Use value labels to use words in place of numbers.
Use d commonly for Likert scales
In variable view, locate the variable column.
Click the right side of the box you wish to create labels for.
Value is the original number.
Label is the word that you want.
Do not have to be in a specific order.
Go to data view
Click “Value Labels”
Use to remove if we do not want it in our specific analysis.
Used if you want to exclude outliers.
Go to “Data View”
Click “select cases…”
Click “if condition is satisfied”
Next, click “If”
Write formula in box in which you want to KEEP in your analysis, NOT what you want to exclude.
Click “paste” for sytanx
Highlight and click the green “play” button
Cases are excluded. This is apparent by looking at the “data view”, which displays slashes through the cases that have been excluded.
To include cases, go back to “select cases”, and click the “all cases”
This removes the slashes, which indicates that the cases have been included.
Used to sort them in preferred order.
Click “sort cases”
If we want to take a variable and transform it into a different variable.
Click “recode into different variables”
Arrow over variable
When choosing the name, do not include spaces because it will be a new column
Click “old and new values”
For old value, type it in exactly as it is in the data set.
When using a word, check “output variables are strings”
Code scales back to their original state.
Click “recode into diff. variables”
Arrow over variables
Type new column name
Descriptive vs inferential data
Descriptive- gives descriptive without applying to the population
Inferential- tries to obtain an accurate sample to represent the population
Nominal- categorical data
Ordinal – numbers of order but not an equal distance between them
Interval- order of numbers that are equal in distance but do not have an absolute zero
Ratio – order of number that are equal in distance but have an absolute zero
Mean- The average of scores or data
Deviation Score- how far score is away from the mean
Standard deviation – average distance of all scores from the mean sample
Sum of Squares = addition of all squared sums
Variance- shows difference between a sample or population
Transform normally distributed variables into standard normal distribution
Independent Variable (IV)- what is manipulated; either causes or does not cause a change
Dependent Variable (DV)- the variable that will be measured
Operational DV- how DV is measured
Null Hypothesis – The IV will not Change the DV
H0 = X̅1 = X̅2
Alternative Hypothesis- The IV will change the DV- H1 = X̅1 ≠ X̅2
Types of error
-Type 1 – False positive
-Type 2 – False negative
-Alpha Level α- The chance of type 1 error
-.05 and .01 are most common
-Increases the chances of rejecting null
-Sample size increase
-Higher alpha level
-One tail testing
Σ= sum of squares
s = sample
σ = population
α= alpha level or chance of type 1 error