcards

1
Q

What are the two ways to gather data?

A

1) Conduct an experiment.

2) Take an observational study.

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

Experiments

A

attempt to manipulate or influence the subjects in order to obtain the data.

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

T/F In experiments subjects are usually randomly assigned to groups

A

True.

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

T/F In-properly designed experiments can be used to prove causation?

A

False, properly designed experiments can be used to prove causation.

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

Observational study

A

Measures the characteristics of the subject without attempting to manipulate or influence objects.

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

T/F Observational studies can prove causation?

A

False, cannot prove causation. They can conclude that two variables are related. Association does not imply causation.

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

What is the goal of observational studies?

A

Not only to describe the sample we see, but hopefully generalize characteristic of the sample to a much larger population of individuals. But this only works when samples are representative of the population.

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

Simple random sampling

A

Randomly selecting values from a list. This is the most basic, unbiased, sampling method. Each subject in a population has the same chance of being included in the sample.

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

Stratified Sampling

A

The population is divided into non-overlapping groups and a random sample is obtained from each group. “Few subjects from all groups”

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

Cluster Sampling

A

The population is divided into non-overlapping groups and all individuals within a randomly selected group or groups are sampled. “All samples from a few groups” Needs a larger sample in order to achieve a particular margin of error. Can be cheaper and more effective when a random sampling is not feasible.

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

Convenience sampling

A

Individuals most easily obtained. Internet surveys are a common form of convenience sampling.

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

Systematic Sampling

A

Using a rule to select a sample. For example, selecting every 10th person.

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

Sampling Bias

A

A property of a sampling method that produces statistics that consistently miss-estimate the parameter. Occurs when using nonrandom samples or having under coverage.

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

T/F Bias is a property of the sampling method, not the data itself.

A

True

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

What are the most common causes of bias

A

1) Nonrandom sampling. 2) Undercoverage. 3) Nonresponse bias. 4) Response bias

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

What are two forms of nonrandom sampling?

A

1) Convenience samples. 2) Voluntary samples.

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

Under coverage

A

Certain demographics of the population are systematically excluded from being in the sample.

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

Nonresponse bias

A

Sample subjects cannot be reached or refuse to participate.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

Response bias

A

Occurs when the subjects gives an incorrect response or when the questions are asked in confusing or misleading ways.

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

Experimental unit

A

is a person or object upon which a treatment is applied

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

Treatment

A

A condition applied to the subject

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

Explanatory variable

A

Explains or influences changes in our response variable.

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

Response variable

A

Is the response of interest when measured after treatments are applied.

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

What is the goals of an experiment?

A

Determine the effect of the explanatory variable has on the response variable.

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

Placebo

A

A “dummy treatment”

26
Q

Placebo Effect

A

A psychological a phenomenon in which just taking medication improves the patient health even if that medication is inert

27
Q

Double blind

A

Neither the researchers or patients know which patients is getting the real medication.

28
Q

Single Blind

A

The experimenter knows which patient is getting the real medication.

29
Q

Random assignment

A

When treatments are randomly assigned to subjects.

30
Q

What is the goal of random assignment

A

The goal is to even out the effect of lurking or confounding variables.

31
Q

Completely randomized designed

A

The experimental units are randomly assigned to the treatments without concern with anything else. Often used to study conditions which are chronic that do not have a permanent cure.

32
Q

Matched-pairs design

A

The experimental units are related (twins, husband and wife, pre-test vs post-test scores) or matched before the experiment takes place.

33
Q

What is an example of matched-pairs design?

A

Before and after analysis.

34
Q

What is the goal of random sampling?

A

Produce groups that are as similar as possible with all respects except for the explanatory variable.

35
Q

Lurking Variable

A

A variable which is not observed in the study that influences the association between the response and explanatory variables due to its own association with each of those variables.

36
Q

Why can we use an experiment to prove cause and affect, but not observational studies.?

A

In experiments, random assignment can be applied to control for lurking variables which are not controlled in observational studies.

37
Q

What are the ethical reasons behind the use of experiments and observational studies in science?

A

It is immoral and difficult to intentionally impose behaviors on people over long periods of time. Therefore, short term experiments are preferable to establish causality. But if people willing participate in certain behaviors then long term observational studies can be used.

38
Q

Anecdotal Evidence

A

Evidence which is gathered from personal stories. Impossible to tell if there are actually representative of what happens to an entire population.

39
Q

Sample Survey

A

Selects a sample of subjects from a population and collects data from them.

40
Q

Sampling frame

A

The list of subjects in the population from which a sample is taken.

41
Q

Random Number Table

A

Generates a series of random numbers used to select subject.

42
Q

What are three ways to contact subjects?

A

1) Personal interview
2) Telephone Interview
3) Self-administered questionnaire.

43
Q

Margin of error

A

The margin of the sample percentage varies from the population percentage.

44
Q

T/F All that matters for accurate sampling is sample size

A

False. We are better off with a small random sample than a much larger volunteer sample.

45
Q

Control comparison group

A

The group which is given the placebo to compare to the group which receives the treatment.

46
Q

T/F A Control group is always necessary to conduct a study

A

False, you can compare the treatment group to a group receiving an existing treatment which has been shown to be more effective than a placebo.

47
Q

Margin of error rough calculation

A

1/Sqr(n) times 100%

48
Q

Replication

A

1) Assigning multiple experimental units to each treatment. 2) Repeating similar experiments.

49
Q

Statistically significant

A

When the difference between the result for the two treatments is so large that it would be rare to see such a difference by ordinary variation.

50
Q

What are the hallmarks of a good sampling design?

A

Effectively ensures that each person in a population has an opportunity to be selected.

51
Q

How can sampling methods be used together to gather accurate results?

A

Cluster or stratified sampling can be used to narrow down which districts to use simple random sampling. Which is often more expensive and labor intensive.

52
Q

Case-control study

A

Is a retrospective observation in which subjects who have a response outcome of interest and subjects who have the other response outcome are compared on an explanatory variable. Useful in observing outcome for explanatory variable.

53
Q

Prospective studies

A

Follows its subjects into the future. Also called cohort studies.

54
Q

Sample Survey

A

Takes a cross section of a population at a current times. Also called cross-sectional studies.

55
Q

Factor

A

A categorical explanatory variable having as categories the experimental conditions.

56
Q

Why is using multiple factors in a study often more useful that studying only one factor?

A

You can determine if using two treatments together is more effective than using either treatment on their own.

57
Q

Cross Over Design

A

A matched pair design in which subjects cross over during experiment treatment to using another treatment. Used to minimize the effect of lurking variables. Useful in agricultural studies.

58
Q

Block

A

A set of matched experimental units. A low dose, high does, or placebo.

59
Q

Randomized B lack

A

A block design with random assignment of treatments.

60
Q

Self Selection Bias

A

Individuals select themselves in a group. Arises when survey participants decide for themselves whether or not they want to participate.

Statistics 2000 (9 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions