STAT 110 EXAM 1 Review

What are Individuals?

The objects described by a set of data.

What is a Census?

A sample survey that attempts to include the entire population in its sample.

What is a Matched-Pairs Design?

A special case of a randomized block design. It can be used when the experiment has only 2 treatment conditions and subjects can be grouped into pairs based on some blocking variable.

What is a Block Design?

The random assignment of subjects to treatments is carried out separately with in each block.

What are Variables?

Characteristics of an individual.

Qualitative/Categorical Variables:

- Categories of data

- Non-numeric data

EXAMPLE: eye color, gender, SSN, area code, class

Quantitative Variables:

Numeric data

EXAMPLE: height, weight, age, number of siblings, number of hours enrolled

Observational Studies

Do not attempt to influence the response. "Look but don't touch." Passive data collection.

Experiments

Attempt to influence the response by deliberately imposing a treatment on the subjects. Active data production.

A researcher finds 500 adults over 40 who regularly eat oatmeal. She matches each with a similar adult who does not regularly eat oatmeal. She measures the bad cholesterol (LDL) for each adult and compares them.

Observational Study.

Another researcher finds 1,000 adults over 40 who do not regularly eat oatmeal and are willing to participate in a study. She assigns 500 of these to a diet that includes a daily breakfast of oatmeal. The other 500 continue their usual habits. After 6 months, she compares changes in LDL levels.

Experiment.

What is the population in a statistical study?

Contains all of the individuals of interest.

What is a sample?

Contains a subset of the population.

What is a parameter?

A fixed number that describes a population.

(usually we don't know the true value)

What is a statistic?

A number that describes a sample.

(value is known for a given sample)

What is a Simple Random Sample?

A sample chosen in such a way that every set of n individuals has an equal chance of being chosen.

What is a Biased Sample?

A statistical sample of a population in which some members of the population are less likely to be included than others.

What is a Convenience Sample?

It is sampling which involves the sample being drawn from that part of the population which is close to hand.

What is a Voluntary Sample?

This sample chooses themselves by responding to general appeal.

Data is gathered by asking people to go to a website and answer questions online.

Voluntary response

Interviewers choose people on the street to interview.

Convenience sample

What is a Stratified Random Sampling?

- Divide sampling frame into groups of individuals.

- Take simple random sample in each stratum.

What is a Probability Sample?

A sample chosen by chance.

What is a Cluster Sample?

You survey everyone in each cluster or organization you chose to survey.

We can control the MoE by picking the right sample size. How do we keep a sample from being biased?

Using a simple random sample

If you increase the sample size while keeping the level of confidence the same, the MoE will?

Decrease

A group of sociology students want to conduct a survey to learn more about USC students' beliefs regarding social media. The students distribute the survey to their classmates because the members of the class are easy to access and the researchers are likely to get a high response rate. What type of sampling is this?

Convenience sampling

What is Simpson's Paradox?

An apparent paradox in which a trend present in different groups is reversed when the groups are combined.

During a particular summer, an experiment was conducted to find out the preference between two types of beverages: soda and lemonade. 2,700 people were randomly polled and their preference was noted. The results showed that more men than women preferred lemonade. Upon investigation, it was discovered that the data was drawn from two locations: city and rural. In each location, the gender and the choice of drinks were collected. When the data was split out by location, more women than men actually preferred lemonade. What is this an example of?

Simpson's Paradox

A 2003 survey by the Pew Research Center estimated that 46% of Republicans said they like to register their opinions on online surveys, compared with only 28% of Democrats. What are some of the potential lurking variables?

Age, gender, income

If you wanted to select a sample of size 5 from a population of size 275, how many digits would be in each unique label?

3

(000-999)

What is Bias?

- When your sample statistic either always overestimates or always underestimates the true values of the population parameter.

- A measurement process has bias if it always either overstates or understates the true value of the property it measures.

What is Variability?

Describes how spread out the values of the sample statistic are in repeated samples.

What is Sampling Errors?

Errors caused by the act of taking a sample

What is a sampling frame?

When we start with a list of the entire population.

What is a Response Error?

Occurs when a subject gives an incorrect response

What is a non-response error?

The failure to obtain data from an individual selected for a sample

What is a non-sampling error?

Errors that are not related to the act of selecting a sample from the population

What is a processing error?

Mistakes in mechanical tasks such as doing arithmetic or entering responses into a computer.

What is a non-response rate?

