# UNIT 3 - SAMPLES and EXPERIMENTS Flashcards

1
Q

A 4 year high school of 2000 students, sampling 40 high students: Describe a simple random sample

A

Number students 1-2000. Use rantom number generator to get 40 unique integers from 1 to 2000.

2
Q

A 4 year high school of 2000 students, sampling 40 high students: Describe a stratified sample

A

Stratify by year. Randomly choose 10 FR, 10 SO, 10 JU and 10 SENIORS

3
Q

A 4 year high school of 2000 students, sampling 40 high students: Describe a convenience sample

A

Ask the first 40 students coming to the locker rooms after school. This is problematic because athletes may not have the same preferences as non athletes.

4
Q

A 4 year high school of 2000 students, sampling 40 high students : Describe a systematic sample

A

Get an alphabetical list of all of the students, 2000/40=50. Randomly choose one of the first 50 students and then every 50th student after that.

5
Q

A 4 year high school of 2000 students, sampling 40 high students: Describe a cluster sample

A

Imagine that all of art classes have 10 students and they are mixed with fr, so, jr and srs… You would randomly choose 4 classes and survey everyone in each of the 4 classes.

6
Q

What is a flaw of SRS that is not a flaw of others?

A

You could get any sample group with an SRS. You could sample a high school and just randomly get a sample of just male juniors. While it is not likely, it could happen. All groups are possible, and equally likely. We stratify to prevent this from happening.

7
Q

A 4 year high school of 2000 students, sampling 40 high students: Since ALL GROUPS (samples) are possible and equally likely, show some groups that you could get randomly from and SRS that would not be representative of the entire school.

A

all female, all freshmen, all seniors, all athletes.. these could happen in an SRS (but they are not likely to)

8
Q

A 4 year high school of 2000 students, sampling 40 high students: Explain how stratifying has “impossible groups”

A

You couldn’t get all freshmen in your sample

9
Q

A 4 year high school of 2000 students, sampling 40 high students: Explain how clustering has “impossible groups”

A

You couldn’t get 2 people from each classroom, because you would be randomly choosing classrooms and asking everyone in those classes.

10
Q

A 4 year high school of 2000 students, sampling 40 high students: Explain how systematic has “impossible groups”

A

You couldn’t get the first 40 people alphabetically (because you are taking every nth)

11
Q

What is the standard sampling method?

A

A Simple Random Sample (SRS) is our standard. Every possible group of n individuals has an equal chance of being our sample. That’s what makes it simple. Put the names in a hat.

12
Q

give an Example of a MULTISTAGE sample

A

Suppose you want to poll urban, suburban and rural citizens, you can divide a map into those strata, and then randomly choose neighborhoods or streets in each and ask everyone on those streets. Here you stratified by community type and then clustered by street.

13
Q

What is a multistage sample?

A

A sample that combines several sampling methods

14
Q

What are the two types of observational studies?

A

Retrospective, and Prospective

15
Q

What is a simple random sample?

A

put all of the names in a hat. every group is possible. pull the numbers

16
Q

What is cluster sampling?

A

Cluster- grab clusters of the population. each cluster should be representative ( like the population) use a few clusters.

17
Q

What is retrospective study?

A

A retrospective study is a study that looks backwards in time (or at the present moment).

18
Q

What is systematic sampling?

A

collecting data from every nth subject.

19
Q

What is prospective study?

A

Prospective study is when you study the experimental unit’s present and future.

20
Q

What is a representative sample?

A

A sample that looks like the population. It has similar characteristics.

21
Q

What is stratified sampling?

A

When you break the population into groups with similar attributes and randomly select from each strata.

22
Q

What are the “good” sampling methods?

A

SRS (simple random sample), stratified, clustered, systematic, multistage

23
Q

What are the “bad” sampling methods.

A

convenience samples, voluntary samples

24
Q

When your sampling frame is different from the population, then you risk ____

A

undercoverage

25
Q

What is wording bias

A

A type of response bias, When the wording of the question impacts response to it. (type of response bias)

26
Q

Systematic, how do you find the N for every nth subject, and then how do you proceed?

A

TOTAL POP/SAMPLE SIZE= your n (round down). Then use RAND INT to Randomly choose first. RANDINT(1, n). And then take every nTH.

27
Q

What is BIAS in sampling?

