Brainscape's Knowledge GenomeTM

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


See full index

Multivariate Data Analysis - 175.746 > Week 2 - Statistical Fundamentals > Flashcards

Week 2 - Statistical Fundamentals Flashcards

1
Q

What is falsification?

A

The act of disproving a hypothesis or theory.

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

What is an independent variable?

A

The variable we think is the cause and is manipulated.

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

What is a dependent variable?

A

The variable we think is the effect and is not manipulated.

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

What is a nominal variable?

A

When two things that are equivalent in some sense but there are more than two possibilities.

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

What is an ordinal variable?

A

When categories are ordered - naming the winners in a competition as first, second, third

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

What is a continuous variable?

A

A variable that gives us a score for each person and can take on any value on the measurement scale that we are using. It can be measured to any level of precision.

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

What is an interval variable?

A

Interval data appears on a scale at equal intervals.

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

What is a ratio variable?

A

Takes the interval variable a step further by requiring the interval scale to have a true and meaningful zero point - a lecturer rate as a 4 is twice as helpful as one rated a 2.

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

What is a discrete variable?

A

It can only take on certain values (usually whole numbers).

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

What is measurement error?

A

The discrepancy between the numbers we use to represent the thing we are measuring and the actual value of the thing we’re measuring - the value we would get if we measured it directly

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

What is validity?

A

The ability to which an instrument actually measures what it sets out to measure.

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

What is reliability?

A

Whether an instrument can be interpreted consistently across different situations.

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

What is criterion validity?

A

The ability for an instrument to measure the criterion it claims to measure through your comparison to objectvie criteria - You asses this by relating scores on your measure to real-wrld problems.

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

What is concurrent validity?

A

The ability for the new instrument to correlate with an exsisting criteria.

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

What is predictive validity?

A

The ability for a new instrument to predict observations at a later point in time.

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

What is content validity?

A

The degree to which individual items represent the construct being measured, and cover the full range of the construct.

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

What is test-retest reliability?

A

When you test the same group of people twice: a reliable instrument will produce similar scores at both points in time.

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

What is correlation research?

A

When we obseve what naturally goes on in the world without direcetly interferring with it.

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

What is experimental research?

A

When we manipulate one variable to see its effect on another.

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

What is cross-sectional research?

A

When we take a snapshot of many variables at a single point in time.

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

What is longitudinal research?

A

When we measure variables at differnt time points.

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

What are confounding variables?

A

External factors that effect both the predictor and outcome variable.

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

What is a between-subjects design?

A

Different groups participate in different experimental conditions.

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

What is a within-subjects design?

A

The independent variable is manipulated using the same group.

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

What is unsystematic variation?

A

Small differences in data that is caused by unknown factors.

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

What is systematic variation?

A

Differenes in data created by a specific experimental manipulation.

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

What is randomisation?

A

It eliminates most other sources of systematic variation by selecting a random sample of participants.

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

What are practice effects?

A

The tendency for participants to perform differently in the second experimental condition because of familiarity with the experimental situation.

29
Q

What are boredom effects?

A

The tendency for participants to perform differently in the second experimental condition because they are tired or bored from having completed the first condition.

30
Q

What is counterbalancing?

A

A technique used to reduce systematic variation (such as practice and boredom effects) which work by chaning the order in which conditions are participated in.

31
Q

What is a normal distribution?

A

A distribution of data which results in a bell-shaped curve. It implies that the majority of scores lie around the centre of the distribution.

32
Q

What is a skew? Positive and negative.

A

A lack of symmetry on a distribution scale.
Positive - frequent scores clustered at low end
Negative - frequent scores clustered at higher end

33
Q

What is a kurtosis?

A

A lack of ‘pointyness’ or the degree to which scores cluster at the ends of the distribution (tails).

34
Q

What is leptokurtic?

A

A positive kurtosis - a distribution which is thin in the tails

35
Q

What is a platykurtic?

A

A negative kurtosis - a distribution which is wide in the tails

36
Q

What is central tendency?

