Brainscape's Knowledge GenomeTM

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


See full index

BCPS > Statistics > Flashcards

Statistics Flashcards

1
Q

Nominal vs Ordinal data

A

Nominal - classified into groups in an unordered manner and with no indication of relative severity (M/F, morality, disease state). Binary data can fall in here (only 2 options)

Ordinal - ranked in a specific order but with no consistent level of magnitude of difference between ranks (NYHA functional class: 1,2,3,4)

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

Continuous variables? Also what’s the difference between interval and ratio scaled?

A

counting variables.

Interval scaled: data ranked in a specific order with a consistent change in magnitude between units; the zero point is arbitrary (degrees farenheit)

Ratio scaled” like “interval” but with an absolute zero (degrees Kelvin, pulse, BP, time, distance).

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

Descriptive vs inferential statistics?

A

Descriptive - Used to summarize and describe data that are collected or generated in research studies, this is done both visually and numerically.

Inferential - Conclusions or generalizations made about a population (large group) from the study of a sample of that population

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

What are 4 commonly used types of descriptive statistics?

A

Frequency distribution, histogram, scatter plot, box plot

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

How do you measure central tendency?

A

Mean - used only for continuous and normally distributed data, very sensitive to outliers (tends toward the tail), most commonly used/well-understood. Should be given with SD.

Median - Midpoint of the values when placed in order from highest to lowest, half above and below. Used for ordinal or continuous data (especially for skewed populations). Insensitive to outliers. IQR. NOT SD.

Mode - most common value in a distribution, used for nominal, ordinal, or continuous data. Data may have > one mode (bimodal, trimodal), describes meaningful distributions with a large range of values.

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

What is standard deviation?

A

Measure of the variability about the mean, applied to continuous data that are normally distributed or transformed to be.

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

What is the empirical rule?

A

68% within +/- 1 SD, 95% within +/- 2 SD, 99% within +/- 3 SD

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

What is the coefficient of variation (CV) and variance?

A

CV relates mean to the SD (SD/mean X 100%), Variance = SD^2

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

What is the range?

A

Difference between the smallest and largest.

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

What are percentiles?

A

Point in a distribution which a value is larger than some % of the other values. IQR- percentile that describes the middle 50%, encompasses the 25th-75th percentile.

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

What measures of central tendency should be presented with continuous, interval scaled data?

A

The mean

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

What measures of central tendency should be presented with ordinal data?

A

Median

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

What is gaussian distribution?

A

Normal distribution, most common model for population distributions, bell shaped or symmetric.

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

How do we assess gaussian distribution?

A

Median - mean - most practical and easiest to use

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

What is the standard error of the mean (SEM)?

A

Estimate of the certainty that the calculated sample mean represents the true mean. Not variability in the sample. SD/sqrt(n).

Application- 95% confidence interval is around mean +/- 2 SEM

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

What do parametric tests assume?

A

Data being investigated have an underlying normal distribution, data are continuous, data being investigated have variances that are about equal.

17
Q

What is a one-sample test?

A

Compares the mean of the study sample with the population mean (known).

18
Q

What is a two sample independent samples or unpaired test?

A

Compares the means of two independent samples

19
Q

What is a paired test?

A

Compares the mean difference of paired or matched samples (related samples test). Often seen in a crossover study design.

20
Q

What 4 key questions should be asked about every statistical test?

A

1: What type of data is it? (nominal, ordinal, or continuous)
2: Is the data parametric (normally distributed) or is there a skew?
3: How many study groups are there?
4: What is the study design? (parallel vs crossover, etc.)

21
Q

What are the tests for continuous data with 2 independent samples?

A

Student’s t test and Mann-Whitney U

22
Q

How does the t test work?

A

T test takes 2 averages (means) and compares them.

Independent samples is 2 unrelated groups and compares them. Paired is uses the same group for both measurements (look for a before and after measurement).

23
Q

What is the test for continuous data and 3 or more independent samples?

A

1-way ANOVA

24
Q

What is the test for continuous data and related or paired samples?

A

Paired T-test

25
Q

What to know about the one-way ANOVA?

A

Like a student’s t test but with more groups

26
Q

What to know about the two-way ANOVA?

A

Same as the 1-way ANOVA but if you add an additional group into the independent variable

27
Q

What is a repeated measures ANOVA?

A

like a paired t-test but can take multiple measurements (i.e. at 4,6,8,12 weeks).

28
Q

What to know about Chi-square?

A

Used when comparing categorical variables

29
Q

What tests are used for ordinal data and 2 independent samples?

A

Mann-Whitney U (analogous to the student’s t-test but can be used with ordinal and continuous data),

Wilcoxon Rank Sum

30
Q

What tests are used for ordinal data and related or paired samples?

A

1: Sign test
2: Wilcoxon signed rank

31
Q

What test is used for ordinal data and 3 or more independent samples?

A

Kruskal-Wallis 1 way ANOVA

32
Q

What test is used for ordinal data and 3 or more related samples?

A

Freidman 2-way ANOVA

33
Q

What tests are used for ordinal data and measures of correlation?

A

1: Spearman
2: Kendal Rank
3: Kendal Coe

34
Q

What tests are used for nominal data and 2 independent samples?

A

1: Chi-Square
2: Fisher’s Exact

35
Q

What tests are used for nominal data and related or paired samples?

A

McNemar (chi square test with related samples)

36
Q

What tests are used for nominal data and 3 or more independent samples?

A

Chi-Square for k independent samples

37
Q

What tests are used for nominal data and 3 or more related samples?

A

Cochran q

38
Q

What test is used for nominal data and measures of correlation?

A

Contingency Coefficient

39
Q

What’s the pneumonic for data?

A

NOIR

BCPS (21 decks)

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