
Operational Definitions
 Describes the research operations that specify the values or categories of a variable.
 The book gave the example of your friend making a cake and it was so good that you want to make it so you ask them for the recipe and they give you just the ingredients (not measurements or steps). The likelihood of you making the cake based off of just that it will probably not taste the same for receiving the full recipe (operational definition) it should taste very similar to their cake.

Indicator
 An indicator consists of a single observable measure, such as a single questionnaire item in a survey
 Indicators provide imperfect representations of concepts for two reasons
 They often contain errors of classification
 They rarely capture all the meaning of a concept

Manipulation operations
Manipulation operations are designed to change the value of a variable

Measurement operations
Measurement operations estimate existing values of variables.

Index/Scale
An index or scale is used in selfreport attitude measurement, to combine all responses in one place.

Reliability
Reliability is concerned with questions of stability and consistency

Target Population
The population to which the researchers would like to generalize his or her results

Sampling frame
 Denotes the set of all cases from which the sample is actually selected
 Not a sample
 It’s the operational definitions of the population that provides that basis for sampling

Sampling error
 The amount that a given sample statistic deviates from the population parameter it estimates
 How much it differs from the known population mean

Standard error
 The statistical measure of the “average” of such errors for an entire sampling distribution
 The larger the sample, the smaller the standard error

Stratified Sampling
 Population is subdivided into two or more mutually exclusive segments, called strata, based on categories of one or a combination of relevant variables.
 Simple random samples then are drawn from each stratum, and these subsamples are joined to form the complete stratified sample

Cluster Sampling
 A sample in stages
 The population is broken down into groups of cases, called “clusters.”
 Clusters consist of natural groupings and draws cases only from samples clusters

Convenience Sampling
Researcher selects a requisite number of cases that are conveniently available

Purposive Sampling
Investigator relies on his or her expert judgement to select units that are “representative” or “typical” of the population.

Quota Sampling
 A form of purposive sampling that bears a superficial resemblance to stratified random sampling
 Divides population into relevant strata such as age, gender, and race
 Once strata are established

Cross sectional designs
data on a sample or "cross section" of respondents chosen to represent a particular target population are gathered at essentially one point in time. There are two variations on the crosssectional design.

Contextual designs
sample enough cases within a particular group or contexts to describe accurately certain characteristics of those contexts

Social network designs
focus on the relationships or connections among social actors (people, orgs, countires) and the transaction flows (processes occuring along the connecting links

