Psychological Statistics Unit 1

Population

Entire set of observations that we are interested in drawing a conclusion in.

Sample

A subset of the population

Parameters

A number that describes a characteristic of a population (mu)

Statistics

A number that describes a characteristic of a sample

Descriptive statistics

Summarizes the characteristics of a data set.

Inferential statistics

Using sampled data to draw a conclusion about a larger data sample or a population.

Sampling error

From sample to sample the results might differ

Variable

A quantity that can change in value

Constant

A fixed value

Independent variable

The variable that is being controlled

Dependent variable

The variable that changes due to the independent variable.

Discrete variable

Does not have a meaningful intermediate point (ex. number of siblings someone has because you cannot have a half sibling)

Continuous variable

Has an infinite number of values between points (ex. a rating scale is continuous)

Dichotomous variable

Only two variables (ex. present vs absent)

Categorical variable (qualitative variable)

A variable that can be stored into groups or categories with the aid of names or labels.

Nominal

Classes or categories (ex. gender, political affiliation, etc.) (numbers reflect categories)

Ordinal

Order or rank (ex. class rank, position in a race)

Interval

An amount with no absolute zero (ex. Degrees Fahrenheit)

Ratio

An amount, this type has an absolute zero

Construct (a constructed concept)

A label that organizes and summarizes the essence of some behavior, object, or event

Operational definition

Specific description of how a construct will be measured or defined.

What are four things that a good operational definition has?

1) Quantifiable

2) Unambiguous

3) Specific

4) Contextual (timeframes, limits, etc.)

Reliability

Is it consistent/stable?

Validity

Is the measure accurate/does it measure what it is supposed to

3 factors to consider in formulating operational definitions

1) Frequency

2) Intensity/magnitude

3) Duration/speed

Correlation

Relationship between two variables and how x varies as y varies.

Regression

Correlation expanded to show predicting y from x

What are four factors that might affect a correlation?

1) Restricted range (underestimate of true relationship)

2) Extreme groups: Overestimate of relationship

3) Extreme scores/gutting the distribution: Drastically affect r

4) Non-linear relationship: Give an underestimate of true relationship

What is r²

EXPLAINED coefficient of determination

Represents the % of variance in y accounted for by variance in x

What is 1 - r²?

UNEXPLAINED coefficient of determination

Variance accounted for by other variables

Predictor variable (x)

Similar to an independent variable, but not necessarily manipulated

Criterion variable (y)

Like a DV. Variable being predicted.

Bivariate regression

Has ONLY one predictor one criterion

Multiple regression

More than one predictor, but only one criterion