BookmarkSubscribeRSS Feed

[예제로 배우는 SAS] 9-1.Counting Frequencies

Started ‎06-11-2020 by
Modified ‎06-11-2020 by
Views 215

1.PNG

 

안녕하세요. MYSAS입니다.

 금주는 빈도수 계산에 대해서 알아보도록 하겠습니다.

 

 

 

목  차

  1. Introduction
  2. Counting Frequencies
  3. Selecting Variables for PROC FREQ
  4. Using Formats to Label the Output

 

 

 

1. Introduction

  PROC FREQ는 문자형 및 숫자형 변수를 셀 때 사용합니다. 물론 어떤 테이블이든지 사용이 가능하구요. 덧부텽서, PROC FREQ를 이용하여 횟수와 퍼센트를 포함한 테이블을 만들어낼 수 있습니다. 통계학을 하시는 분은 카이 스퀘어, 확률계산, 상대적 리스크 계산할 때 유용하게 사용할 수 있겠죠?  

 

 

 

  1. Counting Frequencies

일반적인 사용방법은 이렇습니다

 

PROC FREQ DATA = 데이터 셋 명;

RUN

 

다음과 같은 데이터 셋이 있다고 가정합시다.

 

 

The SAS System                        09:33 Friday, August 5, 2011   3

 

ID    GENDER             AGE           QUES1           QUES2            QUE3

 

1      F                 22               1               2               2

2      M                 31               2               3               1

3      F                 26               5               5               5

4      F                 42               2               1               4

5      M                 37               3               4               1

6      M                 55               4               5               3

7      M                 63               2               3               4

 

 

Proc freq data=mysas.survey;

Run;

 

실행하면 다음과 같은 output이 생성됩니다.

 

 

 

                                                     The FREQ Procedure

 

                                                                  Cumulative    Cumulative

                                   ID    Frequency     Percent     Frequency      Percent

                                   -------------------------------------------------------

                                    1           1       14.29             1        14.29

                                    2           1       14.29             2        28.57

                                    3           1       14.29             3        42.86

                                    4           1       14.29             4        57.14

                                    5           1       14.29             5        71.43

                                    6           1       14.29             6        85.71

                                    7                 14.29             7       100.00

 

 

                                                                    Cumulative    Cumulative

                                 GENDER    Frequency     Percent     Frequency      Percent

                                 -----------------------------------------------------------

                                 F                3       42.86             3        42.86

                                 M                4       57.14             7       100.00

 

 

                                                                  Cumulative    Cumulative

                                  AGE    Frequency     Percent     Frequency      Percent

                                  --------------------------------------------------------

                                   22           1       14.29             1        14.29

                                   26           1       14.29             2        28.57

                                   31           1       14.29             3        42.86

                                   37           1       14.29             4        57.14

                                   42           1       14.29             5        71.43

                                   55           1       14.29             6        85.71

                                   63           1       14.29             7       100.00

 

 

                                                                   Cumulative    Cumulative

                                 QUES1    Frequency     Percent     Frequency      Percent

                                 ----------------------------------------------------------

                                     1           1       14.29             1        14.29

                                     2           3       42.86             4        57.14

                                     3           1       14.29             5        71.43

                                     4           1       14.29             6        85.71

                                     5           1       14.29             7       100.00

 

 

                                                                   Cumulative    Cumulative

                                 QUES2    Frequency     Percent     Frequency      Percent

                                 ----------------------------------------------------------

                                     1           1       14.29             1        14.29

                                     2           1       14.29             2        28.57

                                     3           2       28.57             4        57.14

                                     4           1       14.29             5        71.43

                                     5           2       28.57             7       100.00

 

 

  

                                                     The FREQ Procedure

 

                                                                   Cumulative    Cumulative

                                  QUE3    Frequency     Percent     Frequency      Percent

                                  ---------------------------------------------------------

                                     1           2       28.57             2        28.57

                                     2           1       14.29             3        42.86

                                     3           1       14.29             4        57.14

                                     4           2       28.57             6        85.71

                                     5           1       14.29             7       100.00

 

 

 output과 같이 각 변수별로 빈도수, 확률 및 누적 확률 등 빈도수에 관련한 모든 자료가 전부다 출력됩니다.

