Segars: Introduction to Biostatisitics Flashcards

1
Q

What is a Null hypothesis (H0)

A

-there will be NO change!!!!!

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

What is aternative hypthesis (H1)?

A

-there WILL be a change between groups

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

What does it mean when something is normally distributed?

A

-when mean, median, and mode are all equa

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

% found withing 1 SD of the mean on a normally distributed curve?

A

-68%

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

2 SD’s

A

-95%

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

3SD’s

A

-99.7%

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

What does a + skew curve look like?

A
  • tail pointing to right
  • Mean>median
  • mode will always be that peak
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

negative skew

A
  • tail pointing to left

- Mean< median

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

What is skewness?

A

-a measure of the asymmetry of a distribution

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

What are the 3 kinds of statistical test?

A
  • Nominal
  • ordinal
  • Interval
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Nominal

A
  • no magntitude
  • no consistency of scale
  • named… only 2 things
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Ordinal

A
  • yes magnitude
  • no consistency of scale
  • ex: pain scale
  • +3 categories
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Interval/ratio

A
  • yes magnitude
  • yes consistency of scale
  • ex: age
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What are the required assumptions of interval data?

A
  • normally distributed
  • equal variances :use levene’s test
  • Randomly-derived and independent
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

1 of the 4 key questions to selevting the correct statistical test?

A
  • What DATA LEVEL is being recorded

- is it Nominal, ordinal, or interval???

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

2

A
  • what type of comparison/assessment is desired?
  • Correlation
  • regression
  • survival comparison
  • group comparison
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

What are the values for correlation?

A

-+1 and -1, upwards slope and downwards slope (45 degrees)

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

If we are looking for a correlation test, what are the possibilities?

A
  • Nominal= contingency coefficient
  • Ordinal= Spearman correlation
  • Interval= pearson correlation
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

What do we have to know about pearson correlation?

A

-just assesses for linear correlation, there may still be non linear correlations present if pearson correlation non-signif.

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

After we decide if it is nominal, ordinal, or interval, what do we do next?

A
  • look for 5 things
  • 2 groups
  • > or = 3 groups
  • Proportion of events (survival)
  • Measure of correlation
  • Prediction or association
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

What are survival tests commonly represented by?

A

-a kaplan meier curve

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

What will all survival tests have on the bottom?

A

-time on x axis

23
Q

If it is survival, what are the possibiliities?

A
  • Nominal= log rank test
  • Ordinal= cox-proportional hazards test
  • interval= Kaplan Meier test
24
Q

what is a regresssion?

A
  • provides a measure of the relationship between variables by allowing the prediction about the dependent, or outcome, variable knowing the value/category of independent variables (IV’s)
  • also able to calculate OR for a measure of association and control for confounding IVs
25
Q

If it is outcome prediction/association (or regression), what are the possibilites?

A
  • Nominal= logisitic regression
  • ordinal= multinomial logistic regression
  • Interval= linear regression
26
Q

What are the last 2 questions we have to ask before we pick which statistical test we want to do?

A
  • How many groups

- is the data independent or related

27
Q

Nominal 2 groupd of indy data

A

-pearson’s chi square test

28
Q

Nominal >=3 groups indy

A

-chi square test of independence

29
Q

> = 2 groups with expected cell count of >5?

A
  • fisher’s exact test

- aka, not a lot of people

30
Q

What are the key words for “paired” or “related” data?

A
  • pre vs post
  • before and after
  • baseline vs end
31
Q

Ordinal and 2 groups of indy data?

A

-Mann-whitney test

32
Q

> = 3 groups of indy data

A

-Kruskal-Wallis test

33
Q

What does the Mann whitney and kruskal wallis tests compare?

A

-the median values between the groups

34
Q

2 groups of pair/related data

A

-wilcoxon signed rank test

35
Q

> =3 groups of paired/related data

A
  • Friedman test

- both compar median values again

36
Q

post hoc tests for 3 or more gorup comparisons

A
  • student newman keul test
  • dunnett test
  • dunn test: good for when groups are NOT of equal size, we need that for the other 2….
37
Q

Interval 2 grops of indy data

A

-student t test

38
Q

Interval >=3 groups of indy data

A
  • Analysis of variance (ANOVA)
  • both tests compare the MEANS
  • Multiple analysis of variance (MANOVA)
39
Q

Interval >= 3 groups of independent data w/ confounders?

A
  • analysis of Co variance (ANCOVA)

- MANCOVA

40
Q

Interval, 2 groups, paired/related

A

-Paired t-test

41
Q

> =3 groups, interval, related

A
  • repeated measures ANOVA

- Repeated measured MANOVA

42
Q

Interval, >= 3 groups, paired, confounders

A
  • repeated measures ANCOVA

- Repeated measures MANVOVA

43
Q

Interval data post hoc tests for 3 or more group comparisons

A
  • student-newman-keul test
  • Dunnett test
  • Tukey or Scheffe tests
  • Bonferroni corretion
  • Dunn test: rememebr, NOT EQUAL SIZE FOR THIS ONE, BUT YES EQUAL FOR THE OTHER 2
44
Q

What are the 4 questions we have to ask when selecting the correct statistical test?

A
  • What data level is being recorded?
  • What type of comparison is desired?
  • how many groups?
  • Indy or related?
45
Q

What is a type 1 error?

A
  • rejecting a null hypothesis when it is actually true and YOU SHOULD HAVE ACCEPTED IT YOU DUMB ASS!
  • insert picture guys that look the same but we said that they are different
  • same, yet we said they were different
46
Q

What is a Type 2 error?

A
  • accepting a null hypothesis when you should have rejected it
  • insert pic of a fat guy next to a skinny guy and we said that they were the same… different, yet we said it was the same
47
Q

What is power (1-B error)?

A

-the ability of a study design to detect a true difference if one truly exists between group comparisons, and therefore the level of accuracy in correctly accepting/rejecting the null hypothesis

48
Q

What is the relationship between sample size and power?

A

-the larger the sample size, the greater the likelihood of detecting a difference if one truly exists

49
Q

What 3 things go into sample size determination?

A
  • minimum difference between groups deemed relevant/important
  • expected variation of measurement
  • alpha and beta error rates and confidence interval
50
Q

What is the p value

A

-probability of making a type 1 error

51
Q

What is the magic number for p value?

A
  • 5% or 0.05

- if below that, then we can go ahead and reject the null hypothesis

52
Q

What is the other thing that we use besides p value that is based on variation in sample and sample size?

A
  • Confidence Interval (CI)

- 95% was blue

53
Q

When are the stats NOT significant for the CI?

A

-if CI crosses 1.0 (for ratios) or 0.0