Week IX - Interpreting Statistics for the Real World Flashcards

(80 cards)

1
Q

what is the purpose of descriptive statistics?

A

Summarize and describe data

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

what tools does descriptive statistics typically rely on?

A
  • mean
  • median
  • SD
  • graphs
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

define frequency distribution

A

The number of times a data point occurs (categorical and continuous variables)

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

define central tendency

A

The central value of a variable (continuous variables), e.g., mean, median

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

define mean

A

Sum of all values, divided by the number of participants.

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

define median

A

Point in the distribution that divides the scores in half.

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

define mode

A

Number that occurs most frequently in a distribution

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

define variability

A

How far away the observations are spread from the variable’s center (continuous variables), e.g., range, standard deviation

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

define heterogenous

A

refers to more variability in data

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

define homogenous

A

refers to less variability in data

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

define range

A

The highest minus the lowest score in a distribution.

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

define standard deviation

A

summarizes the average amount of deviation of values from the mean

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

outline the 68-95-99 rule

A
  • 68% of the data points fall within one SD (mean ± SD, or 𝜇 ± 𝜎)
  • 95% of the data points fall within two SD (mean ± 2SD, or 𝜇 ± 2𝜎)
  • 99.7% of the data points fall within three SD (mean ± 3SD, or 𝜇 ± 3𝜎)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

bivariate descriptive statistics describes relationships between which variables?

A
  • cross tabulations
  • correlations
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

define cross tabulations

A

a statistical method used to analyze the relationship between two or more categorical variables by grouping data into rows and columns

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

what correlation coefficients are commonly used?

A
  • Pearson’s ‘r’
  • Spearman’s ‘rho’
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

define positive correlation

A

High values on one variable are associated with high values on the other

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

r ranges from what with positive correlation?

A

r = 0 to +1

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

define negative correlation

A

High values on one variable are associated with low values on the other

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

r ranges from what with negative correlation?

A

r = -1 to 0

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

define no correlation

A

No relationship between the variables

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

r ranges from what with no correlation?

A

0

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

what is the purpose of inferential statistics?

A

Make conclusions beyond your sample

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

what tools does inferential statistics often rely on?

A
  • Hypothesis testing
  • Confidence intervals
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
what are the steps of hypothesis testing?
1. state the hypothesis 2. set signifance level 3. calculate test statistic 4. obtain p-value 5. make decision 6. interpret results
26
what does the null hypothesis imply?
no effect/no relationship
27
what does the alternative hypothesis imply?
there is an effect/relationship
28
define test statistics
a standardized value calculated from your sample data that is used to test a hypothesis (e.g., t, F, χ²)
29
define p-value
Probability of observing results if H₀ is true
30
in what instance do we reject null hypothesis?
if p value is ≤ α (Significance level)
31
in what instance do we fail to reject null hypothesis?
if p value > α (Significance level)
32
define type I error
false positive - rejecting a null hypothesis that is, in fact, true
33
define type II error
false negative - accepting a null hypothesis that is, in fact, false.
34
define level of significance
the predefined probability of making a Type I error
35
define confidence interval
a range of values that likely contains the true population value
36
what factors influence CI?
* Sample size (larger → narrower CI) * Variability (less variability → narrower CI)
37
a CI with a mean difference that does not include 0 implies what?
statistically significant
38
a CI with a mean difference that includes 0 implies what?
not statistically significant
39
a CI with a ratio that does not include 1 implies what?
statistically significant
40
a CI with a ratio that does include 1 implies what?
not statistically significant
41
what is a t-test used for?
to test the difference between two group means
42
define independant t test
t test that compares two different groups
43
define dependant (paired) t test
t test that compares the same group twice or compare two related groups
44
what is an ANOVA used for?
to test mean group differences of three or more separate, unrelated groups at a single point in time
45
what is a chi squared test used for?
to analyze the association of two categorical variables
46
what does the Pearson correlation test?
linear relationships between two continuous variables
47
what assumptions does the pearson correlation rely on?
- Linear relationship - Normally distributed data
48
what does the spearman correlation test?
ranked relationships between two ordinal or non-normal variables
49
what is multivariate statistical analysis used for?
analysis of three or more variables at the same time.
50
when is a multiple linear regression used?
when several independent variables are included to predict a continuous outcome
51
what is an ANCOVA?
Combination of ANOVA and multiple regression.
52
when is an ANCOVA used?
to examine the influence of an categorical independent variable on a continuous dependent variable while removing the effect of covariates or “confounding variables”
53
when is logistic regression used?
when outcome is categorical
54
an odd ratio of >1 in logistic regression means?
higher odds of outcome
55
an odd ratio of <1 in logistic regression means?
lower odds of outcome
56
an odd ratio of =1 in logistic regression means?
no association
57
what are the two types of measurement?
- categorical - continous
58
what are the two types of categorial measurements?
- nominal - ordinal
59
define nominal
Using numbers to categorize characteristics or attributes. | E.g., marital status: Married =1, Single=2
60
define ordinal
Ranks people on an attribute | eg performing ADL: 1 = dependent, 2 = needs assistance, 3 = independent
61
what are the two types of continous measurements?
- interval - ratio
62
define interval
Ranks people on an attribute and the differences between levels are known | E.g., temperature: the difference between 0°C and 5°C = 10°C and 15°C
63
define ratio
Have a true and meaningful zero and provide information about the absolute size of the attribute | e.g. height, weight
64
what is the lowest level of measurement?
nominal
65
what is the highest level of measurement?
ratio
66
define skewed distribution
"peak" is off-centered.
67
population mean is signified by what symbol
μ (mu)
68
population SD is signified by what symbol
σ (sigma)
69
sample mean is signified by what symbol
M or x̄ (x-bar)
70
sample SD is signified by what symbol
s
71
what are the 6 considerations of interpreting study results?
1. Credibility and accuracy of results (unbiased estimation) 1. Precision of the estimate of effects 1. Magnitude of effects and importance of results 1. Meaning of the results (especially about causality) 1. Generalizability of results 1. Implications of the results for nursing theory, practice development or further research
72
define inference
drawing conclusions about the truth in the real world based on limited information, using logical reasoning.
73
what 4 types of validity contribute to the credibility of study results?
* Statistical conclusion validity. * Internal validity. * External validity. * Construct validity.
74
what factors contribute to corroboration of results?
- replication - consistency across studies - triangulation
75
what are other aspects of interpretation?
- Precision of the results * Magnitude of effects and importance * Clinical Significance * Meaning of the results * Generalizability * Implications of results
76
what measure communicates the precision of study results?
CI
77
define clinical significance
the practical importance of research results in terms of whether they have genuine, palpable effects on the daily lives of patients or on the health care decisions made on their behalf
78
what statistic measures are used to determine clinical significance?
- effect size indexes - Confidence intervals - Number need to treat (NNT)
79
define NNT
how many patients need to receive a treatment for 1 additional patient to benefit
80
define minimal important change (MIC)
a benchmark for interpreting change scores that represents the smallest change that is important or meaningful to patients or clinicians.