Presentation is loading. Please wait.

Presentation is loading. Please wait.

16b. Accessing Data: Means in SAS ®. 1 Prerequisites Recommended modules to complete before viewing this module  1. Introduction to the NLTS2 Training.

Similar presentations


Presentation on theme: "16b. Accessing Data: Means in SAS ®. 1 Prerequisites Recommended modules to complete before viewing this module  1. Introduction to the NLTS2 Training."— Presentation transcript:

1 16b. Accessing Data: Means in SAS ®

2 1 Prerequisites Recommended modules to complete before viewing this module  1. Introduction to the NLTS2 Training Modules  2. NLTS2 Study Overview  3. NLTS2 Study Design and Sampling  NLTS2 Data Sources, either 4. Parent and Youth Surveys or 5. School Surveys, Student Assessments, and Transcripts  9. Weighting and Weighted Standard Errors

3 16b. Accessing Data: Means in SAS ® 2 Prerequisites Recommended modules to complete before viewing this module (cont’d)  NLTS2 Documentation 10. Overview 11. Data Dictionaries 12. Quick References  Accessing Data 14b. Files in SAS 15b. Frequencies in SAS

4 16b. Accessing Data: Means in SAS ® 3 Overview  Purpose  Exploring existing data Means Comparative means  Weights  Closing  Important information

5 16b. Accessing Data: Means in SAS ® 4 NLTS2 restricted-use data NLTS2 data are restricted. Data used in these presentations are from a randomly selected subset of the restricted-use NLTS2 data. Results in these presentations cannot be replicated with the NLTS2 data licensed by NCES.

6 16b. Accessing Data: Means in SAS ® 5 Purpose Learn to  Run simple statistical procedures Means  Watch for Missing values n’s Weighted vs. unweighted data

7 16b. Accessing Data: Means in SAS ® 6 Means How to run means Means are run on continuous variables such as  Number of months  Income  Age  Test scores Syntax with options to control printing PROC MEANS data = sasdb.n2w2dirassess mean min max n maxdec=2; /*limits output*/ VAR ndaAP_w ; run ; These results cannot be replicated with full dataset; all output in modules generated with a random subset of the full data.

8 16b. Accessing Data: Means in SAS ® 7 Means These results cannot be replicated with full dataset; all output in modules generated with a random subset of the full data.

9 16b. Accessing Data: Means in SAS ® 8 Means Important: Do not use the standard errors from this procedure.  These data are from a stratified sample, so standard errors are not calculated correctly in this procedure.  Standard errors in this procedure assume a simple random sample, not a complex stratified sample. More about this later. These results cannot be replicated with full dataset; all output in modules generated with a random subset of the full data.

10 16b. Accessing Data: Means in SAS ® 9 Comparative means As with frequencies, comparative means can be run in a single step. The by- (or independent) variable must be categorical. Reminder: Do not include the standard error in statistics. Syntax: Simply add a CLASS statement. PROC MEANS data = sasdb.n2w2dirassess mean min max n maxdec=2 ; CLASS na_age4 ; VAR ndaAP_w ; These results cannot be replicated with full dataset; all output in modules generated with a random subset of the full data.

11 16b. Accessing Data: Means in SAS ® 10 Comparative means These results cannot be replicated with full dataset; all output in modules generated with a random subset of the full data.

12 16b. Accessing Data: Means in SAS ® 11 Means and comparative means: example Means and comparative means  Use the Wave 3 parent/youth interview file.  Run means on np3NbrProbs.  Run comparative means on np3NbrProbs by W3_AgeHdr2005 and by W3_DisHdr2005. These results cannot be replicated with full dataset; all output in modules generated with a random subset of the full data.

13 16b. Accessing Data: Means in SAS ® 12 Means and comparative means: Example These results cannot be replicated with full dataset; all output in modules generated with a random subset of the full data.

14 16b. Accessing Data: Means in SAS ® 13 Weights How to weight data. Running procedures unweighted is useful for exploratory analysis and recommended for becoming familiar with the data.  It is important to review the unweighted n’s. However, unweighted results must never be reported. The procedures we used to calculate means and comparative means can be run with weights.  The weighted means will be correct.  The weighted standard errors will not be correct using these procedures; do not report them. Weighting in SAS requires a WEIGHT statement.  The procedures themselves do not change.  Weights are applied when there is a WEIGHT statement. These results cannot be replicated with full dataset; all output in modules generated with a random subset of the full data.

15 16b. Accessing Data: Means in SAS ® 14 Weights Syntax PROC MEANS data = sasdb.n2w3ParYouth mean min max maxdec=2 ; WEIGHT np3Wt; VAR np3NbrProbs ; run ; To turn the weight off, omit the statement or comment it out. PROC MEANS data = sasdb.n2w3ParYouth mean min max maxdec=2 ; *WEIGHT np3Wt; VAR np3NbrProbs ; run ; These results cannot be replicated with full dataset; all output in modules generated with a random subset of the full data.

16 16b. Accessing Data: Means in SAS ® 15 Weights: Example Weights: Run the earlier examples with a weight.  Run means example weighted with np3Wt. W3 Parent interview weight np3wt np3NbrProbs np3NbrProbs by W3_AgeHdr2005 and by W3_DisHdr2005 These results cannot be replicated with full dataset; all output in modules generated with a random subset of the full data.

17 16b. Accessing Data: Means in SAS ® 16 Weights: Example These results cannot be replicated with full dataset; all output in modules generated with a random subset of the full data.

18 16b. Accessing Data: Means in SAS ® 17 Weights: Example These results cannot be replicated with full dataset; all output in modules generated with a random subset of the full data.

19 16b. Accessing Data: Means in SAS ® 18 Weighted example These results cannot be replicated with full dataset; all output in modules generated with a random subset of the full data.

20 16b. Accessing Data: Means in SAS ® 19 Unweighted example These results cannot be replicated with full dataset; all output in modules generated with a random subset of the full data.

21 16b. Accessing Data: Means in SAS ® 20 Closing Topics discussed in this module  Exploring existing data Means Comparative means  Weights Next module:  17b. Accessing Data: Manipulating Variables in SAS

22 16b. Accessing Data: Means in SAS ® 21 Important information  NLTS2 website contains reports, data tables, and other project-related information http://nlts2.org/http://nlts2.org/  Information about obtaining the NLTS2 database and documentation can be found on the NCES website http://nces.ed.gov/statprog/rudman/http://nces.ed.gov/statprog/rudman/  General information about restricted data licenses can be found on the NCES website http://nces.ed.gov/statprog/instruct.asphttp://nces.ed.gov/statprog/instruct.asp  E-mail address: nlts2@sri.com


Download ppt "16b. Accessing Data: Means in SAS ®. 1 Prerequisites Recommended modules to complete before viewing this module  1. Introduction to the NLTS2 Training."

Similar presentations


Ads by Google