The percentage of people that did not respond or return their surveys

How do you calculate the MoE at 95% confidence?

MoE= 1/√n

Which is the correct confidence statement?

We are 95% confident that between 62.43% and 93.67% of all employed adult women are in favor of government funding for daycare.

How do you reduce the MoE by half?

To reduce the MoE by half, you have to quadruple the sample size. So multiple the sample size by 4.

For a given sample size n, what happens to the MoE as we increase the confidence level?

The MoE increases as we increase the confidence level

For a given confidence level, what happens to the MoE as we increase the sample size?

The MoE decreases as we increase the sample size

What does MoE only include?

Random sampling errors

Suppose a farmer wishes to work out the average milk yield of each cow type in his herd which consists of Ayrshire, Friesian, Galloway and Jersey cows. He divides up his herd into the four sub-groups and takes random samples from each of them.

Stratified random sampling

Suppose that the Department of Agriculture wishes to investigate the use of pesticides by farmers in England. The farmers were grouped according to the county in which their farm was located. A sample of these counties was then chosen at random and all farmers in the selected counties were included in the sample.

Cluster sampling

What is Phase I of Clinical Trial Phases?

Evaluate safety, determine dosage, identify side effects

What is Phase II of Clinical Trial Phases?

Evaluate effectiveness and safety.

What is Phase III of Clinical Trial Phases?

Confirm effectiveness and monitor side effects; compare to commonly used treatments.

What is Phase IV of Clinical Trial Phases?

Studies conducted after FDA approval and treatment is on the market; evaluate long-term effects.

Police trainees were seated in a darkened room facing a projector screen. Ten different license plates were projected on the screen, one at a time, for 5 seconds each, separated by 15-second intervals. After the last 15-second interval, the lights were turned on and the police trainees were asked to write down as many of the 10 license plate numbers as possible, in any order at all. A random sample of 15 trainees who took this test was then given a week-long memory training course. They were then retested. What type of experimental design is this?

Matched Pairs (before-and-after)

Twelve overweight men are used in a study to test three treatments for weight reduction. It is known that heavier patients may show greater weight reduction, so the men are divided into four groups based on initial weight before the study begins. What type of experimental design is this?

Block Design

What is the Declaration of Helsinki?

States that while there is always a need for research, the subject's welfare must always take precedence over the interests of science and society.

What is the Declaration of Geneva?

A declaration of physicians' dedication to the humanitarian goals of medicine, a declaration that was especially important in view of the medical crimes which had just been committed in Nazi Germany.

(Intended as a revision of the Oath of Hippocrates.)

What are the 3 Elements of Basic Data Ethics?

1. Institutional Review Board

2. Informed Consent

3. Confidentiality

What does Confidential mean?

That the researchers have identifying information for the participant, but that information is not released in the study.

What does Anonymous mean?

That the researchers do not have identifying information for the participants.

What is Valid Measure?

A variable is this if it is relevant or appropriate as a representation of that property.

What is Reliability?

The repeatability of your measurement. If an instrument measures the same way each time it is used under the same condition with the same subjects it's said to be reliable.

Why is it sometimes better to use a rate instead of a count?

Denominators might be different.

What is Predictive Validity?

A measurement of a property has this if it can be used to predict success on tasks that are related to the property measured.

What is Random Error?

A measurement process has this if repeated measurements on the same individual give different results.

If a random error is small, what do we say?

The measurement is reliable

What is the Measured Weight?

true weight + bias + random error

How do we improve the reliability of our measurements?

Use averages

How do we improve the bias in our measurement?

Use a better instrument

What is a confounding/lurking variable?

A variable that has an important effect on the relationship between explanatory and response variables, but is not one of the explanatory variables being studied.

What is a Placebo?

A dummy treatment with no active ingredients

What is the Placebo Effect?

The patients favorable response to a dummy treatment.

What is a Double-Blind Experiment?

Neither the individuals nor the researchers know who belongs to the control group and the experimental group.

What is the treatment group?

Any specific experimental condition applied to the subjects.

What are the subjects?

The individuals studied in an experiment.

What is the control group?

One group and it receives a placebo or already proven treatment.

What is the Explanatory Variable?

A variable that we think explains or causes changes in the response variable.

What is the Response Variable?

A variable that measures an outcome or result of a study.

A MoE of +-2% means that?

95% of those samples would produce a statistic that is within +-2% of the true population parameter.