Section 3 (Chapter 5 & 6)

Front 1

The science of collecting, organizing, and INTERPRETING data

Back 1

Statistics def #1

Front 2

The actual data that describes something

Back 2

Statistics def #2

Front 3

The whole group you want to know something about

Back 3

Population

Front 4

subgroup of the population from which data is collected

Back 4

Sample

Front 5

the characteristic you want to know

Back 5

Population Parameter

Front 6

the numbers and observations about the characteristic from the sample

Back 6

Sample Statistics

Front 7

State the goal of your study PRECISELY (who and what)

Back 7

5 Basic steps, step one

Front 8

Choose a representative sample

Back 8

5 Basic steps, step two

Front 9

Collect the data from the sample and summarize what we learned

Back 9

5 Basic steps, step three

Front 10

Use the sample statistics to infer the population parameter

Back 10

5 Basic steps, step four

Front 11

Draw conclusions about the study itself. Determine what could be done better the next time you do the study

Back 11

5 basic steps, step five

Front 12

a sample in which the relevant characteristics of the sample members are generally the same as those of the population

Back 12

representative sample

Front 13

Sample method where you choose a sample of items in such a way that every sample of the same size has an equal chance of being selected

Back 13

simple random sampling

Front 14

sample method where you use a simple system to choose the sample, such as selecting every 10th or 50th member of the population.

Back 14

systematic sampling

Front 15

sampling method where you choose a sample member that is easy to select

Back 15

convenience sampling

Front 16

sampling method where you partition the population into at least two strata (groups) and then draw a sample from each

Back 16

stratified sampling

Front 17

in a statistical study where the design or conduct tends to favor a certain result(s)

Back 17

Bias

Front 18

researchers observe or measure characteristics of the sample members but do not attempt to influence or modify these characteristics

Back 18

observational study

Front 19

researchers apply a treatment to some of all of the sample members and then observe the effects of the treatment

Back 19

experiment

Front 20

a group in an experiment whose members receive the treatment being tested

Back 20

treatment group

Front 21

a group in an experiment whose members DO NOT receive the treatment being tested

Back 21

control group

Front 22

a treatment that lacks the active ingredients of the treatment being tested in a study but looks and feels identical to the treatment so that participants cannot distinguish whether they are receiving the placebo or the real treatment

Back 22

placebo

Front 23

the situation in which patients improve simply because they believe they are receiving a useful treatment

Back 23

placebo effect

Front 24

in an experiment, the participants do not know whether they are members of the treatment or control group, but experimenters do know

Back 24

single-blind

Front 25

neither the participants nor the experimenters know who belongs to the treatment group and who belongs to the control group

Back 25

double-blind

Front 26

an observational, retrospective, study that resembles an experiment because the sample naturally divides into two of more groups

Back 26

case-control study

Front 27

the participants who engage in the behavior under retrospectivestudy form ________, which makes them like a treatment group

Back 27

cases

Front 28

the participants who DO NOT engage in the behavior under retrospectivestudy form ________, which makes them like a control group

Back 28

controls

Front 29

The _______ __ ________ in a statistical study used to describe a ________ ________ that is likely to contain the true population parameter.

Back 29

margin of error

confidence interval

Front 30

from (sample statistic - margin of error)

to (sample statistic + margin of error)

Back 30

confidence interval

Front 31

Should you believe?

look for the goal, clear population, type of study (obs or exp), blind, random. Was it appropriate

Back 31

Guideline 1: Get a Big Picture of the Study

Front 32

Should you believe?

evaluate for potential biases that might invalidate its conclusions. researchers pressured to produce results the funding company likes

Back 32

Guildeline 2: Consider the Source

Front 33

occurs whenever researchers select their sample in a way that tends to make it unrepresentative of the population.

Back 33

selection bias

Front 34

occurs whenever people choose whether to participate

Back 34

participation bias

Front 35

Should you believe?

is the sample representative of the population, how was the population selected

Back 35

Guideline 3: Look for Bias in the Sample

Front 36

any item or quantity that can vary or take on different values. items or quantities that the study seeks to measure

Back 36

variable

Front 37

Should you believe?

How was the study measured

Back 37

Guideline 4: Look for Problems in Defining or Measuring the Variables of Interest

Front 38

variables that are not intended to be part of the study can sometimes make it difficult to interpret results properly

Back 38

confounding veriables

Front 39

Should you believe?