A

Where the centre of a frequency lies - mode, median, and mean.

37
Q

What is a bimodal distribution?

A

The mode is the value that occurs most frequently. A bimodal has two scores which appear often.

38
Q

What is a multimodal distribution?

A

It is where there are several numbers that occur frequently.

39
Q

What is the interquartile range?

A

It is the distance between the top and bottom 25% of scores.

40
Q

What are the lower and upper quartiles?

A

They are the median of the lower and upper half of the data.

41
Q

What is the deviance?

A

The average distance between a value and the mean.

42
Q

What is Σ?

A

Sigma - means add up all of what comes after

43
Q

What is X?

A

Refers to set of population parameters?

44
Q

What is x?

A

Refers to a set of sample parameters?

45
Q

What is the sum of squared errors?

A

The deviance of each score is squared.

46
Q

What is the variance?

A

The average dispersion of data from the mean (still squared).

47
Q

What is the standard deviation?

A

The square root of the variance which is used to get an accurate representation of how much the values differ from the mean.

48
Q

What is the difference from a variable and a parameter?

A

Variables are measured constructs that vary across entities in the sample. Parameters are estimated from the data and are constants believed to represent some fundamental truth about the relations between variable in the model.

49
Q

What are degrees of freedom?

A

The degrees of freedom is the number of scores used to compute the total adjusted for the fact we’re trying to estimate the population value. One of the values measured must be true so we use N-1.

50
Q

What is the fit of a model?

A

The degree to which a statistical model represents the data collected.

51
Q

What are linear models?

A

Models which are based on s straight line.

52
Q

What are parameters?

A

Parameters are estimated values from the data and are usually constants believed to represent some fundamental truth about the relations between variables in the model.

53
Q

What is sampling variation?

A

Samples will vary because they contain different members of the population.

54
Q

What is sampling distribution?

A

The frequency distribution of sample means (or whatever parameter you’re trying to estimate).

55
Q

What are confidence intervals?

A

Boundaries, based on sample means, within which we believe the population will fall.

56
Q

What is an alternative hypothesis?

A

The hypothesis that an effect will be present. Also called the experimental hypothesis.

57
Q

What is the null hypothesis?

A

It states the oppostie of the alternative hypothesis, usually that an effect is absent.

58
Q

What is a test statistic?

A

The ratio of systematic to unsystematic variance or effect to an error. It compares how good a model or hypothesis is against how bad it is.

59
Q

What is a one-tailed test?

A

It tests a directional hypothesis.

60
Q

What is a two-tailed test?

A

It tests a non-directional hypothesis.

61
Q

What is type I error?

A

When we believe that there is a genuine effect in our population, when in fact there isn’t.

62
Q

What is type II error?

A

When we believe that there is no effect in the population when, in reality, there is.

63
Q

What is the b-level? (beta level)

A

The b-level is .2 (or 20%) and suggests that if we took 100 samples of data from a population in which an effect exists, we would fail to detect that effect in 20 of those samples (so we’d miss 1 in 5 genuine effects).

64
Q

What is experimentwise error rate?

A

The probability of making a Type I error in an experiment involving one or more statistical comparisons when the null hypothesis is true in each case.

65
Q

What is the Bonferroni correction?

A

A correction applied to the a-level to control the overall type I error rate when multiple significance tests are carried out. Each test conducted should use a criterion of significance of the a-level (normally 0.5) divided by the number of tests conducted.

66
Q

What is the a-level?

A

The probability of making a Type I error.

67
Q

What is a test’s statistical power?

A

The ability of a test to detect and effect of a particular size (a value of 0.8 is a good level to aim for).

68
Q

What is Cohen’s d?

A

An effect size that expressed the difference between two means in standard deviation units.

69
Q

What is effect size?

A

An objective and usually standardized measure of the magnitude of an observed effect. Measures include Cohen’s d, Glass’s g, and Person’s r.

Multivariate Data Analysis - 175.746 (8 decks)

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