STATS lecture 1

voluntary random sampling

A sampling method where the participants choose to be a part of the study / choose to answer a poll (often creates bias due to self-selection)

convenience sampling

A sampling method that samples those who are available and easiest to reach often creates undercoverage and underepresentation.

Simple random sample (SRS)

Each member of the population and every sample of size n has an equally likely chance of being selected for the sample (EX: drawing names from a hat)

Sampling frame

List of items or subjects you wish to sample from (EX: roster of all registered students at SDSU)

Sampling variability

Each sample will select different people and therefore different values for the measured variables (no two samples will be identical)

Stratified random sampling

The sampling frame is divided into non-overlapping groups or strata (ex: age groups, genders that have similar characteristics). A random sample is taken from each stratum, and then these smaller samples are combined to form the entire sample. (EX: Freshman(20) Sophomores(18) n=38))

Cluster sampling

The population is divided into groups called (heterogeneous) clusters. We then randomly select clusters and measure all of the individuals within the selected clusters. (EX: sdsu—> Freshman(all) Sophmore (none) Junior(ALL) Senior(none)

Multistage Random Sample

Combining a variety of sampling methods

Systematic random sample

Interval-based method used for quality control (EX: every five dogs)

sampling Interval formula

I = N/n

sampling interval example

Suppose you want to sample 8 houses from a street of 120 houses. 120/8 = 15(sampling interval). Every 15th house is chosen after a random starting point between 1 and 15 is chosen.

undercoverage

A group is underrepresented / populations left out of the process of choosing a sample.

Nonresponse bias

When an individual chosen for the sample can’t be contacted / refuses to cooperate / participants refuse to answer some questions

Response bias

The behavior of the respondent or of the interviewer influences the outcome of the survey or questionnaire (caused by how the researcher phrases the question)

Randomization

To ensure that we do not impose personal bias in the selection process and use enough subjects in each group to reduce chance variation in the results (treatments randomly assighned to each subject)

Control groups

aka placebo group

replication

To ensure we get the same results repeatedly (not just by chance)

Blocking

Grouping subjects with similar characteristics. All experimental conditions are then administered to each block.

Completely randomized

randomly assigning subjects into treatment groups + measuring an outcome (k = # of treatments)

Matched pairs

Choose pairs of subjects that are as closely matched as possible in characteristics that may affect the outcome. Then randomly assign them to treatment groups. Two subjects per group. Each subject is measured before + after. (EX: one subject tries two pairs of Coke vs pepsi)

Block design

Generalized version of the matched pairs that allows for comparisons of more than 2 treatments. 3(+) subjects per group/block.

observational study

Observes individuals and measures variables of interest but does not attempt to influence the responses (observe + record)

retrospective study

study that looks backwards in time (studying a disease that takes a while to appear)

prospective study

study that looks forward in time (taking a group of subjects and following them over a long period of time)

experiment

Researchers randomly apply treatment, then observe its effects on the subject

comparative treatment

compares the effects of different treatments, one of which may be really no treatment or the control group—> (they take a placebo, not an actual treatment)

experimental units

individuals being studied in the expirement (living or nonliving)

factors

The independent variables that affect the dependent variables

treatment

A specific condition applied to the subjects (a combination of the factors; # of treatments (x) = multiply (Y) levels of the factors

placebo

dummy treatment (minimizes false effects in an experiment)

blinding