Are there other variables that take on different values which may affect the results

Back 39

Guideline 5: Beware of Confounding Variables

Front 40

Should you believe?

can produce inaccurate or dishonest responses, especially for sensitive subject

Back 40

Guideline 6: Consider the Setting and Wording in Surveys

Front 41

Should you believe?

misrepresenting data in graphs or concluding statements; maybe misinterpreted results from researchers or jump to conclusions, or make exaggerated conclusions

Back 41

Guideline 7: Check that Results are Presented Fairly

Front 42

Should you believe?

ask:

Did the study achieve it's goals? Did conclusions make sense? Is there any alternative results?

Back 42

Guideline 8: Stand Back and Consider the Conclusions

Front 43

has 2 columns (categories and frequency)

Back 43

frequency table

Front 44

first column in a frequency table, lists names of data

Back 44

categories

Front 45

the numbers, data values in the category

Back 45

frequency

Front 46

fraction (percentage) of data values

frequency in category / total frequency

Back 46

relative frequency

Front 47

the number of values at or above that point (that categories plus all preceding categories)

Back 47

cumulative frequency

Front 48

2 types of data

Back 48

qualitative and quantitative data

Front 49

describes a quality or non-numerical data

Back 49

qualitative data

Front 50

counts or measurement data

Back 50

quantitative data

Front 51

group the data into categories that cover a range of possible values

Back 51

binning data

Front 52

set of bars to represent the frequency or relative frequency

Back 52

bar graph

Front 53

must always represent the total relative frequency of 100% and the proportion of the circle is the same as the %

Back 53

pie charts

Front 54

Label on graph

explains what is shown in the graph and source of the data

Back 54

title

Front 55

Label on graph

numbers on vertical axis with tick marks to indicate scale and the variable name of the vertical axis

Back 55

vertical scale and title

Front 56

Label on graph

names indicating the items in the horizontal scale, which may or may not include tick marks indicating a scale and the variable name of the horizontal axis

Back 56

horizontal scale and title

Front 57

Label on graph

only required when multiple sets of data are on the same graph; key

Back 57

legend

Front 58

a bar graph in which the data categories are quantitative; must follow the natural order of the numerical categories

Back 58

histogram

Front 59

serves the same purpose as a histogram, uses connected dots instead of bars

Back 59

line chart

Front 60

a line chart or histogram with the horizontal axis representing time

Back 60

time-series graph

Front 61

exists between two variables when higher values of one variable consistently go with higher values of another variable

Back 61

Definition of Correlation ~ Positive example

Front 62

when higher values of one variable consistently go with lower values of another variable

Back 62

Definition of Correlation ~ Negative example

Front 63

When there is no pattern between variables

Back 63

No correlation

Front 64

When both variables increase or decrease together

Back 64

positive correlation

Front 65

when one variable increases and the other decreases

Back 65

negative correlation

Front 66

how closely two variables follow a pattern

Back 66

strength of correlation

Front 67

coincidence

Back 67

possible explanation for a correlation

(1)

Front 68

common underlying cause

Back 68

possible explanation for a correlation

(2)

Front 69

Direct Cause

one variable causes the other

Back 69

possible explanation for a correlation

(3)

Front 70

look for a situation in which two variables are correlated regardless of whether other factors vary

Back 70

Guidelines for Establishing Causality

(1)

Front 71

Among groups that differ only in the presence or absence of the suspected cause, check that the effect is similarly present or absent

Back 71

Guidelines for Establishing Causality

(2)

Front 72

Look for evidence that larger amounts of the suspected cause produce larger amounts of the effect.

Back 72

Guidelines for Establishing Causality

(3)

Front 73

If the effect might be produced by other potential causes (besides the suspected cause), make sure that the effect still remains after accounting for these other potential causes.

Back 73

Guidelines for Establishing Causality

(4)

Front 74

If possible, test the suspected cause in an experiment.

