Research Methods I Flashcards

Flashcards from Research Methods I lecture notes.

Psychological Test

A systematic procedure using samples of behavior to evaluate cognitive/affective functioning against a standard or norm.

Scaling

The process of constructing scales for psychological tests (e.g., Thurstone, Likert, Semantic differential, Guttman).

Statistics

A branch of mathematics dealing with the collection, analysis, interpretation, and presentation of masses of numerical data.

Measurement

The use of devices or rules for assigning numbers to objects or events.

Nominal Level of Measurement

Values represent categories (e.g., sex: 0=male, 1=female).

Ordinal Level of Measurement

Higher values indicate more of something, but distances between values are not meaningful (e.g., education level).

Interval Level of Measurement

Distances between values are meaningful, but there is no true zero point (e.g., temperature).

Ratio Level of Measurement

Possesses all qualities of nominal, ordinal, and interval scales, with a true zero point (all arithmetic operations are possible).

Descriptive Statistics

Quantitative description/summary of acquired quantitative data.

Inferential Statistics

Measures derived from a sample used to estimate population values.

Mode

Most frequently occurring value in a dataset.

Median

Value that divides the rank-ordered distribution of values into two equal halves (50% above, 50% below).

Mean

Sum of all values divided by the number of values (Σ).

Measures of Variability

Measures that indicate the dispersion or scatter within a set of data.

Range

Difference between the highest and lowest values; sensitive to outliers.

Semi-Interquartile Range

(Q3 – Q1)/2; where Q3 is the third quartile (75th percentile) and Q1 is the first quartile (25th percentile).

Variance

(∑(X-M)2)/N; where X is each value, M is the mean, and N is the number of values.

Standard Deviation

Square root of the variance; a measure of the spread of scores around the mean.

Thurstone Scaling

Creating an item pool, judging the items, and ranking them based on the median and interquartile distance.

Likert Scale

Item scores are not dichotomous, unlike in Thurstone scaling.

Z-score

Indicates the location of an obtained value in a distribution, with a mean of 0 and standard deviation of 1.