Revision Flashcards
1
Q
What is the independent variable?
A
A variable manipulated by a researcher
2
Q
What is a dependent variable?
A
A variable that measures the effect that manipulating another variable has on
3
Q
What is variance?
A
An estimate of the variability (spread) of a set of data
4
Q
What is a confounding variable?
A
A variable that affects the outcome being measured as well as, or instead of the independent variable
5
Q
How do you calculate degrees of freedom for one sample?
A
DF = n - 1
6
Q
How do you calculate degrees of freedom for two samples?
A
DF = n1 + n2 where n is sample size
7
Q
What is meant by degrees of freedom?
A
Degrees of freedom are the maximum number of logically independent values, which are values that have the freedom to vary, in the data sample
8
Q
3 qualities of a mean is…
A
- the sum of all scores divided by the number of scores
- the value from which the scores deviate least
- a hypothetical value that doesn’t have to be a value in the data set
9
Q
What does a z-score indicate?
A
A z-score indicates the number of standard deviations a score is from the mean
10
Q
What is partial eta squared?
A
A measure of effect size
11
Q
4 Assumptions for normally distributed data
A
- the distribution is symmetrical about the mean
- the values for the mean, mode and median are the same
- there are scores both above and below 2 standard deviations
- approximately 68% of scores fall within +/- 1 standard deviation
12
Q
What is a positive skew?
A
A frequency distribution in which low scores are most frequent
13
Q
What is a negative skew?
A
A frequency distribution in which high scores are the most frequent
14
Q
What is platykurtic distribution?
A
A frequency distribution in which there are too many scores at the extremes of the distribution
15
Q
What is standard error a measure of?
A
The variability of sample estimates of a parameter
16
Q
What is the relationship between standard error and sample size?
A
Standard error decreases as the sample size increases
17
Q
What does 95% confidence interval of the mean suggest?
A
95 out of 100 confidence intervals will contain the population mean
18
Q
What is p?
A
The probability of observing a test statistic at least as big as the one we have if there were no effect in the population
19
Q
What is a type I error?
A
Occurs when we conclude there is an effect in the population when there is not
20
Q
What is a type II error?
A
Occurs when we conclude that there is not an effect in the population when there is
21
Q
Assumptions of parametric tests
A
Normality
Homogeneity
Linearity
Independence
Interval or ratio data
Random sampling
No extreme scores
22
Q
What does the bonferroni correction do?
A
Corrects a family wise error
23
Q
How many variables are there in a one-way repeated measures?
A
Only one independent variable and only one dependent variable
24
Q
How many dependent variables are needed for an ANOVA to be conducted?
A
There must only be one dependent variable at interval level or higher
25
How many levels in an independent variable must there be for an ANOVA to be used?
There must be 3 or more levels in one independent variable
26
What do unplanned comparisons test?
They test every possibility that is, compare each condition to each other
27
What does mauchly’s test indicate in a repeated measures ANOVA?
Indicates whether there is a significant difference between the variances of the conditions
28
What do tests of significance like ANOVA look at?
The probability that the samples are from the same population
29
What does a non-significant levene test mean?
The assumption of homogeneity of variance has not been violated
30
What does a non-significant levene test mean?
The assumption of homogeneity of variance has not been violated
31
When is a test significant with an alpha level of .05?
If the p value is less than .05
32
What post hoc would you run for a Kruskall-Wallis test with significant results?
Mann Whitney
33
What post hoc would you run for a significant Friedman test?
Wilcoxon
34
How do you know how many post hoc pairwise comparisons to make?
Use the formula n(n-1)/2 where n is the number of groups
35
How to calculate a new alpha level
Divide .05 by number of pairwise comparisons
36
What is the effect size for a wilcoxon test?
The z statistic divided by the square root of the number of observations
37
What is the non-parametric alternative to the one-way between-subjects ANOVA?
Kruskal Wallis
38
What is the kruskal wallis test used for?
To compare more than two independent groups
39
What is the non-parametric alternative for a one-way repeated-measures ANOVA?
Friedman
40
What is the test statistic based on for kruskal Wallis?
The ranks of the groups
41
What is the test statistic based on for friedmans test?
The sum of ranks
42
When do you use post hoc tests?
