Biostats Final

Front 1

It is the number of standard deviations that a given value is above or below the mean

Back 1

Z-score

Front 2

Is the likelihood or chance that something is true or that an event will occur.

Back 2

Probability

Front 3

all possible values

Back 3

Population

Front 4

a portion of the population

Back 4

sample

Front 5

all the sample means plotted on a histogram

Back 5

sampling distribution

Front 6

Two forms of inferential statistics:

Back 6

Hypothesis testing
Estimation

Front 7

generalizing from a sample to a population with calculated degree of certainty

Back 7

Inferential statistics

Front 8

__________is a statistical procedure that allows researchers to use sample data to draw inferences about the population of interest.

Back 8

Hypothesis Testing

Front 9

A hypothesis test is a statistical method that uses sample data to evaluate a hypothesis about a ___________.
Also called a test of significance.

Back 9

population parameter.

Front 10

a claim or statement about a property or characteristic of a population.

Back 10

A hypothesis

Front 11

A scientific hypothesis must be_______.

Back 11

testable.

Front 12

What is the goal of hypothesis testing?

Back 12

The goal of the hypothesis test is to determine whether or not the treatment has any effect on the individuals in the population.

Front 13

This says there is no treatment effect.

Back 13

State the Null hypothesis H0:

Front 14

This says that the treatment has an effect on the dependent variable

Back 14

Scientific or Alternate Hypothesis H1 or (Ha):

Front 15

The null hypothesis cannot be proven _____only proven _____.

Back 15

True;False

Front 16

The Null and Alternate must be ___________of each other to cover all possibilities.

Back 16

exact opposites

Front 17

What are the two possible conclusions of hypothesis testing?

Back 17

Reject the null hypothesis H0.
Cannot reject the null hypothesis H0.

Front 18

If, under a given assumption, the probability of a particular observed event is exceptionally small, we conclude that the assumption is probably not correct.

Back 18

Rare Event Rule

Front 19

__________ is the smallest level of significance at which
H0 would be rejected when a specified test procedure is used
on a given data set.

Back 19

The P-value

Front 20

The _________ is a value computed from the sample data.

Back 20

test statistic

Front 21

Who sets the level of significance?

Back 21

researcher

Front 22

A significant result means the null hypothesis _______.

Back 22

has been rejected.

Front 23

What is the major distinction between a one tailed and two tailed test ?

Back 23

criteria they use for rejecting the H0

Front 24

A ____tailed test allows you to reject the H0 when the difference between the sample and the population is relatively small.

Back 24

one tailed test

Front 25

A ____tailed test requires a relatively large difference independent of direction.

Back 25

two-tailed test

Front 26

If the treatment is still similar to the original population, then we conclude that there is no evidence for a treatment effect, ___________.

Back 26

and we fail to reject the null hypothesis.

Front 27

Is the size of the difference between the sample and the population.

Back 27

critical factor

Front 28

allows researchers to use sample data to draw inferences about the population of interest.

Back 28

Hypothesis testing

Front 29

The mistake of rejecting the null hypothesis when it is actually true.

Back 29

Type I error

Front 30

The mistake of failing to reject the null hypothesis when it is actually false.

Back 30

Type II error

Front 31

The consequences of a type ___ error are usually not as serious as those from a Type ___ error.

Back 31

2 ;1(more dangerous)

Front 32

The power of a test can be increased by using____________.

Back 32

larger samples

in general, the larger the sample is the better it will represent the population.

Front 33

Interpretation Cohen's d (effect size )

Back 33

0.2 or below = "small" effect
0.5 = "medium" effect
0.8 and above = a "large" effect

Front 34

_____ is the probability that the test will correctly detect a real treatment effect and correctly reject the null hypothesis

Back 34

Power

Front 35

The _______ of a statistical test is the probability that the test will correctly reject a false null hypothesis.

Back 35

power

Front 36

As power ______, the probability of a type II error _______.

Back 36

Increases;Decreases

Front 37

_________ power analysis is conducted after a study has been completed, and uses the obtained sample size and effect size to determine what the power was in the study.

Back 37

Post-hoc

Front 38

The entire set of individuals defined in a study

Back 38

Target population

Front 39

Process by which you select the elements of the population

Back 39

Randomization

Front 40

The difference between a statistic and a parameter

Back 40

Sampling error

Front 41

results from sampling error

Back 41

Systematic bias

Front 42

Normal and usual variation in characteristics of a population. Scores are scattered around the mean

Back 42

Random variation

Front 43

Inferential statistics based on random sampling is the best way to...

Back 43

Eliminate systematic bias
Increase representation

Front 44

Provides exactly equal chance of being selected

Back 44

Simple random sampling

Front 45

Used when you know that some variables are critical to your study

Back 45

Stratified random sampling

Front 46

Involves selecting every nth individual on a random list
Population = 100, sample size = 20, take every 5th

Back 46

Systematic sampling

Front 47

Which type of sampling method is a Classroom of students or Other intact groups?

Back 47

Convenience sampling

Front 48

Sampling error decreases as sample size increases. T/F

Back 48

True

Front 49

measures the effect of the hypothesis. It is not the actual significance level.

Back 49

Cohen’s d

Front 50

is a test statistic and transforms your raw score into a standard score

Back 50

Z score

Front 51

Two types of test statistics:

Back 51

Parametric
Non Parametric

Front 52

What are the 4 levels of measurement?

