Biostats Test 2 Kuma

Front 1

for numerical one group data what test do you do?

Back 1

t-test one sample
Confidence interval (the easy way)

Front 2

What are the question that should be asked about a sample?

Back 2

is this group representative of the population
is the sample random
how far are the results form the norm

Front 3

What are the steps for preforming a test

Back 3

1. state the Ho: x=
H alt: x does not = u
2. collect the data (will be given)
3. pick and preform a test statistic
4. critical value of t for significance
5. compare the measured t value with the critical value of t

Front 4

t-test one sample

Back 4

used when there is one numerical data with one group with normal distribution

Front 5

critical vlaue of t for significance

Back 5

at what value of t is significant
two tailed 0.05 is base case, defing the central tendency 95% of the sample

if t is outside the critical t value reject the Ho and t is significant

Front 6

if t is > Critcal t

Back 6

there is a difference
reject Ho
p<0.05

Front 7

if t is </= ti critical t

Back 7

fail to reject Ho there is no difference
p>0.05

Front 8

95% confidence intercal (the easy way) (t-test one group)

Back 8

represents the sample
if u is not in the range this is significant reject the Ho
indicator of sample studied

Front 9

95% CI (t-test one group)=

Back 9

x+/- t(0.05) (SEM)

Front 10

what do you do with ordinal or skewed data

Back 10

do not use a t-test
use the NP test based on medians rather than means

parallel version of a t-test is the sign test

Front 11

numerical data two groups

Back 11

1. paired
2. independent

Front 12

paired data

Back 12

1 group measured twice

2 groups of data

Front 13

independent data

Back 13

2 groups measured once

2 goups of people

Front 14

if the Confindence levels overlap when doing an indepentent t-test what tells that tell you

Back 14

that they are not significant

when they do not overlap they are significant

Front 15

if independent data is skewed or ordinal

Back 15

use the wilcoxon rank sum test

Front 16

problem with doing multiple pairings of t-test

Back 16

increases the chance of error each test has 5% chance of error and have to add them each time

Front 17

what can you do to account for multiple comparisons problems

Back 17

want 5% error as a whole

bonferoni correction

Front 18

bonferone correction

Back 18

divide alpha/#of tests

spreading alpha across all the test

Front 19

alpha priori

Back 19

doing the correction before the test are done

Front 20

ANOVA

Back 20

analysis of variance

start from a grand mean and see how different the groups are

looking at the variation within the groups and between the goups

Front 21

degrees of freedom for more than 1 group

Back 21

N(total number of subjects)- # groups

Front 22

variance between

Back 22

sume of (x-xi)2

Front 23

variance within

Back 23

sum of (Sdi)2

Front 24

f test (n,d)

Back 24

variation bw/variation w/in

Front 25

if f is > CV

Back 25

f is significant

Front 26

populaindivtion

Back 26

represents the entire group of individuals in whom are interested

Front 27

sample

Back 27

those who aer representative of the population

draw inferences from the sample about the population

Front 28

sampling error

Back 28

we have to recognize that the information in the sample may not fully reflect what is true about the population

introduced by studying only some of the population

Front 29

random sample

Back 29

individuals are selected randomly
everyne in the population has and equal chance of being selected

Front 30

parameter of the population

Back 30

mean or proportion

estimate using data collected from the sample a sample satistic and a point estimate

Front 31

sampling distribution of the mean

Back 31

if the sample size is large there should be a normal distribution

if the sample size is small the estimates of the mean follow a normal distribution if the sample is normally distributed

the mean is an unbiased of the population (estimates true population mean)

the variablity of the distribution is measured by the standard deviation of estimates

Front 32

standard error of the mean(SEM)

Back 32

if we know the population standard deviation then the SEM is given by
cigma/square root of n

Front 33

a large SEM

Back 33

indicates that the estimate is imprecise

Front 34

a small SEM

Back 34

the estimate is precise

Front 35

the SEM is reduced if

Back 35

the sample size is increased
the data is less variable

Front 36

standard deviation describes

Back 36

the variation in the data values and shoul dbe quoted if you wish to illustrate variability in the data

Front 37

SEM describes

Back 37

the precision of the sample mean and should be quoted if you are interested in the mean of a set of data

Front 38

95% CI if the distribution of sample means lies within

Back 38

1.96 SD
range of values within which we are 95% confident that the true population mean lies

Front 39

the samplng distribution of a proportion follows a ______ distribution

Back 39

binomial

Front 40

a wide CI indicates

Back 40

the estimate is imprecise

Front 41

a narrow CI indicates

Back 41

imprecision

Front 42

the width of CI depends on the size of

Back 42

SE, which depends on the sample size

Front 43

null hypothesis

Back 43

assumes no efect
difference in means is equal to 0

Front 44

alternative hypothesis

Back 44

holds if the null is not true

relates to the theory we are investigating

Front 45

two tailed test

Back 45

where we do not specify a direction that the difference may take (higher or lower than the mean)

used most often

Front 46

test statistic

Back 46

reflects the amount of evidence in the data against the null

usulaly the larger the value the greater the evidence

Front 47

p-value

Back 47

is the probability of obtaining our resutls or something more extreme if the null is true