When you did not generate specific hypotheses before the experiment
43
When the between groups variance is a lot larger than the within-groups variance, the F value is ____ and the likelihood of such a result occurring because sampling error is _____
Large; low
44
What is the main effect?
The overall effect of an independent variable on a dependent variable
45
What does a significant value for Mauchlys test mean?
The assumption of sphericity has been violated
46
What should follow a violated assumption of sphericity?
The greenhouse-geisser or huynh-feldt correction
47
What is the primary use of a two way repeated measures ANOVA?
To assess the impact of two independent variables on a single dependent variable with repeated measures
48
What does the interaction effect test?
Whether the effect of one independent variable on the dependent variable depends on the level of the other independent variable
49
What is a key assumption of a two way repeated measures ANOVA?
There must be sphericity for both independent variables
50
What follows a significant interaction effect found in a two way ANOVA?
Post hoc tests
51
What is a significant main effect for one independent variable in a two way ANOVA?
Indicates that the effect of one independent variable on the dependent variable differs across the levels of the other independent variable
52
What is the purpose of the bonferroni correction?
To adjust the significance threshold to control the overall probability of making type I errors when performing multiple tests
53
Planned comparisons vs post hoc
Planned comparisons focus on the specific hypothesis set before the study, while post hoc tests explore all possible comparisons after the data has been analysed
54
When is it appropriate to use post hoc tests?
When you have no specific hypotheses in mind and want to explore all possible pairwise comparisons
55
What is statistical power?
The probability of correctly rejecting the null hypothesis
56
What is the relationship between effect size and statistical power?
As effect size increases, statistical power increases
57
What is a core principle of open science?
Sharing data, materials and methods publicly
58
What platform is commonly used for open science to share research data and materials?
Open science framework
59
What does replication crisis refer to?
The inability to reproduce the results of published studies
60
What does reproducibility mean?
To repeat a study using the same data and methods
61
A reason for replication crisis?
Publication bias towards positive findings
62
What can improve reproducibility of research in psychology?
Sharing data and analysis scripts openly, using the open science framework
63
What research practice permits testing of cause and effect relationship?
Experimental research
64
What is the main purpose of random assignment?
To eliminate the influence of confounding variables
65
An example of a continuous variable
Statistics test score
66
Relationship between effect size and statistical power
As effect size increases, statistical power increases
67
What represents a measure of central tendency?
Median
68
In a between subjects design participants are assigned to…
Multiple groups
69
I’m a two way ANOVA the interactions refers to what?
The combined effect of both independent variables on the dependent variable differs across
70
What does the confidence interval provide information about?
The range of values within the true population parameter
71
What is the interval scale?
The interval scale has equal intervals between values but no absolute zero
72
What is a disadvantage of the within-subjects design?
Order effects
73
What is standard deviation?
A measure of how spread out the scores are in a data set
74
What does ANOVA compare?
The means of three of more groups
75
What does the F-ratio in ANOVA test?
The ratio of between group variance to within-group variance
76
What is the non-parametric equivalent of a one-way between groups ANOVA?
Wilcoxon test
77
Post hoc tests determine what?
Which specific group means differ from each other
78
What does the assumption of homogeneity of variance mean?
The variance within each group is approximately equal
79
How many independent variables are examined in a two way anova?
2
80
What is statistical power?
The probability of rejecting a false null hypothesis
81
What does not have a direct affect on statistical power?
The hypothesis
82
What is the non-parametric equivalent to a within subjects one way ANOVA?
Friedmans test
83
What is a familywise error?
The probability of making at least one type I error across all in multiple comparisons
84
How do you control familywise errors?
Apply a bonferroni correction
85
What are examples measures of central tendency ?
Mean
Median
Mode
86
If a score in a data set has a Z-score of 0 this means
The score has a value equal to the mean of that data set
87
What is sampling distribution?
A distribution of statistics obtained by selecting all the possible samples of a specific size from a population
88
What is standard error?
The standard deviation for the distribution of sample means
89
What is sampling error?
the discrepancy, or amount of error, between a sample statistic and its corresponding population parameter
90
Of what is p the probability?
P is the probability of observing a test statistic at least as high as as the one we have if there were no effect in the population
91
When can sphericity be assumed?