Back 74

Guidelines for Establishing Causality

(5)

Front 75

Determine the physical mechanism by which the suspected cause produces the effect

Back 75

Guidelines for Establishing Causality

(6)

Front 76

discover a correlation, but cannot determine whether the correlation implies causality

start criminal investigation

Back 76

Levels of Confidence in Causality

Possible Cause

Front 77

reason to suspect correlation is cause & effect relationship (3 or 4 guidelines are met)

Issue a search warrent

Back 77

Levels of Confidence in Causality

Probable Cause

Front 78

found model that one thing causes another, it seems unreasonable to doubt the model

convict of crime

Back 78

Levels of Confidence in Causality

Cause Beyond Reasonable Doubt

Front 79

data set describes the values taken on by the variable & the frequency of each value

Back 79

distribution

Front 80

sum of all values / the number of values added

Back 80

Mean

Front 81

the middle value of the ordered data

if there is an even number if values, it is the mean of the middle two

Back 81

Median

Front 82

the value or values that occur most frequently

List like this: x or {x,y} or {x,y,z}

Back 82

Mode

Front 83

a data value that is much higher or much lower than almost all other values.

Back 83

Definition of Outlier

Front 84

what can change the mean but has no affect on the median or mode?

Back 84

answer: outlier

Front 85

What average should we use?

1,2,3,4,5,25

Back 85

answer: do not use Mean when there is an outlier

use median or mode

Front 86

Unimodal

Back 86

Shape of Distribution

one peak

Front 87

Bimodal

Back 87

Shape of Distribution

two peaks

Front 88

Uniform

Back 88

Shape of Distribution

categories have same frequency

Front 89

the left hand is a mirror image of the right half

Back 89

symmetric

Front 90

the distribution data values are more spread out on the named side

Back 90

skewed (left or right)

Front 91

Back 91

image of symmetric

Front 92

Back 92

image of left skewed

Front 93

Back 93

image of right skewed

Front 94

how wide the data is spread

Back 94

defination of variation

Front 95

the simplest way to describe variation is

Back 95

range

Front 96

lowest, lower quartile, median, upper quartile, highest

Back 96

5 Number Scores

Front 97

the quartile that divides the lower

Back 97

lower quartile

Front 98

when finding the upper or lower quartile, what do you not include

Back 98

do not include the median

Front 99

Whisker and box plot

the one with the most variation has

Back 99

the largest space between quartiles

Front 100

Greek letter sigma

Back 100

Standard Deviation

Front 101

Standard Deviation equation

Back 101

Square root ((sum of deviation from mean)squared / n - 1

Front 102

calculate standard deviation steps using calculator

Back 102

data: list 1: enter all numbers in set

2nd data: enter 3 times

Front 103

used to approximate the standard deviation

Back 103

Range Rule of Thumb

Front 104

range rule of thumb equation

Back 104

St Dev = range/4

Front 105

Lowest value approx=

Back 105

mean-2(st dev)

Front 106

Highest value approx=

Back 106

mean+2(st dev)

Front 107

symmetric bell shape curve with a well-defined peak

Back 107

Definition for Normal Distribution

Front 108

most data values are clustered near the mean giving a well defined peak

Back 108

#1 condition for a normal distrubition

Front 109

Data values are spead evenly about the mean making the distribution symmetric

Back 109

#2 condition for a normal distrubition

Front 110

Larger deviations from the mean become scarcer giving the tapered tails on the ends

Back 110

#3 condition for a normal distrubition

Front 111

Individual data values are a result of several different factors

Back 111

#4 condition for a normal distrubition

Front 112

68% falls within

Back 112

1 standard deviation

Front 113

95% falls within

Back 113

2 standard deviations

Front 114

99.7 falls within

Back 114

3 standard devations

Front 115

# of standard deviations from mean

Back 115

Definition for Standard Score or Z-Score

Front 116

Standard Score or Z-Score =

Back 116

(data value - mean) / Standard deviation

Front 117

the smallest value in which n% of the data values are at or below that data value (round down)

Back 117

Definition for Nth Percentile of a data set

Front 118

using the sample statistic to learn something about the population

Back 118

Definition for Statistical Inference

Front 119

If it is unlikely to happen by chance and small variations do happen by chance

Back 119

Definition for Statistical Significant

Front 120

Close to what we are expecting

Back 120

Definition for Not Significant

Front 121

Far from what is expected

Back 121

Definition for Significant

Front 122

The probability of an observed difference occurring by chance is 1 in 20 (0.05) or less, the difference is significant at the 0.05 level

Back 122

Definition for Quantifying Significance #1

Front 123

The probability of an observed difference occurring by chance is 1 in 100 (0.01) or less, the difference is significant at the 0.01 level

Back 123

Definition for Quantifying Significance #2

Front 124

(Sample stat - m of e) to (sample stat + m of e) =

Back 124

95% confidence interval

Front 125

Margin of Error approximately =

Back 125

1/square root n