A

A systematic FLAW in your method. Undercoverage, Wording, Volutary, Convenience, Comfort (psychological), Response, Non-response BIAS. Even with a larger sample, you will still have bias.

28
Q

What’s the difference between a prospective and a retrospective study?

A

A retrospective study takes a group and looks back at its history while a prospective study watches a group for a period of time and records the data along the way into the future.

29
Q

What is a weakness of a SRS?

A

Suppose you want a sample of 50 high school students, with an SRS, although unlikely you could get “all freshmen” which wouldn’t be representative.

30
Q

Is it always better to do a census or to sample?

A

depends on the availablility of the data. If the you want to look at SAT vs GPA, you may easily be able to get all of the school’s data and do that study (a census). If you have to go out and get the info, you may want to take a sample to save time and energy.

31
Q

What is a sampling frame?

A

It is the frame from which you get your sample. For instance, if you call people the frame would be “people with phones,” if FOX news takes a poll, the sampling frame is “fox news watchers”

32
Q

When sampling, what kind of sample are we striving to get?

A

A representative sample, we want our sample to have similar charactaristics as the population

33
Q

To make a survey to tell of a restaurant is good, would you ask the people coming out of the restaurant?

A

People at the restaurant are probably there because they already like it. If you asked the question “Is this your first time dining here?” and if they say “yes” you survey them, that would be a better method. But then again.. the people wouldn’t go into an Italian restaurant if they didn’t like that type of food.

34
Q

What is undercoverage?

A

Undercoverage is when a group of the population is not represented in the sample. When the sampling frame isn’t representative.

35
Q

What is response bias? How do you avoid it?

A

Response bias is any influence that may sway the respondent e.g wording of the question, interviewer’s behavior/background. Therefore, in a survey, ask questions that allow respondents to answer comfortably and honestly. Keep the wording “indifferent” or neutral in some way in order to unduly favor one response over another.

36
Q

Things that cause nonresponse bias ?

A

(remember non response is that the people you ask, or try to ask don’t respond) Lazy researcher, shy survey takers, who is the questioner, environment,

37
Q

What is a quality of SRS that is not a quality of Systematic, Stratified or Clustering?

A

In an SRS, all groups are possible, and ALL POSSIBLE GROUPS have the same chance of being picked (like all senior male students.).The other methods have lots of impossible groups. SRS has no impossible groups. Example: -Stratified- an impossible group would be all girls (you’re taking some boys and girls)-Clustered- an impossible group would be all girls (each cluster has boys and girls)-systematic- an impossible group would be first 10 people that are right next to each other (you are taking every nth person, so you will skip)

38
Q

What is statistically significant?

A

When an observed difference is too odd for us to believe that it is likely to have occurred naturally (or just randomly). Basically it is Statistically Significant when we don’t think it happened randomly. when you think “something’s up” or “something’s fishy”

39
Q

How can you use random numbers to sample?

A

Number the subjects 00-99 (if less than 100) or 000-999 (if less than 1000) or 0000 to 9999 etc.. then use a random number table taking one, two, three or four numbers at a time. Throw out repeats.

40
Q

In which sampling methods do the subjects have equal chances of being selected?

A

SRS, Stratified, Clustered, Systematic, and multistage. In all of these, the subjects have an equal chance (but groups have different chances)

41
Q

How are we proving causation in experiments and obs studies?

A

No causation in a study, maybe association or correlation. ONLY IN EXPERIMENTS TO YOU TALK ABOUT CAUSALITY.

42
Q

Name types of bias

A

undercoverage, non response, response, voluntary

43
Q

What is the placebo effect?

A

When those who get the placebo show improvements, or show the effects of the treatment. This often happens to up 20% of participants!

44
Q

what is the best way to reduce bias?

A

randomness and good sampling methods.

45
Q

What is sampling error?

A

How far your statistic is from the parameter (how far your calculation from your sample was from the population parameter)

46
Q

Suppose you want to see the relationship between gender and candy preference in squirrels. How may you do a stratified vs cluster sample

A

STRATIFIED: You can split the list of all of the squirrels in your neihborhood by gender and randomly select 20 males from th list of all of the males, and then 20 females (strata) from all of the females. CLUSTER: you can randomly choose to 5 different trees and survey all of the squirrels in those trees, assuming that there are 4 squirrels living in each tree (clusters, the trees have both M and F).