When the mauchly’s test is non-significant
92
What is a measure of effect size for a between-groups one-way ANOVA?
ETA squared
93
What is the test statistic?
Variance explained by the model / variance not explained by the model = effect / error
94
What does an ANOVA compare?
The amount of variance explained by our explained by our experiment with the variance that is unexplained
95
A frequency distribution in which low scores are most frequent is said to be…
Postively skewed
96
When are non-parametric tests used?
The assumptions of parametric tests have not been met
97
When you generated specific hypotheses about this before the experiment what do you use?
Planned comparisons
98
In a multifactorial ANOVA what is the main effect?
The effect of one of your independent variables on the dependent variable, ignoring the effects of all other independent variables
99
What is an effect size?
A quantitative measure of the magnitude of an effect
100
What is statistical power?
The probability that a test will detect an effect when there is one
101
What is a sample?
A smaller but representative collection of units from a population used to make inferences about that population
102
What is a population?
The collection of units to which we want to generalise a set of findings or a statistical model
103
Why are statistical models used?
To represent what is happening in the real world
104
What is a deviation?
The difference between the mean and an actual data point
105
How can deviations be calculated?
By taking each score and subtracting the mean from it
106
Sum of squared measures is a measure of what?
Variability
107
What does the result of the t-test depend on?
The size of the difference between the means
The variability in the data
108
Limitations of p-values
They are not standardised
different sample sizes will yield different p-values for the same effect magnitude
A large study will detect small effects that could be non-significant in a smaller study
109
What is an effect size?
A standardised measure of the size of an effect meaning it’s comparable across studies
110
Different measures of effect size are…
Cohens d
eta squared
Partial eta squared
111
If there are outliers in the data what can be done?
Transform the data set
Change the outlier itself
112
What is analysis of variance?
Parametric test statistic that allows us to test if 3 or more sample means come from the same population
113
Which assumption check is needed for between designs?
Levene’s test
114
Which assumption test is needed for a within design?
Mauchly’s/ test of sphericity
115
What do ANOVAs compare
The variance between groups with the variance within groups
116
What does it mean when F increases?
The more likely it is that the groups are not from the same population
117
What is levene’s test used for?
To assess the equality of variances
118
What is the Mauchly’s test of sphericity?
A test only relevant to within-design anova. Asks if the data meets the additional assumption that the variances of the differences between the conditions are roughly equal.
119
What does sphericity mean?
Equality of variance of the differences between all combinations of the groups or levels
120
What effect size is used for between groups ANOVA?
Eta squared
121
What effect size is used for within groups ANOVA?
Partial eta squared
122
How can you define degrees of freedom?
As the number of independent pieces of information you make to make that calculation
123
The difference between calculating df1 and df2 is for a two way anova …
Df1 = k (number of levels) - 1
Df2 = n - k
124
How do you calculate df in a one way anova?
Df1 = k (n of levels) - 1
Df2 = (n [number of observations] - 1) - (N [number of participants] - 1) - (k - 1)
125
How do you calculate df in a one way anova?
Df1 = k (n of levels) - 1
Df2 = (n [number of observations] - 1) - (N [number of participants] - 1) - (k - 1)
126
The assumptions for ANOVA are?
DV data on interval or ratio scale
Sampling distribution of means is normal
Homogeneity of variance (levene - between, Mauchly’s within)
127
What would you use after a significant friedmans test?
Wilcoxon with a bonferroni correction
128
What test would you use for a significant kruskal Wallis?
Mann Whitney with a bonferroni correction
129
When do we use non-parametric tests?
DV data is nominal or ordinal
Data are not normally distributed
Unequal variance
130
What are the limitations of null hypothesis significance testing?
Over reliance in psychology on p-values alone for determining importance effects
The p value is not a standardised index; it reflects the size of the sample as well as the size of the effect
A small study can produce a non-significant result with the same effect size as a large study that is significant because of the difference in sample size
131
What is a priori power analysis?
Conducted prior to conducting research and is typically used to determine an appropriate sample size to achieve adequate power to detect an effect
132
What is post hoc power analysis?
Conducted after a study has been conducted and used the obtained sample size and effect size to determine what the power was in the study
