# Research Methods Flashcards

1
Q

Independent Variable

A

The variable whose effect is being studied

2
Q

Dependent Variable

A

The variable expected to change due to variations in the independent variabble

3
Q

What is the difference between a true experiment and a quasai experiment and correlational study.

A

True experiment: Independent var is manipulated, subject is randomly assigned to different groups
Quasi: no random assignment
Correlational study: no manipulation of independent var

4
Q

What is another name for a naturalistic observation?

A

A field study

5
Q

Population is

A

The total number of subjects that fit into a specific characteristics. i.e. people whom live in the US. People over 40 etc.

6
Q

Sample

A

Is a sampling of people that is representative of the larger population.

7
Q

The best way for researchers in getting an accurate sample?

A

A random sample.

8
Q

What is another type of random sample?

A

Stratified random sample

9
Q

What does a random stratified sample

A

It is a random sample that includes specific groups in proportion with the larger population. An attempt to get a more accurate measure.

10
Q

Describe Between subject design

A

subject is exposed to only one level of independent variable. The subjects are assigned ranomly to groups and subjects are not given the same level of IV as another group.

11
Q

Can groups differ on chance even with random selection?

A

Yes

12
Q

What is matched subject design

A

Where the experimenter matches the two groups. So that people with similar abilities or characteristics are matched together and then studied together. For example if there is variability of intelligence between groups and intelligence is the dependent

13
Q

What is within subjects design research

A

The subjects own performance is the basis of comparison. The crucial thing here is that the subject is exposed to more than one condition, allowing the researcher to separte the effects of individual differences in intelligence from the effects of the IV. A-B, A-B-A etc

14
Q

What are the most obvious problems in research design

A

Experimenter bias
Demand Characteristics
Placebo Effect
Hawthorne Effect

15
Q

Describe the placebo effect:

A

When people show positive effects to sham treatment, intert substances, or no active treatment.

16
Q

What is the Hawthorne effect

A

The effect that being observed has on behavior

17
Q

Describe demand characteristics

A

Cues in research situations that suggest to the subject what is expected.

18
Q

Describe experimenter bias

A

How the experimenter biases the study in all aspects, methods, statistics, design and reporting.

19
Q

What are the two major categories of statistics?

A

Descriptive and inferential

20
Q

What is descriptive statistics concerned with?

A

Is concerned with organizing, describing, quantifying, and summarizing a collection of actual observations.

21
Q

What is inferential statistics concerned with?

A

Inferential statistics researchers generalize beyond actual observations.

22
Q

Frequency distributions

A

A chart that is used as a graphic representation of the frequency of one variable of the data.

23
Q

Measures of central tendency are

A

mean, median and mode

24
Q

mode

A

Is the most frequent value

25
Q

If there are two modes, what is it called?

A

Bimodal

26
Q

A distribution can have 3 or 4 modes

A

then it is polymodal

27
Q

Median is the central number

A

Count the numbers and figure out which one is exactly in the middle. If even average the two middle numbers.

28
Q

Mean

A

Is the average of the data across all subjects. Or in otherwords the numerical 50%

29
Q

What are numbers that don’t fit the central tendency?

A

outliers

30
Q

What is the most sensitive measure to extreme outliers?

A

mean

31
Q

What are measures of variability

A

Range
Standard deviation
variance
Variability or dispersion scores

32
Q

Range

A

Is the smallest number subtracted from the largest

33
Q

Standard deviation

A

The average scatter away from the mean. (square root of the variance)

34
Q

Variance

A

The square root of the STD

35
Q

What is a normal distribution

A

It is a bell shaped curve of the data that follows a typical pattern.

36
Q

With normal distribution how can you tell the percentile of the score the person is in?

A

By using the z-score

37
Q

What is the z-score?

A

The number of STD away from the mean.

38
Q

What is 1 z score account for

A

34% on one side of the distribution, 68% on both sides

39
Q

What does 2 z score account for

A

14% or 13.6% between 1 and 2, aprox 48.5% on one side of the distriubution and aprox 97% on both sides

40
Q

What is above 2 zscore

A

1.5% on one side or 3 % on both sides

41
Q

What is a T-score?

A

It is a standardize score with a STD of 10. Often used for test scoring because of the nice even round numbers.

42
Q

What is a non-normal distribution?

A

When the data does not fit a normal distribution

43
Q

If the mean is less than the median then

A

the data is skewed to the left (lower numbers)

44
Q

If the mean is larger than the median then

A

the data is skewed to the right (higher numbers)

45
Q

Are correlation coefficients descriptive or interferential?

A

descriptive

46
Q

What does a Corelation coefficent measure

A

It allows you to understand to what extent two variables may be related.

47
Q

What is the range of scores of a correlation coefficient?

A

-1 to 1

48
Q

If two variables have a positive correlation then?

A

It can be said that a change in the value of one tends to be associated with a change in the same direction of the value of the other variable.

49
Q

What would be a perfect correlation?

A

Score of 1.0 or -1.0

50
Q

What is no correlation equal to?

A

zero

51
Q

What is the cornerstone technique of factor analysis?

A

Correlation. Factor analysis attempts to account for the interrelationships among various variables b seeing how groups of variables “hang together”

52
Q

What does inferential statistics use?

A

a small batch of actual observations to make conclusions about the entire population. Used to make inferences or generalizations.

53
Q

What is significance test

A

Is a tool researchers use to draw conlusions about populations based upon research conducted on samples.

54
Q

What are researchers trying to show

A

That either the research or the null hypothesis is supported by the research.

55
Q

What is the criterion for significance?

A

5 percent, that means three is less than a 5% chance that the data is due to chance, sometimes referred to as the alpha level.