47
Q

What is difference between non response bias and undercoverage?

A

You may ask someone to take a survey, they may say no. They may feel differently than the people who decide to take the survey. In this case, that is non-response bias. Undercoverage happens when you didn’t even ask some people to take the survey. The people you didn’t even ask might feel different.

48
Q

How is BIAS different from SAMPLING error

A

Bias is a systematic flaw in your sampling method. Sampling error is always present even with the best methodology- it is the natural variablility of sample statistics. Different samples give different statistics.

49
Q

name 2 differences between experiments and observational studies:

A
1. Experiments can prove causation (studies can’t) . 2. In experiments, you assign treatments (studies you just watch)
50
Q

name 2 differences between observational studies and experiments:

A
1. Observational studies cannot prove causation - experiments can. 2. In observational studies you are just collecting data and observing- in experiments you manipulate the environment/treatment.
51
Q

What is the difference between response bias and nonresponse bias?

A

Response is when the person’s response is influenced by the question or questioning method (like if a parent asks if you use drugs, as opposed to a friend… there is only one answer to this, but one might respond differently to them), non response is is when the people who don’t respond might have different opinions/views than the people who did.

52
Q

Example of response bias

A

A teenager goes to the doctor’s office with their parents. The doctor asks the teen if they vape. The teen may say “no” because their parent’s are there, even though they do vape.

53
Q

What is the main purpose of a placebo ?

A

To blind the subject that is being experimented on to avoid influence to the given variable therefore altering the response variable . When people think they’re getting help, they often improve anyway..

54
Q

Example of undercoverage

A

You only ask people who go to Home Depot about their views on school lunches.

55
Q

Example of nonresponse bias

A

In a survey, a person does not answer a few questions (or a person is on your list and you can’t get a hold of them)

56
Q

How can you decrease sampling error?

A

Get a larger sample

57
Q

Is sampling error a mistake?

A

IT IS NOT A MISTAKE!!! Because the data in samples are generally different, the statistics calculated from one sample to another vary and are generally not equal to the parameter. This variablilty of STATISTICS is called sampling error.

58
Q

Can you eliminate sampling error?

A

Only if you take a census. Larger samples have less error.

59
Q

What is random sampling?

A

When we use chance to select a sample, like rolling dice, a random number generator, or a random number table in our selection process. We use randomization in all of the “GOOD” sampling methods.

60
Q

T/F An unbiased sampling method will eliminate error

A

No, error is always there. Error is not a mistake.

61
Q

What is the problem with convenience sampling?

A

The sample may not be representative as it is not randomized to include every type of person. Friends and family are convenient but they likely share similar opinions and thus the sample is not representative of a population.

62
Q

In which sampling methods do all subjects have the same probability of being chosen?

A

SRS, cluster, systematic and stratified all give subjects equal likelihood of being chosen.

63
Q

How is undercoverage different from non response

A

64
Q

How is a sampling frame different from the population?

A

Suppose you are wondering how elderly people on the cape feel about a new medicare law. If you go to nursing homes and randomly sample residents, then the frame is “elderly people at those nursing homes.” Your population is still elderly people on cape cod.

65
Q

Will larger samples reduce BIAS?

A

No, bias is a systematic flaw, even large samples will still have bias. If you ask more people outside of McDonalds, you still only get answers from people who eat at McDonalds (large samples can reduce error, however)

66
Q

Example of wording bias

A

Do you support food assistance and nutrition programs for children living in poverty? VS. Do you approve of supporting lazy people on welfare?

67
Q

How are voluntary and convenience samples similar

A

With voluntary, people choose them selves, with covenience, the people are just chosen by researcher, neither uses randomness and both are prone to BIAS.

68
Q

What is wrong with using volunteers in a survey?

A

(Volunteers are often upset or emotionally attached) Those who volunteer may not be like the rest of the population. An example may be, if you’re trying to find our how often people volunteer for things. So you ask for volunteers to take the survey. A question may be “when was the last time you volunteered for something?” Well. they all just volunteered for the survey!

69
Q

How can the WORDING of the question lead to response bias

A

Words or phrases that impact your feelings tend to influence responses. Look for “devastating, horrific, wonderful etc.” Sometimes there is a background story like “Many americans lose jobs to illegal aliens every year, do you feel this is fair”

70
Q

What type of study would find relationship beween Verbal and Math SAT?