Front 48

non-parametric tests

Back 48

replace data with ranks
used with ordinal data or categorical data

have less power than parametirc tests

Front 49

primary aim of a hypothesis test

Back 49

is to provide an exact p value

Front 50

confidence interval provides

Back 50

quantifies the effect of interest and enables us to asses the clinical implications

Front 51

bioequivalence trials

Back 51

randomized trials that are interested in showing the rate and extent of absorption of new formulations of the drug is the same of the old

Front 52

equivalence range

Back 52

used in bioequivalent trials

the range that corresponds to an effect of clinical importance

the CI for th effect lies within the equivalence range the two treatments are equal

Front 53

type I error

Back 53

we reject the null when it is true and conclude there is an effect when there is none

will never our chosen significance level

Front 54

type II error

Back 54

we do not reject the null when it is false and conclude that there is no evidence of an effect when there is

the power of the test (1-beta)

the power is the probability of rejecting the null when it is false

Front 55

power should be at least

Back 55

80%

Front 56

factors that affect power

Back 56

sample size (power increases with an increasing sample size

varibility of observation (power increases as the varibiltiy decreases

effect of interest (the power of the test is greater for larger effects

significance level (the power is greater if the significance level is larger

Front 57

situations that involve multiple comparisons

Back 57

subgroup anaylyses
multiple comparisons for a single outcome variable (making pari wise comparisons between groups)
multiple outcome variables
interim analyses (when treatment comparisons are made at predetermined intermediate stages of a study
data dredging (a priori)

Front 58

multivarient anaylsis

Back 58

consider simultaneously the effects of one or more explanatory variables or more than one outcome variable

Front 59

instead of a t-test for skewed data use

Back 59

a sign test or a wilcoxon rank test

Front 60

sign test is based on

Back 60

medians

Front 61

wilcoxon signed rank test

Back 61

takes into account the ranks of the data as weel as their signs

Front 62

paired t-test

Back 62

the individuals are linked to each other in somw way

Front 63

can you use a sign test for paired data

Back 63

yes, use it whe the data is skewed or ordinal

asseses the medians

Front 64

wilcoxon signed ranks tests for paired data

Back 64

takes into account not only of the signs of the difference but also their magnitude and therefore is more powerful than the sign test

Front 65

unpaired two sample t-test

Back 65

normal distribtion
based on means

Front 66

wilcoxon rank sum test

Back 66

used when the data is skewed instead of a unpaired two sample t-test

Front 67

mann-whitney U test

Back 67

used when the data is skewed instead of a unpaired two sample t-test

gives identical results although it is slightly more complicated to carry out by hand

Front 68

numerical data more than 2 groups use

Back 68

one-way analysis of variance (ANOVA)

Front 69

two types of variantion in the ANOVA

Back 69

between group variantion and within group variantion

Front 70

the ANOVA test is based on

Back 70

the ratio of the within group vairation and between group variation (F)

Front 71

non-parametric equivalent of the ANOVA

Back 71

Kruskal-Wallis test

Front 72

for categorical data use (a single proportion)

Back 72

the test of single proportions

individuals either have the desired trait or not (a proportion)

used for normal distribution

Front 73

the sign test applied to a proportion

Back 73

can be used to express a preference

Front 74

categorical data two proportions

Back 74

2 independent groups

Front 75

for 2 independent categorical groups use

Back 75

the chi-squared test

data is obtained as frequencies

Front 76

if the assumptions are not satisfied (categorical data)

Back 76

use a fisher's exact test to obtain the p value

Front 77

related groups (categorical data)

Back 77

McNemar's test

Front 78

McNemar's test

Back 78

the 2 groups are related or dependent

Front 79

chi-squared test large contingency tables

Back 79

the data may be represented in an rxc table with r rows and c columns

the enteries in the table are frequencies

every individual is represented once

Front 80

when there is a 2x2 table use

Back 80

chi-squared test

Front 81

chi-squared test for trend

Back 81

takes into account the ordering of the groups

Front 82

power def.

Back 82

the chance of detecting a statisically significant, a specified effect if it exist

at least 80%

Front 83

significance level (alpha)

Back 83

the cut off level below which we will reject a null

Front 84

varibility

Back 84

the standard deviation