56
Q

Types of Error in significance testing

A

Type I error and Type II error

57
Q

What is type I error

A

When you reject the null hypothesis (when it is true)

58
Q

What is type II error

A

When you accept the null (when it is false)

59
Q

What is the probability that one will make a type II error

A

It is reffered to bta

60
Q

What are the major types of significance testing?

A

T-test, ANOVA, chi-square test

61
Q

When is a t-test used?

A

When trying to compare two groups.

62
Q

When is an ANOVA used?

A

When trying to compare more than two groups.

63
Q

What is chi square?

A

Tests the equality of two frequencies or proportions. This is for categorical data and not numerical data.

64
Q

Describe ANOVA more clearly.

A

They describe how much groups differ by comparing the between group variance.

65
Q

What factor does an ANOVA use?

A

An F-ratio which is equal to the between-group variance estimate and within-group variance estimate.

66
Q

What else is categorical data called

A

Nominal data

67
Q

What are the two types of factorial analysis?

A

Factorial design: each level of a given independent variable occurs with each level of the other independent variables.
Interaction: when the effects of one independent variable are not consistent for all levels of th other independent variables

68
Q

What is meta analysis?

A

The statistical procedure that can be used to make conclusions on the basis of data from different studies. It reaches more general conclusions.

69
Q

What is reference testing?

A

It is two ways of interpreting data via comparing the criteria of the results to some common factor so that there is a more accurate comparison of results.

70
Q

What is norm-referenced.

A

Assessing an individuals performance in terms of how that individual performs in comparison to others. We compare one test taker to that test’s norms.

71
Q

What is a problem with norm referenced data

A

Is that the population to whom the tests will be administered can, and often does, change.

72
Q

What is domain-referenced data?

A

Is concerned with the question of what the test taker knows about a specific content domain. Performance on such a test is described in terms of what the test taker knows or can do. An example of domain referenced is the driver’s license test.

73
Q

Reliability is?

A

Is the consistency with which a test measures whatever it is that the test measures.

74
Q

What is test-retest reliability

A

The reliability of the measures from test to test in the same person.

75
Q

What is alternate-form reliablility

A

Two tests looking at the same measure are given and the consistency is measured.

76
Q

What is split-half reliablity

A

The comparison of the first part with the second part of the test.

77
Q

Other forms

A

Inter-rater, Intra rater reliability (between people, between the same person.) i.e. the experimenter

78
Q

What is validity?

A

It is the extent to which the test actually measures what it purports to.

79
Q

What does validity depend on?

A

relationship between test, objective sources of information regarding behavior, knowledge or interest

80
Q

What are the major types of validity?

A
```Content
Face
Criterion Concurrent
Predictive
Construct Convergent
Discriminate```
81
Q

What is content validity

A

Does test measure what it is supposed to in the given content area?

82
Q

What is face validity?

A

Does the test on its appearance look like it tests what it supposed to?

83
Q

What is Criterion concurrent validity

A

Does test performance indicate previous learning of the content measured.

84
Q

What is predictive validity

A

Does test performance predict future performance?

85
Q

What is construct convergent validity?

A

Does test performance relate to the interest level in the content matter?

86
Q

What is discriminate validity?

A

Is the test performance not related to the test-taking experience? I.e. does the measure actually look at outside factors or just the exp of the test.

87
Q

Other types of validiity

A

extrinsic (ability to generalize results)

intrinsic (ability to apply the results to the population measured)

88
Q

How is criterion validity assessed?

A

Cross validation, testing on two samples and not just one.

89
Q

What are the two ways construct validity are measured?

A

convergent and disciminant validity

90
Q

What are the two ways criterion validity is measured?

A

concurrent and predictive validity

91
Q

What are the different scales of mesaurement

A

nominal/categorical
ordinal
Interval
Ratio

92
Q

What is an example of nominal data:

A

names i.e. political affiliation

93
Q

What is an example of ordinal data:

A

ranks i.e. orders of finishes in a race

94
Q

What is an example of interval data:

A

equal intervals i.e. temp (can perform add/subract)

95
Q

What is an example of ratio data

A

equal intervals with a true zero point i.e. income (add/subtract/multiply)

96
Q

What are the two types of ability tests

A

Aptitude tests and achievement ttests

97
Q

What is an aptitude test?

A

Used to predict what we can achieve through training?

98
Q

What is an achievement test?

A

Tests used to assess how much one knows (i.e. content and skill)

99
Q

What is an IQ test?

A

An aptitude test

100
Q

How was IQ orginaly calculated?

A

via a ratio of mental age (measured on test) vs chronological age

101
Q

What is deviation IQ

A

It is now how it is measured and indicates how well one performed relative to peers.

102
Q

What is normally on a personality test?

A

Between 100 and 500 statements that a person rates themselves on.

103
Q

Name the major pesonality tests

A

MMPI (Minnesota Multiphasic Personality Inventory)
Empirical criterion-keying approach
California psychological Inventory

104
Q

Projective Tests

A

Stimuli is ambigious, test taker is not limited to the number of possible responses. A test-taker is given the stimuli and asked to interpret what he or she sees.

105
Q

Examples of projective tests

A

Rorschach Inkblot
Thematic Apperception Test
Blacky pictures
Rotter Incomplete sentences blank

106
Q

What is the Barnum effect

A

Which refers to teh tendency of people to accept and approve of the interpretaiton of their personality that you give them. This is a form of pseudovalidation.

107
Q

What is interest testing?

A

Tests an individual’s interestes in different lines of work. Best known as the Strong-Campbell Interest Inventory.

108
Q

What is the RIASEC system

A

a method of dividing interests into realistic, investigative, artisitic, social, enterprising, and conventional.