A

You could take all of the SAT Math and Verbal scores and run a regression and find the r-quared value and linear model. This would be a Retrospective Study.

71
Q

What’s the difference between stratified and cluster sampling?

A

Stratified- you divide the population up into groups with similar traits, called strata (homogeneous groups) and randomly choose a few from each strata.

72
Q

In which sampling methods do all GROUPS have the same probability of being chosen?

A

Only in SRS do all GROUPS have the same probability of being chosen, all of the other methods have IMPOSSIBLE GROUPS.

73
Q

Why do you have to Stratify?

A

You don’t have to.. But you might want to if you feel that a simple random sample might not be representative of the population . You want your sample to be like the population. a representative sample (it represents the population well).

74
Q

How is Blocking in an Experiment Similar to Stratefying in a Sample?

A

The two are similar because they divide the subjects into homogenous groups where the subjects are all similar (these traits were already present in the population)

75
Q

How are we manipulating the environment differently in experiments and studies?

A

No manipulation or treatments in an observational study. You only manipulate environment in an experminet.

76
Q

4 ingredients: What is “control?”

A

You want to control the environment as best as you can so that the only difference between groups is the treatment, and the treatment only. Everything else should be similar.

77
Q

How are we making inferences differently in experiments vs studies?

A

In observaional studies, you make and inference about the population, in an experiment you make an inference about a treatment.

78
Q

4 ingredients: What is “replication?”

A

Having enough subjects. You don’t want to test fertilizer on just one plant.

79
Q

Give an example of matched pair design for comparing a new blood pressure medication to an older version?

A

Have subjects use the new medication for a month and the old one for a month and compare. Be sure to randomize which month and blind.

80
Q

Who can be blinded? ( two groups)

A
1. Subjects (and dog owners..). The poeple getting treatment and 2. administrators. Those delivering treatments and assessing effectiveness of treatments.
81
Q

Why does it make sense to double-blind an experiment?

A

It reduces bias in an experiment. If subjects don’t know what treatment they’re receiving, they won’t change their habits based on that knowledge. If evaluators don’t know which treatment each subject is receiving, they won’t bias the true results based on the results they expect to see

82
Q

What is the sure way to assign treatments correctly?

A

throw names in hat and first half in group 1 and the rest group 2. . Or number subjects from 1-n and use randint until you get half for group 1.

83
Q

What is the difference between single-blind and double blind?

A

Single blinding is when all individuals in either one of the classes are blinded; double-blinded is when everyone in BOTH classes are blinded. Classes are: subjects and the other is treatment givers + evaluators

84
Q

What is the purpose of matching?

A

it isolates the differences between subjects so help see the impact of the treatment.

85
Q

4 INGREDIENTS TO EXPERIMENTS

A

Compare, control , randomization, replication (and BLOCKING when you need to)

86
Q

4 ingredients: What is “compare?”

A

Having something to compare your treatment with helps you see its effectiveness.

87
Q

4 ingredients: What is “BLOCKING?”

A

If you think different groups of subjects may respond differently to treatments because of location, gender, age, then you make BLOCKS, and make sure to compare the treatments within each block.

88
Q

What are the two (three) types of experiments?

A
1. Completely randomized 2. Randomized block (matched pairs)
89
Q

What is a control group?

A

The group that doesn’t get a treatment (or gets the old treatment). It helps us see the impact of the environment. It gets the placebo or standard care but goes through all of the motions

90
Q

Give example of factors and levels

A

Factor: medication. Levels: 50mg, 100mg and 200mg.

91
Q

What is a level in an experiment? give example

A

Example. For the Factor “SLEEP” the, level(s) would be how many hours the subjects were alowed to sleep.. 4 hours, 6 hours, 8 hours.. 3 levels

92
Q

What is difference between completely randomized and random block design?

A

Completely randomized takes all units and puts them in a hat and randomly chooses treatments, blocked puts them all in different hats first (blocks) and then chooses

93
Q

What is matched pair design?

A

A type of blocking where you match subjects to other “like” subjects MOST OFTEN SEEN WHEN YOU COMPARE A SUBJECT TO ITSELF!! (like pre-post tests)

94
Q

Suppose you are doing a weight loss experiment with 2 diets (A. low carb and B. low fat), and three medications (1. NUTRI LOSS, 2. POUND DROPPER and 3. SLIMMERLY). How many treatment groups would there be?

