Check Tabs on Phone Check All Components Again if Time Ask People to Look at Paper

Trouble Argument

Some universities in the United States require that freshmen alive in the on-campus dormitories during their start yr, with exceptions for students whose families live within a sure radius of campus. That is, sure freshmen whose families live close plenty to campus are permitted to live off-campus. After completing their outset or 2nd year of school, students living in the dorms may choose to move into an off-campus apartment. How prevalent is this pattern?

In the sample dataset, there are several variables relating to this question:

• Rank - Class rank (Freshmen, Sophomore, Inferior, Senior)
  • RankUpperUnder - Class rank recoded into Underclassman/Upperclassman (come across the Recode into Unlike Variables tutorial)
• LiveOnCampus - Exercise you live on campus? (Aye/No)
• State - Are you an in-state or out-of-land student? (In State, Out of state)
  • State_Residency - Land residency, converted from cord to numeric so that missing values are correctly identified (Run across the Automated Recode tutorial)

Allow's utilize different aspects of the Crosstabs procedure to investigate the relationship between class rank and living on campus.

Part one - Elementary Crosstabs

Using the sample information, let's make crosstab of the variables Rank and LiveOnCampus. Let the row variable be Rank, and the column variable exist LiveOnCampus.

Running the Procedure

Using the Crosstabs Dialog Window

1. Open up the Crosstabs window (Analyze > Descriptive Statistics > Crosstabs).
2. Select Rank every bit the row variable, and LiveOnCampus as the column variable.
3. Click OK.

Using Syntax

            CROSSTABS   /TABLES=Rank BY LiveOnCampus   /FORMAT=AVALUE TABLES   /CELLS=COUNT   /COUNT ROUND CELL.          

Output

The Instance Processing Summary tells us what proportion of the observations had nonmissing values for both Rank and LiveOnCampus. In this sample, there were 47 cases that had a missing value for Rank, LiveOnCampus, or for both Rank and LiveOnCampus.

The 2nd table (here, Class Rank * Exercise y'all live on campus? Crosstabulation) contains the crosstab. We can chop-chop notice data about the interaction of these two variables:

• Many more freshmen lived on-campus (100) than off-campus (37)
• About an equal number of sophomores lived off-campus (42) versus on-campus (48)
• Far more juniors lived off-campus (xc) than on-campus (8)
• Merely one (1) senior lived on campus; the rest lived off-campus (62)

Note the margins of the crosstab (i.due east., the "total" row and column) give us the same information that nosotros would get from frequency tables of Rank and LiveOnCampus, respectively:

• The sample had 137 freshmen, 90 sophomores, 98 juniors, and 63 seniors
• There were 231 individuals who lived off-campus, and 157 individuals lived on-campus

Part ii - Row, column, and full percentages

Permit's build on the table shown in Example 1 by adding row, column, and full percentages. For simplicity'due south sake, let'south switch out the variable Rank (which has four categories) with the variable RankUpperUnder (which has two categories).

Running the Procedure

Using the Crosstabs Dialog Window

1. Reopen the Crosstabs window (Analyze > Descriptive Statistics > Crosstabs).
2. In the Row box, supplant variable Rank with RankUpperUnder.
3. Click Cells. In the Percentages area, check off Row, Column, and Full percentages. (In the following examples, we will exist showing each of these 1 at a time for ease of reading.) Click Go along.
4. Click OK to run.

Using Syntax

            CROSSTABS   /TABLES=RankUpperUnder BY LiveOnCampus   /FORMAT=AVALUE TABLES   /CELLS=COUNT ROW COLUMN Full   /COUNT ROUND Cell.          

Output

Row percents

If the row variable is RankUpperUnder and the column variable is LiveOnCampus, so the row percentages volition tell usa what percentage of the upperclassmen or what percentage of the underclassmen live on campus. That is, variable RankUpperUnder will determine the denominator of the pct computations.

• The proportion of underclassmen who live off campus is 34.8%, or 79/227.
• The proportion of underclassmen who live on campus is 65.2%, or 148/226.
• The proportion of upperclassmen who live off campus is 94.4%, or 152/161.
• The proportion of upperclassmen who live on campus is v.6%, or 9/161.

Column percents

If the row variable is RankUpperUnder and the cavalcade variable is LiveOnCampus, then the column percentages volition tell us what percentage of the individuals who alive on campus are upper or underclassmen. That is, variable LiveOnCampus will determine the denominator of the percentage computations.

• The proportion of individuals living off campus who are underclassmen is 34.2%, or 79/231.
• The proportion of individuals living off campus who are upperclassmen is 65.viii%, or 152/231.
• The proportion of individuals living on campus who are underclassmen is 94.3%, or 148/157.
• The proportion of individuals living on campus who are upperclassmen is five.7%, or nine/157.

Total percents

If the row variable is RankUpperUnder and the column variable is LiveOnCampus, then the total percentage tells the states what proportion of the total is within each combination of RankUpperUnder and LiveOnCampus. That is, the overall table size determines the denominator of the percentage computations.

• Underclassmen living off campus make up 20.4% of the sample (79/388).
• Underclassmen living on campus make upwardly 38.one% of the sample (148/388).
• Upperclassmen living off campus make upwards 39.ii% of the sample (152/388).
• Upperclassmen living on campus make upwards 2.iii% of the sample (9/388).

Part 3 - Crosstabs with Layer Variable

Let'due south modify our assay slightly by taking into account the students' state of residence (in-country or out-of-state). Here, we will exist working with three categorical variables: RankUpperUnder, LiveOnCampus, and State_Residency.

In this case, we want to create a crosstab of RankUpperUnder by LiveOnCampus, with variable State_Residency acting as a strata, or layer variable.

Running the Procedure

Using the Crosstabs Dialog Window

1. Open the Crosstabs dialog (Analyze > Descriptive Statistics > Crosstabs).
2. Select RankUpperUnder equally the row variable, and LiveOnCampus as the column variable.
3. Select State_Residency every bit the layer variable.
4. You may want to go dorsum to the Cells options and turn off the row, column, and total percentages if you lot have only run the previous instance.
5. Click OK.

Syntax

            CROSSTABS   /TABLES=RankUpperUnder BY LiveOnCampus By State_Residency   /FORMAT=AVALUE TABLES   /CELLS=COUNT   /COUNT ROUND Cell.          

Output

Once again, the Crosstabs output includes the boxes Case Processing Summary and the crosstabulation itself.

Discover that after including the layer variable State Residency, the number of valid cases we have to work with has dropped from 388 to 367. This is considering the crosstab requires nonmissing values for all 3 variables: row, cavalcade, and layer.

The layered crosstab shows the individual Rank past Campus tables within each level of State Residency. Some observations we can describe from this table include:

• A slightly higher proportion of out-of-state underclassmen live on campus (30/43) than practise in-state underclassmen (110/168).
• In that location were about equal numbers of out-of-country upper and underclassmen; for in-country students, the underclassmen outnumbered the upperclassmen.
• Of the nine upperclassmen living on-campus, but two were from out of country.

fitzgeraldnortur54.blogspot.com

Source: https://libguides.library.kent.edu/SPSS/Crosstabs

Share this post