Reference no: EM132309309

Tasks (use syntax for all the steps):

1. Create a new syntax file, specify the working directory, and save the syntax file to the folder you specified.

2. Read the student level data, select students from the United States, and save as a new data set with the name "PISA2015_StudentUS.sav".

How many students in the U.S. participated PISA in 2015?

3. Randomly draw 20% of the U.S. students from the data set you obtained from the previous task. Save the new dataset to the folder you specified with the name "PISA2015_StudentUS_Sample.sav", and use it for the following tasks.

What is the sample size of the new data set?

4. Merge the two data sets (PISA2015_StudentUS_Sample.sav; PISA2015_School.sav), and save the merged the data set with the namePISA2015_MergedSample_US.sav.

Note: Use "CNTSCHID" as the matching variable. Make sure it is sorted before merging. And the school data set does not contribute to any new cases.

Hint: If you are using SPSS V26, change the syntax "/FILE=" to "/TABLE=".

5. There are too many variables in the merged data set and you will only use a small number of them for your project. Save the merge sample data as a new data set that contains the following variables, only. Name the new data set with "PISA2015_MergedSample_US_HW1.sav".

Selected variables:

CNTSTUID
ST004D01T
ST034Q01TA
ST034Q02TA
ST034Q03TA
ST034Q04TA
ST034Q05TA
ST034Q06TA
ST094Q01NA
ST094Q02NA
ST094Q03NA
ST094Q04NA
ST094Q05NA
PV1SCIE
SCHSIZE
CLSIZE
STRATIO
SCHLTYPE

[Use PISA2015_MergedSample_US_HW1.sav for tasks 6-9. Do not forget to save all the changes.]

6. Recode the variable "ST004D01T" to a new variable "Female" with the new coding (1=Female, 0=Male, all other values = system missing). [Make sure the new variable has label, values, etc.]

7. You find that PISA used six questions (ST034Q01TA to ST034Q06TA) to collect data about students' sense of school belong. Create a new variable with the name "SchSense" so that you can use it as a proxy of the construct of school belonging.

a. Recode the variables that need to be reverse-coded (into different variables).

b. Obtain the new variable by computing the average scores over all selected variables.

8. Create a new variable with the name "LikeScience" by computing the total score out of the five related variables (ST094Q01NA to ST094Q05NA).

9. Recode the variable "SCHSIZE" into a new variable "SchSizeCat" by categorizing the school size values into the following four categories:
Values:

1 = School size ≤ 100

2 = 100 < School size ≤ 1000

3 = 1000 < School size ≤ 2000

4 = 2000 < School size ≤ 3000

10. Submit all the related files, including the syntax file, the output file, and all the data sets you saved.

Data Sets:

PISA student level data: PISA2015_Student.sav;

PISA school level data: PISA2015_School.sav

Attachment:- Data Set Details.rar