Sta 210 Final Exam- Uky

Front 1

Association

Back 1

when some values of one variable tend to occur more often with some values of the second variable than with other variable of the same (second) variable

Front 2

Confidence statement

Back 2

statistic plus or minus the MOE

Front 3

Confounding

Back 3

when the effects of two variables on the response cannot be distinguished from one another.. often caused by lurking variables

Front 4

Correlation

Back 4

measure of straight line association (think scatter plots); numerical value that determines that direction and strength of liner association

Front 5

Correlation coefficient

Back 5

common numerical measure of a straight line association; always between -1 and 1; identified as "r"

Front 6

Explanatory variable

Back 6

a variable that might cause changes in the response variable

Front 7

Ha

Back 7

alternative hypothesis

Front 8

Ho

Back 8

null hypothesis

Front 9

inference

Back 9

act of drawing conclusions based on information we have that we assume to be accurate

Front 10

Lurking variable

Back 10

variable not directly studied that can compromise the ability to attribute any changes in response to a treatment

Front 11

Margin of error (MOE)

Back 11

numerical way of acknowledging that you know the sample statistic is not going to give perfect knowledge about the population parameter; attached to some notion of confidence interval

Front 12

negative association

Back 12

scatterplot downwards to the right

Front 13

Placebo

Back 13

dummie pull/treatment

Front 14

Placebo effect

Back 14

tendency for patients to show a real response to a fake treatment

Front 15

positive association

Back 15

a scatterplot that is upwards to the right

Front 16

randomization

Back 16

action that produces groups that are similar in all aspects; action that eliminates potential biases

Front 17

response variable

Back 17

variable that measures the outcome of a study

Front 18

sampling distribution

Back 18

plot of repeated sampling of a statistic

Front 19

scatterplot

Back 19

x-y plot taken on different subjects

Front 20

sensitivity

Back 20

ability of the test to identity positive outcomes as positive outcomes correctly

Front 21

simple random sample (SRS)

Back 21

sample of "n" individuals chosen from the population in such a way that every set of "n" individuals had the same chance of being chosen

Front 22

specificity

Back 22

ability of the test to correctly identify negative outcomes as negative

Front 23

statistical significance

Back 23

when differences in treatments are sufficiently large that they are unlikely to be due only to chance

Front 24

Simpson's Paradox

Back 24

when trends are one way for certain groups, but when the groups are combined, the trend reverses

Front 25

2 sources of confounding

Back 25

1) inadequate or improper comparison
2) lack of randomization

Front 26

US population

Back 26

about 300 million

Front 27

babies born in US each year

Back 27

4 million

Front 28

Americans that die each year

Back 28

2.4 million

Front 29

1 in 4 of who die,

Back 29

die of heart disease

Front 30

1 in 4 of who die,

Back 30

die from cancer

Front 31

deaths in traffic accidents

Back 31

43,000

Front 32

deaths that are homicides

Back 32

17,000

Front 33

deaths from AIDS

Back 33

16,000

Front 34

black Americans

Back 34

40 million

Front 35

Americans that identify as Latino

Back 35

14%

Front 36

reasoning process

Back 36

process of reasoning from premise to a conclusion

Front 37

examples of poor inference

Back 37

decimal point error
poor graphs
implausible number
percentages or absolutes (both can be deceptive)
incorrect comparisons

Front 38

experiments vs. surveys

Back 38

experiments: make a concerted effort to control conditions under which data is collected

Front 39

correlation doesn't mean...

Back 39

causation

Front 40

causation

Back 40

a relationship between two variables in which a change in the level of one causes a change in the other

Front 41

in regards to "r" the correlation coefficient, the closer to 1/-1 the. . .

Back 41

better or stronger the correlation

Front 42

inference can be defined as a conclusion drawn from evidence?

Back 42

true

Front 43

goal of sampling

Back 43

to make inferences about a population from what we know about sample data

Front 44

qualities of Push Polls

Back 44

goal: to influence opinions
often negative
often short
sample size is very large
biased

Front 45

population

Back 45

large collection of subjects/items that you are interested in understanding something about

Front 46

sample

Back 46

subjects/items that you are able to measure.interviews; chosen from population

Front 47

parameter

Back 47

number that describes population

Front 48

statistic

Back 48

number that describes the sample

Front 49

sampling variability

Back 49

variability seen in a statistic from sample to sample; same as sampling distribution

Front 50

shape of sampling distribution

Back 50

bell shapes, bell curve
peaks at parameter

Front 51

confidence interval

Back 51

helps to quantify the sampling error

Front 52

types of non-sampling errors

Back 52

data entry
nonresponse
biased questions
question order
false information
voluntary responses

Front 53

MOE doesn't apply when...

Back 53

when there are non sampling errors

Front 54

in hypothesis testing we want high ________ and low ______

Back 54

high sensitivity
low FPR

Front 55

false positive rate

Back 55

when the patient is really negative, but the test comes back positive

Front 56

false negative rate

Back 56

when the patient is really positive, but the test comes back negative

Front 57

1-sensitivity

Back 57

FNR

Front 58

1-specificity

Back 58

FPR

Front 59

in hypothesis testing treatments are either. .

Back 59

effective (Ha) p > p0
ineffective (Ho) p< p0

Front 60

steps for when you see "statistically significant" or "not statistically significant"

Back 60

1 establish comparison
2 express comparison in forms of Ha and Ho
3 determine who comparison turned out
4 articulate risk involved with decision/result

Front 61

practical significance

Back 61

whether the observed difference is big enough that it is practically worth caring about

Front 62

when accepting Ho, FPR is

Back 62

greater than 0.05

Front 63

when rejecting Ho, FPR is

Back 63

less than 0.05

Front 64

p-value is another word for...

Back 64

FPR

Front 65

you have _________ _______ if FPR is less than 0.05

Back 65

statistical significance

Front 66

in the context of testing Ho versus Ha, what did it mean to have a "false positive"

Back 66

you deiced Ha was true, when in fact Ho was true

Front 67

what do you hope to see when working with specificity and sensitivity?

Back 67

high sensitivity and high specificity
high sensitivity and low FPR
BOTH ARE SAME THING