Statistics: Exam 1

Front 1

Selection Bias

Back 1

Occurs when the data that comes from the people who are selected for a study does not represent the population.

Front 2

Nonresponse Bias

Back 2

Occurs when a large number of people who are selected for a study elect to not respond to the survey or key questions on the survey.

Front 3

Observation Study

Back 3

Collect data on participants in their naturally occuring settings/groups. No randomization is used. Cause and effect conclusions are not possible.

Front 4

Experiment

Back 4

Appropriate evidence can support cause and effect conclusions. Random assignment is used instead of naturally occuring settings.

Front 5

Variables

Back 5

Different measurements in observations from one piece of info to the next may vary person to person.

Front 6

Categorical

Back 6

The possible choices are "words" or "categories."

Front 7

Measurement - continuous

Back 7

The variables are numbers and can assume a range of values. The variables can be subdivided into fractional parts. Usually the variable is expressed as "an amount of something."

Front 8

Measurement - discrete

Back 8

One can simply count the number of something that was measured in a given time frame. These variable can not be subdivided and is typically expressed as "a number of" something.

Front 9

Deliberate Bias (One-Sided Statements)

Back 9

Gives the respondent one point of view and tend to agree with the statement. Two sided statements are preferred b/c it states a question without only one point of view.

Front 10

Deliberate Bias (Filtering)

Back 10

Choices in answers contain "undecided" or "don't know" and people will typically choose those instead of a difinitive answer.

Front 11

Deliberate Bias (Importance of Order)

Back 11

Results usually vary based on the order in which the choice is presented. They tend to pick the first choice.

Front 12

Deliberate Bias (Anchoring)

Back 12

Respondants are influenced by the wording of the question and people's perceptions can be distorted when there is a point of anchor. The may have limited knowledge of the topic or distracted by the anchor.

Front 13

Unintentional Bias

Back 13

People oppose questions that contain such words like forbidden, control, ban etc because people do not like to be told what to do.

Front 14

Unnecessary Complexity ("Double-barreled" problem)

Back 14

When the respondant must consider 2 questions in 1 at the same time.

Front 15

Reliability

Back 15

The reproducibility of a measurement over and over.

Front 16

Validity

Back 16

The strength of our conclusions, inferences or propositions.

Front 17

Reliability vs. Validity

Back 17

Reliability measures results over a period of time to get consistant outcomes while validity measures the strength of the outcomes.

Front 18

Histogram

Back 18

Measures data and uses a range of numbers, not words.

Front 19

Right Skewed

Back 19

A larger percent of data is found on lower tail of the histogram. The majority of the data is clumped to the left.

If mean is greater than median.

Front 20

Left Skewed

Back 20

A larger percent of data is found on upper tail of the histogram. The majority of the data is clumped to the right.

If mean is less than median.

Front 21

Symmetrical

Back 21

An equal percent of data is on each tail of the histogram, putting the hump in the center.

If mean and median are approximately equal.

Front 22

Measure of spread (resistant)

Back 22

The IQR. It measures the distance between the Qu and the Ql

If a sample has outliers and/or skewness, this measure are preferred.

Front 23

Measure of spread (sensitive)

Back 23

Standard deviation. It is influenced by outliers and roughly the average of distance that the observations fall from the mean.

If a sample is reasonably symmetric, this measure should be used.

Front 24

Measure of center (sensitive)

Back 24

The mean

Front 25

Measure of center (resistant)

Back 25

The median

Front 26

5 number summary

Back 26

Includes the lowest, lower quartile, median, upper quartile, and hightest

Front 27

Lower quartile (percentile)

Back 27

25% of the data falls below this percentile - 25th percentile

Front 28

Upper quartile (percentile)

Back 28

75% of the data falls below this percentile - 75th percentile

Front 29

Median

Back 29

50% of data falls below this percentile - 50th percentile

The middle number.

Front 30

Mean

Back 30

The average of all the values.

Front 31

Boxplot Interpretation

Back 31

The ends of the box are the Qu and Ql. The line in the middle of the box represents the median. Lines that extend past the box are the highest and lowest values that do not reach the outlier. Asterisks are the outliers.

If one side of the box is larger or smaller that means the data set is skewed.

Front 32

Empirical rule

Back 32

A guideline that can be applied when you know that the sample is normally distributed and one to understand what the standard deviation represents.

It says that for any normal (bell-shaped) curve, approximately:
68% of the values (data) fall within 1 standard deviation of the mean in either direction.
95% of the values (data) fall within 2 standard deviations ...
99.7% of the values (data) fall within 3 standard deviations ...

Front 33

Population

Back 33

The entire group of individuals or objects that we wish to estimate some characteristic's (variable's) value.

Front 34

Sampling frame

Back 34

The list of the sampling units from which those to be contacted for inclusion in the sample is obtained.

Front 35

Sample

Back 35

Those individuals or objects who provided the data collected.

Front 36

Experimental (sampling) unit

Back 36

The individual, person or object that has the measurement (observation) taken on them/it.

Front 37

3 difficulties when samples are obtained

Back 37

Using the wrong sampling frame.

Not reaching the individuals selected.

Getting no response or a volunteer response.

Front 38

No response or volunteer response

Back 38

A low response rate from the sampling units. Also called a nonresponse bias

Front 39

Using the wrong sampling frame

Back 39

When the responses do not appropriately represesent the population. Also called a selection bias.

Front 40

Not reaching the individuals selected

Back 40

When questionarres do not actually reach the proper sample.

Front 41

Margin of error

Back 41

It measures the accuracy of the percent estimated in the survey.

It is calculated using this formula: 1 divided by the square root of the number of people in the sample.

The sample percent + or - the calculated error %.

Front 42

Sampling methods

Back 42

Probability :
1.Simple Random Sampling (SRS)
2.Stratified Sampling
3.Cluster Sampling
4.Multistage Sampling
5.Random-Digit Dialing
6.Systematic Sampling

Judgement:
1.volunteer samples
2.haphazard (convenience) samples

Front 43

Stratified

Back 43

Partitions the population into groups.

Obtains a simple random sample from each group.

Collects data on each sampling unit that was randomly sampled from each group.

Front 44

Cluster

Back 44

Divides the population into groups (clusters).

Obtains a simple random sample of so many clusters from all possible clusters.

Obtains data on every sampling unit in each of the randomly selected clusters.