Overview
This lecture covers entering data into SPSS, understanding variable types, coding categorical variables, running frequency analyses, and choosing appropriate statistics and charts for your data.
Entering Data in SPSS
- Add data for each participant in Data View using previously created variables: ID, gender, height, and weight.
- ID is a random, nominal variable used to anonymize participants.
- Gender is a nominal and dichotomous variable, coded as 1 (Male) and 2 (Female).
- Height and weight are quantitative (scale/ratio) variables with fixed intervals and meaningful zeros.
Coding and Labeling Categorical Variables
- Change variable names in Variable View by double-clicking on them.
- Assign value labels for categorical variables (e.g., 1 = Male, 2 = Female) to avoid confusion.
- Toggle between viewing value labels and numeric codes in Data View for clarity.
Managing Data and Missing Values
- Height is measured in inches; weight in pounds.
- Missing data appears as blank or system missing in SPSS.
- Sort data to view ranges and identify missing values.
Frequency Analysis and Output Interpretation
- Use Analyze -> Descriptive Statistics -> Frequencies to generate frequency tables for variables.
- Frequency output includes valid n (sample size with data), missing values, percent, and valid percent.
- Report 'valid percent' for more accurate representations when missing data exists.
Creating Charts and Choosing Visualizations
- Bar charts are appropriate for nominal data like gender.
- Histograms (with optional normal curve) are used for scale variables like height.
- Avoid using histograms for categorical data; the visual will not represent categories correctly.
Obtaining Descriptive Statistics
- Select statistics like mean, standard deviation, minimum, and maximum for scale variables.
- The histogram of height can show the distribution and normality visually.
Comparing Groups
- Use Analyze -> Compare Means -> Means to compare a scale variable (e.g., height) across groups (e.g., gender).
- Gender acts as a quasi-independent variable; height is the dependent variable.
- SPSS outputs group means and standard deviations for comparison.
Key Terms & Definitions
- Nominal Variable — A variable with categories that have no logical order (e.g., gender, ID).
- Dichotomous Variable — A categorical variable with exactly two possible categories.
- Scale/Ratio Variable — A quantitative variable with equal intervals and a meaningful zero (e.g., height).
- Value Labels — Text descriptions assigned to codes for categorical variables.
- Valid n — Number of cases with non-missing data for a variable.
- Frequency Table — A table summarizing the count and percentage of each value in a variable.
- Histogram — A chart showing the distribution of a scale variable.
Action Items / Next Steps
- Practice entering data and assigning value labels in SPSS.
- Run frequency analyses and interpret output tables and charts for your sample data.
- Compare means of scale variables by categories using the Compare Means function.
- Prepare for the next video on descriptive statistics and z-scores.