 

 

 

  1. Selcting Variables for PROC FREQ

  위에 코딩은 모든 변수를 포함하는 빈도표를 만들지만

 여기에서 TABLE문을 같이 쓴다면 선택하고자 하는 변수만 표시할 수 있습니다. 일반적인 사용법은 이렇습니다-

 

PROC FREQ DATA = 데이터 셋 명;

          TABLES 변수명 (/OPTION);

RUN;

 

 

다음 코딩을 실행해보겠습니다.

 

 

 

Proc freq data = mysas.survey;

          Tables gender ques1-ques2 / nocum

run;

 

 

이 코딩의 의미는 자료 중에 gender, ques1, ques2라는 변수만 선택을 하겠다는 뜻이고 nocum이라는 옵션을 이용하여 누적확률은 구하지 않겠다는 뜻입니다.

 

그럼 다음과 같은 결과물이 나옵니다.

 

 

 

  

                                                     The FREQ Procedure

 

                                               GENDER    Frequency     Percent

                                               -------------------------------

                                               F                3       42.86

                                               M                4       57.14

 

 

                                               QUES1    Frequency     Percent

                                               ------------------------------

                                                   1           1       14.29

                                                   2           3       42.86

                                                   3           1       14.29

                                                   4           1       14.29

                                                   5           1       14.29

 

 

                                               QUES2    Frequency     Percent

                                               ------------------------------

                                                   1           1       14.29

                                                   2           1       14.29

                                                   3           2       28.57

                                                   4           1       14.29

                                                   5           2       28.57

 

이외에도 옵션 중에 NOPERCENT옵션은 말 그대로 퍼센트를 구하지 않겠다는 옵션입니다. 

 

 

 

  1. Using Formats to Label the Outputep

  F가 female을, M이 male을 의미한다는 것은 쉽게 알 수 있습니다.

 ques 변수들의 숫자들이 무엇을 의미하는지 나타내야 할 필요가 있는데

 이때 format을 직접 작성하여 적용시키면 간편하답니다.

 

proc format;

      value $gender

            'F' = 'Female'

            'M'='Male';

      value likert

            1 = 'Strongly disagree'

            2 = 'Disagree'

            3 = 'No opinion'

            4 = 'Agree'

            5 = 'Strongly Agree'

run;

 

 

 

이렇게 포맷을 생성한 

다음과 같은 코딩으로 적용을 시킵니다.

 

다음과 같은 결과물을 확인 할 수 있습니다.

 

The SAS System                        09:33 Friday, August 5, 2011  16

 

                                                     The FREQ Procedure

 

                                               Gender    Frequency     Percent

                                               -------------------------------

                                               Female           3       42.86

                                               Male             4       57.14

 

 

                                         ques1                 Frequency     Percent

                                         -------------------------------------------

                                         Strongly disagree          1       14.29

                                         Disagree                   3       42.86

                                         No opinion                 1       14.29

                                         Agree                      1       14.29

                                         Strongly Agree run         1       14.29

 

 

                                         ques2                 Frequency     Percent

                                         -------------------------------------------

                                         Strongly disagree          1       14.29

                                         Disagree                   1       14.29

                                         No opinion                 2       28.57

                                         Agree                      1       14.29

                                         Strongly Agree run         2       28.57

 

 

                                         ques3                 Frequency     Percent

                                         -------------------------------------------

                                         Strongly disagree          2       28.57

                                         Disagree                   1       14.29

                                         No opinion                 1       14.29

                                         Agree                      2       28.57

                                         Strongly Agree run         1       14.29

 

 

 

수고하셨습니다. 2부는 다음 시간에 올려드리겠습니다.^^ 즐거운 한주 보내세요~

 

본 자료의 저작권은 sas에 있습니다

Version history
Last update:
‎06-11-2020 09:37 PM
Updated by:
Contributors

sas-innovate-wordmark-2025-midnight.png

Register Today!

Join us for SAS Innovate 2025, our biggest and most exciting global event of the year, in Orlando, FL, from May 6-9. Sign up by March 14 for just $795.


Register now!

Article Labels
Article Tags