Quantitative Research Skills & SPSS Analysis Flashcards

Vocabulary flashcards generated from lecture notes covering SPSS file types, variable levels, univariate/bivariate operations, inferential tests, factor analysis, and index construction.

Data file (*.sav)

An SPSS file type containing Data View (which carries raw data) and Variable View (which provides variable information).

Syntax file (*.sps)

A programming file unique to SPSS that can be used as an alternative to drop-down menus for data manipulation and statistical analyses.

Output file (*.spo)

An SPSS file type that displays the results of all statistical analyses requested from the data file.

Nominal Variable

A variable assigned artificial numeric values where numbers indicate differences only, including all dichotomous variables.

Ordinal Variable

A variable where artificial numeric values are assigned to response categories based on ranked or ordered responses.

Scale Variable

A variable carrying true numeric values, also referred to as discrete, continuous, or quantitative variables.

Univariate Analysis

The statistical analysis (descriptive or inferential) of a single variable at a time.

Histogram

The appropriate visualization method for a single scale variable, featuring bars in contact with one another to reflect continuous response categories.

Standard Deviation

A measure of dispersion used to quantify the amount of variation or spread of data values around the sample mean.

Positively Skewed Distribution

A distribution shape characterized by a mean that is greater (larger) than the median.

Negatively Skewed Distribution

A distribution shape characterized by a mean that is smaller than the median.

Recode into Same Variables

An SPSS recoding option that directly changes and overwrites existing variable data.

Recode into Different Variables

An SPSS recoding option that creates new variables from existing data without altering original variables.

Series Mean Procedure

A method to handle missing values by replacing non-response categories with the mean score of valid responses.

Computing Variables

The creation of a new variable based on a specific mathematical or numerical expression of one or more existing variables.

Splitting File

An SPSS procedure to generate separate output files for different subgroups, best utilized when working with 3 variables.

Selecting Cases

An SPSS function used to generate output for a specific single subgroup or response category, best utilized when working with 4 variables.

Dependent Variable (DV)

The focus of study that the researcher is trying to explain; placed in the row box during crosstabulation.

Independent Variable (IV)

The impacting variable that influences or impacts the dependent variable; placed in the column box during crosstabulation.

Cross-tabulation (Crosstabs)

A descriptive bivariate analysis method used to explore differences between scores on two categorical variables.

Chi-squared Test of Independence

An inferential statistic testing whether two categorical variables are independent, without measuring relationship direction or strength.

Phi Coefficient

A measure of association and effect size used specifically for a $2 \times 2$ crosstabulation table.

Cramer's V

A measure of association and effect size used for crosstabulation tables larger than $2 \times 2$ (e.g., $3 \times 4$).

Compare Means (t-test)

A bivariate analysis method used to compare the mean of a scale variable across different groups defined by a categorical variable.

Analysis of Variance (ANOVA)

A statistical technique used to test whether the means of three or more groups are significantly different from each other.

Eta Squared (Eta²)

A measure of association representing the proportion of variance in a scale dependent variable accounted for by a categorical independent variable.

Pearson's Correlation Coefficient (r)

A statistic measuring the strength and direction of the linear relationship between two scale variables, ranging from $-1.0$ to $+1.0$.

Factor Analysis

A statistical method used to describe variability among observed correlated variables in terms of a lower number of unobserved factors.

Eigenvalue

The proportion of total variance explained by each factor in factor analysis; factors must have an eigenvalue greater than $1$.

Factor Loading

The correlation of a variable with a factor; coefficients smaller than $0.30$ are discarded.

Varimax Rotation

An orthogonal rotation method in factor analysis producing loadings near high or low extremes to easily match variables with a single factor.

Cronbach's Alpha

A measure of internal consistency assessing how well a set of variables measures a single, unidimensional latent construct.

Index Construction

The process of combining multiple variables into a single numerical score or summary combination.