CMNS201 - Lab 3. SPSS Variables recoding

Transcript

1. Recoding variables SPSS LABORATORY 3
2. 1. Calendar 2. Previous lecture recap 3. Recoding Variables 4. Exercise INDEX
3. Photo: Startup Weekend Hackathon. Nov.2014 …BEFORE WE START Still having problems installing SPSS? ◦ Book an appointment for office hour (Thursday, 12.30 - 1.20) ◦ Tech problem? Email cmnstech@sfu.ca No extensions for technical problems after Lab 3 assignment.
5. Reading break
6. Photo: Startup Weekend Hackathon. Nov.2014 SET UP SPSS Open the SPSS project file we were working on last week. If you do not have a saved copy: ▪ Go to Canvas ◦ Assignments > SPSS Lab 3 - Variables recoding ◦ Download the Week-3.sav file ▪ Open the file on SPSS ◦ Launch SPP ▪ File > Open > Data… ▪ Find and open the Week-3.sav file
7. Photo: Startup Weekend Hackathon. Nov.2014 VARIABLES IN THE MUSIC-1 DATASET 8
8. Photo: Startup Weekend Hackathon. Nov.2014 Scale VARIABLES MEASURE Ordinal Nominal From Ahmed Al-Rawi’s Week 4 slides
9. Photo: Startup Weekend Hackathon. Nov.2014 Scale VARIABLES MEASURE Ordinal Nominal
10. Photo: Startup Weekend Hackathon. Nov.2014 Scale CHANGING LEVEL OF MEASUREMENT Ordinal Nominal
11. Photo: Startup Weekend Hackathon. Nov.2014 CHANGING LEVEL OF MEASUREMENT
12. Photo: Startup Weekend Hackathon. Nov.2014 CHANGING MEASURE
13. Photo: Startup Weekend Hackathon. Nov.2014 CHANGING MEASURE
14. Photo: Startup Weekend Hackathon. Nov.2014 WHY CHANGING LEVEL OF MEASUREMENT? Sometime we do not need the maximum level of detail. In these cases, reducing the measurement level facilitates the management of data and the analysis of results. Examples of measurement-level reductions: • Age. From Scale (x years) to Ordinal ◦ children [0-12 yrs], teens [13-19], young adult [20-29], adult [30-49], seniors [49+] • Income. From Ordinal: ◦ $0 - $4999, $5000 - $9,999, $10,000 - $14,999, $15,000 - $19,999, $20,000 - $24,999, $25,000 - $29,000 to Nominal: ◦ Below poverty line (0 - $14,999), Above poverty line ($15,000 and above)
15. CHANGING MEASUREMENT LEVEL IN SPSS: VARIABLE RECODING
16. FROM SCALE TO NOMINAL • If tempo is less than 100 BPM, then is Slow • If tempo is greater than 101 BPM, then is Fast Scale Nominal
17. FROM SCALE TO ORDINAL • Lento – slow (45–59 bpm) • Larghetto – rather slow and broad (60–65 bpm) • Adagio – slow with great expression (66–75 bpm) • Andante – at a walking pace (76–107 bpm) • Moderato – at a moderate speed (108–119 bpm) • Allegro – fast, quick, and bright (120–155 bpm) • Vivace – lively and fast (156–175 bpm) • Presto – very, very fast (176+ bpm) Scale Ordinal
18. IMPORTANT: ALWAYS CHECK YOUR NEW VARIABLE PROPERTIES
19. Photo: Startup Weekend Hackathon. Nov.2014 IN CLASS EXERCISE Recode the variable Popularity into a new nominal variable names “Popularity_new” • If popularity is below 75, then the new variable value is “Popular” • If popularity is 76 or above, then the new variable value is “Super popular” To begin, click on Transform > Recode into different variable.
20. 1: select the variable to recode 2: type the new variable name and add descriptive label 3: click change 4: click Old and New Values 5: set your range 6: tick the checkbox and define width 15 7: define the new variable value for the range 8: click add and repeat steps 5-7-8 for the second range. 10: click OK 9: once defined all ranges, click Continue
21. Photo: Startup Weekend Hackathon. Nov.2014 IN CLASS EXERCISE • Go back to the Data View. Your new variable will be the last one on the right. • Drag and drop the new variable next to the original Popularity • Sort the original popularity Ascending (right click on the column header > “Sort Ascending”) • Scroll to popularity = 75 to check if the new variable is correctly recoded • Take a screenshot of the dataset showing that the new Popularity variable correctly changes value when old popularity is above 75 • Upload on Canvas
22. Photo: Startup Weekend Hackathon. Nov.2014 EXAMPLE
23. Photo: Startup Weekend Hackathon. Nov.2014 BONUS TIP: CHECK THE NEW VARIABLE PROPERTIES 8 Go to Variable View. Make sure the properties of your new recoded variable are correct (they should be).
24. Photo: Startup Weekend Hackathon. Nov.2014 TO CONCLUDE… 8 1. Save your project. 2. SPSS project files have the .sav extension. Your saved project includes the data (which means, no need to re-import the dataset next time) and all recoded variables.
25. THANK YOU Alberto Lusoli alusoli@sfu.ca Office hour: Thursday, 12.30pm - 1.20pm (please book an appointment in advance via email).