A

there would be 6: A1, A2, A3, B1, B2, B3

95
Q

Why randomize in an experiment?

A

To reduce confounding variables (and bias).

96
Q

What is the difference between a completely randomized and a randomized block?

A

In a completely randomized experiment, all of the subjects names go into ONE HAT and you pick for treatment groups. In a randomized block design you have more hats (a hat for males, a hat for females etc) and pick for treatments from each.

97
Q

Suppose you sample 150 people randomly from a city to make an inference about the city, and then you sample 150 people randomly from around the country to make an inference about the entire country, which will you be more confident in????

A

It will tell you just as much about both. Same reliability (if sample is representative). Sample size determines confidence. To get more confidence you need a larger sample (not a smaller population)

98
Q

Suppose you are doing a weight loss experiment with 2 diets (A. low carb and B. low fat), and three medications (1. NUTRI LOSS, 2. POUND DROPPER and 3. SLIMMERLY). What is the response variable?

A

weight loss (pounds)

99
Q

What is difference between subject and experimental unit?

A

Humans who are experimented on are commonly called subjects in an experiment. Subjects like dogs, days, plants and anything not human are called Experimental Units

100
Q

4 ingredients: What is “randomization?”

A

You want to randomly assign subjects to treatment groups.

101
Q

What is a factor? give example

A

DIET PLAN would be a factor and levels could be: low carb, low fat, and no diet

102
Q

What is wrong with using voluteers in an experiment?

A

Not much. In an experiment, we are not looking for a sample that is like the population. We just want to see the effectiveness of a treatment. It is fine if the subjects are all similar. In fact it is best sometimes when they are!

103
Q

What “designs” are there for experiments?

A

completely randomized, random block, and matched pair design(type of block)

104
Q

Give example of confounding variable.

A

fertilizer A vs B. If you have two tables in a room with tomato plants and and one table gets A and the other gets B, but later you realize that the table with A was near the windows. You say that SUNLIGHT IS A CONFOUNDING FACTOR in that experiment.

105
Q

Can you stratify in an experiment?

A

NO. stratification is a sampling method, blocking is method used in experiments. They are similar ideas.

106
Q

Give example of randomized block design for a new anxiety med vs placebo with 100 volunteers (60m and 40f)

A

Block by gender. Randomly assign 30m to new and rest placebo. Randomly assign 20w new and rest placebo.

107
Q

How are we using random numbers in experiments vs studies?

A

In a study, we randomly choose subjects to survey from the population as a whole. In an expermint we

108
Q

Give example of a matched pair design study for fuel efficiency

A

Testing fuel efficiency of different gasolines. Subjects use both fuel A for a month and fuel B for a month and compare, based on their driving habits and vehicle, which was more efficient. BE SURE TO RANDOMLY CHOOSE WHICH ONE GOES FIRST FOR EACH SUBJECT.

109
Q

How do we use representative samples in experiments and studies?

A

You don’t need a representative sample in an experiment. You are not making inferences about a population, just about a treatment.

110
Q

When we say “statistics vary” or the “variablility of statistics” are we talking about data from an individual?

A

NO… we are stating that summaries of samples (statistics) will vary from sample to sample. Statistics from one sample will differ from statistics from another sample and they will also differ from the parameters. The distance your statistic is from the parameter is called the ERROR.

111
Q

What do observational studies and experiments have in common?

A

In both, you are making OBSERVATIONS.. recording data… doing statistical analysis…

112
Q

What is the difference between confounding and lurking?

A

Confounding is in experiments, like sunlight confounding a fertilizer experiment. Lurking is when you think hot chocolate causes ski accidents. “lurking”is actually a word not even used in AP STATS.

113
Q

In the fertilizer experiment, how could you plan to eliminate the confounding variable?

A

USING RANDOMIZED BLOCK DESIGN. Make each table a block, and then randomly assign fertilzer A and B to the plants at each table. Compare the fertilizers for table 1, then compare the fertilizers on table 2.

114
Q

What are the differences between the subjects in strata and the subjects in clusters?

A

the “strata” are homogeneous, or have similar traits. The clusters are heterogeneous, or mixed traits.

115
Q

What’s a useful alternative when you can’t run an experiment? What are they useful forms of this, and how do you preform them respectively?

A

An alternative of an experiments could be an observational study.