Back 52

1. Nominal Scale
Gender, ethnic background
2. Ordinal Scale
Hardness of rocks, beauty, military ranks
3. Interval Scale
Celsius or Fahrenheit
4. Ratio Scale
Kelvin temperature, speed, height, mass or weight

Front 53

Assumptions for a Parametric test require data from an_____scale.

Back 53

interval or a ratio

Front 54

Examples of parametric tests:

Back 54

t test
F test (ANOVA Analysis of Variance)
Multivariate Analysis of Variance (MANOVA)
Pearson Product moment Correlation
Regression Analysis

Front 55

Non Parametric Assumptions use _____ scales.

Back 55

Use Nominal or Ordinal scales.

Front 56

Types of Non Parametric Tests

Back 56

Chi square
Mann-Whitney U test
Wilcoxon Rank sum test
Kruskal-Wallis One way analysis of variance
Friedman Two way analysis of variance
Spearman Rank order correlation

Front 57

Nonparametric alternative to the t-test

Back 57

Mann-Whitney U Test

Front 58

The _________test is used to examine differences with categorical variables.
(religion, political preference, etc).

Back 58

chi-square

Front 59

The (n)number of possibilities minus one.
For the chi square n refers to the number of categories.

Back 59

Degrees of freedom df

Front 60

Soda Preference: Coke, Pepsi, Sprite, Fresca
What is your Degree of Freedom?

Back 60

Df = 3

Front 61

What parametric statistic would you use if you want to look at more than 2 groups?

Back 61

ANOVA

Front 62

P value has to be less than .05 in order to be significant, and to reject the null hypothesis.
T/F?

Back 62

True

Front 63

How do we test to see if the means between two sample populations are different?

Back 63

t test

Front 64

used to compare two sample means when the two samples are independent of one another

Back 64

Independent t test

Front 65

is used for matched samples (where the two samples are not independent of one another)

Back 65

Dependent t test

Front 66

Used to evaluate the (mean differences) variability between two or more treatments

Back 66

Analysis of Variance
ANOVA

Front 67

A ratio of variability explained by the treatment (between groups) to error (within groups) variability

Back 67

F-Statistic

Front 68

Two possible explanations for variance:

Back 68

1. Treatment effect:
The differences between groups are caused by the treatments
2. Chance:
The differences between groups are simply due to chance.

Front 69

are analysis that are done after a significant ANOVA to determine exactly which mean differences are significant and which are not

Back 69

Post hoc tests

Front 70

different types of post hoc tests

Back 70

Tukey’s honestly significant difference (HSD) test

Schfee’ test
More conservative safer test

Bonferroni
Simplest
More conservative than Schfee

Front 71

an extension of ANOVA in which main effects and interactions are assessed on a combination of DVs

can have more than one dependent variable

Back 71

MANOVA

Front 72

A statistical technique used to measure and describe the relationship between two variables.

Back 72

Correlation

Front 73

There is no cause and effect

Usually you are just observing relationships

Back 73

Correlation

Front 74

A correlation tells you that a relationship exists, but tell you _________ about cause and effect.

Back 74

nothing

Front 75

an unusual score, relative to the data set. It will influence the mean and the standard deviation.

Back 75

Outlier

Front 76

indicates the extent to which two variables are related.

Back 76

correlation coefficient

Front 77

A correlation Coefficient tells us:

Back 77

A correlation Coefficient tells us:
Direction of relationship
Strength of relationship

Front 78

Used when both variables are measured are least interval. Expressed as ‘r’

Back 78

Pearson product moment correlation

Front 79

Two ordinal variables:

Back 79

Spearman rank Order Correlation (rho)
Kendall rank order Correlation (tau).

Front 80

Correlation Coefficient Strength Interpretation

Back 80

0.0-0.2 Very Low
0.2-0.4 Low
0.4-0.6 Moderate
0.6-0.8 High Moderate
0.8-1.0 High

Front 81

Use to predict the probably an event will occur using a logistic curve for categorical data

Back 81

logistic regression

Front 82

Identify what types of variables may be used in a logistic regression

Back 82

Dependent variable
-Categorical
-Dichotomous

Independent variables
-Any type

Front 83

which statistical tests are used to determine statistical significance for Kaplan-Meier curves

Back 83

Wilcoxon rank-sum test
Mann-Whitney U test
Logrank test: result in a p value

Front 84

Probability of experiencing an event over time

Back 84

survival analysis

Front 85

Patients followed over time until they experience an event

Back 85

Kaplan-Meir

Front 86

Loss of patient data before an event
Patient drop out

Back 86

Censoring

Front 87

A linear association between 2 continuous variables (one IV one DV)

Back 87

Linear Regression

Front 88

The________ tells us about the linear relationship (strength and direction) between variables.

Back 88

Pearson r

Front 89

By squaring Pearson r, we can calculate the __________

Back 89

coefficient of determination, r2

Front 90

______ tells us how much of the variation in the Y is accounted for by the X

Back 90

coefficient of determination, r2

Front 91

The goal of the regression equation is to find the best fitting straight line for a set of data. T/F? what does this mean?

Back 91

True , In other words, to make the best prediction.

Front 92

Often more than one variable predicts an outcome.
Take into account the scores from several IVs on a DV.

Back 92

Multiple regression