SPSS Research Tips

The dependent variables represent the output or outcome whose variation is being studied.
The independent variables represent inputs or causes, i.e. potential reasons for variation.

Statistical/Mathematical models test or explain the effects that the independent variables have on the
dependent variables. (wikipedia)

Variable

Dependent Independent

Group

Nature of variable:
A variable can be continuous or discrete.

A variable can be continuous choose ordinal if its point value is important i.e. 5.9333, 87.25, or 3.64.
A variable can be discrete if it is exact value i.e. Male, Female.

Computation or data treatment

Proper way is to codify your data first, by pressing Alt + E + E keys.

T-Test Conditions
1. Two variables (dependent, independent).
2. One variable should be continuous (decimal point), one is discrete (exact value: Male, Female).
3. Discrete values should be dichotomous (2 values).

Analyze > Compare Means > Grouping variable (Gender)

Test variable (Total Awareness)
Define groups: 1, 2 (this is the codify version of Male and Female)
Look for significance (Sig) on the computer generated result

Below 0.05 value means has significant.

Higher than 0.05 values means no significant (walang pinagkaiba)

Ideal would be 50 per group (50 male, 50 female; 50 with intervention, 50 without)

Use for ANNOVA more than two groups

1 way ANNOVA conditions

1. Two variables.
2. One variable should be continuous (decimal point), one is discrete (exact value: Male, Female).
3. Discrete variable should have at least three values. (Single, Married, Widowed)

Dependent (continuous) pwede marami: Total Awareness

Factor: Civil Status

2 way ANNOVA conditions

1. Should have at least 3 variables
2. One variable should be continuous dependent (decimal point), two discrete independent or
contributor (wealth, educational attainment of parent).

Analyze > General Linear Model > Univariate

Example:
Factor: Educational Attainment, Employment Status
Dependent: Total Awareness (Level)

Pearson Condition
If the correlation of two independent variables (continuous)

Correlation is a statistical technique that is used to measure and describe the STRENGTH and DIRECTION
of the relationship between two variables.

Correlation requires two scores from the SAME individuals. These scores are normally identified as X and
Y. The pairs of scores can be listed in a table or presented in a scatterplot. Usually the two variables are
observed, not manipulated.