275.DATA INDIAN PARKS USING PROC PRINT | PROC MEANS | PROC FREQ | PROC CORR | PROC REPORT | PROC UNIVARIATE | PROC SGPLOT WITH SAS LENGTH STATEMENT FOR ROBUST ANALYSIS

DATA INDIAN PARKS USING PROC PRINT | PROC MEANS | PROC FREQ | PROC CORR | PROC REPORT | PROC UNIVARIATE | PROC SGPLOT WITH SAS LENGTH STATEMENT FOR ROBUST ANALYSIS

/*Creating the parks_india dataset with more than 10 observations */

options nocenter;

data parks_india;

  length ParkName $20 ParkType $18 State $20 KeyAttraction $24 Status $6 Region $6 Comments $24;

  input ParkID YearEstablished Area 

        ParkName $ ParkType $ State $ 

        KeyAttraction $ VisitorCount Status $ EntryFee ConservationScore 

        Region $ Comments $;

  datalines;

1   1936  521   Jim_Corbett        National_Park      Uttarakhand      Tigers             100000 Open   200 95 North  First_in_India

2   1975 1412   Gir                National_Park      Gujarat          Asiatic_Lions      120000 Open   100 94 West   Unique_lion_habitat

3   1984 1330   Sunderbans         National_Park      West_Bengal      Mangroves_Tiger     80000 Open   150 92 East   UNESCO_site

4   1974  104   Bannerghatta       Urban_Park         Karnataka        Safari_Zoo         150000 Open    80 85 South  Incl_Butterfly_Park

5   1985    8   Nehru_Science      Science_Park       Maharashtra      Science_Models     300000 Open    50 60 West   Learning_hub

6   2013   50   Imagica_Theme      Adventure_Park     Maharashtra      Rides_WaterZone    500000 Open   450 40 West   Popular_amusement

7   1981   29   Keoladeo           Wildlife_Sanctuary Rajasthan        Birds               25000 Open    75 88 North  Ramsar_site

8   1976  2.7   Guindy             Urban_Park         Tamil_Nadu       Deer_Birds          70000 Open    40 70 South  City_green_lung 

9   1980  560   Gulf_Mannar        Marine_Park        Tamil_Nadu       Coral_reefs         10000 Open   120 98 South  Biodiversity_hotspot 

10  1987  675   Pin_Valley         Biosphere_Reserve  Himachal_Pradesh Rare_plants          5000 Open    60 90 North  High_altitude_reserve

11  1983  820   Rajaji             National_Park      Uttarakhand      Elephants           40000 Open    90 87 North  Migration_corridor

12  1992  273   Sariska            National_Park      Rajasthan        Leopards            30000 Open    80 84 North  Tiger_reintroduction

;

run;

proc print data=parks_india; 

run;

Output:

Obs	ParkName	ParkType	State	KeyAttraction	Status	Region	Comments	ParkID	YearEstablished	Area	VisitorCount	EntryFee	ConservationScore
1	Jim_Corbett	National_Park	Uttarakhand	Tigers	Open	North	First_in_India	1	1936	521.0	100000	200	95
2	Gir	National_Park	Gujarat	Asiatic_Lions	Open	West	Unique_lion_habitat	2	1975	1412.0	120000	100	94
3	Sunderbans	National_Park	West_Bengal	Mangroves_Tiger	Open	East	UNESCO_site	3	1984	1330.0	80000	150	92
4	Bannerghatta	Urban_Park	Karnataka	Safari_Zoo	Open	South	Incl_Butterfly_Park	4	1974	104.0	150000	80	85
5	Nehru_Science	Science_Park	Maharashtra	Science_Models	Open	West	Learning_hub	5	1985	8.0	300000	50	60
6	Imagica_Theme	Adventure_Park	Maharashtra	Rides_WaterZone	Open	West	Popular_amusement	6	2013	50.0	500000	450	40
7	Keoladeo	Wildlife_Sanctuary	Rajasthan	Birds	Open	North	Ramsar_site	7	1981	29.0	25000	75	88
8	Guindy	Urban_Park	Tamil_Nadu	Deer_Birds	Open	South	City_green_lung	8	1976	2.7	70000	40	70
9	Gulf_Mannar	Marine_Park	Tamil_Nadu	Coral_reefs	Open	South	Biodiversity_hotspot	9	1980	560.0	10000	120	98
10	Pin_Valley	Biosphere_Reserve	Himachal_Pradesh	Rare_plants	Open	North	High_altitude_reserve	10	1987	675.0	5000	60	90
11	Rajaji	National_Park	Uttarakhand	Elephants	Open	North	Migration_corridor	11	1983	820.0	40000	90	87
12	Sariska	National_Park	Rajasthan	Leopards	Open	North	Tiger_reintroduction	12	1992	273.0	30000	80	84

PROC: SUMMARY STATISTICS 

proc means data=parks_india n mean std min max maxdec=2;

  var VisitorCount EntryFee ConservationScore Area;

  class ParkType;

run;

Output:

The MEANS Procedure

ParkType	N Obs	Variable	N	Mean	Std Dev	Minimum	Maximum
Adventure_Park	1	VisitorCount EntryFee ConservationScore Area	1 1 1 1	500000.00 450.00 40.00 50.00	. . . .	500000.00 450.00 40.00 50.00	500000.00 450.00 40.00 50.00
Biosphere_Reserve	1	VisitorCount EntryFee ConservationScore Area	1 1 1 1	5000.00 60.00 90.00 675.00	. . . .	5000.00 60.00 90.00 675.00	5000.00 60.00 90.00 675.00
Marine_Park	1	VisitorCount EntryFee ConservationScore Area	1 1 1 1	10000.00 120.00 98.00 560.00	. . . .	10000.00 120.00 98.00 560.00	10000.00 120.00 98.00 560.00
National_Park	5	VisitorCount EntryFee ConservationScore Area	5 5 5 5	74000.00 124.00 90.40 871.20	38470.77 50.30 4.72 496.50	30000.00 80.00 84.00 273.00	120000.00 200.00 95.00 1412.00
Science_Park	1	VisitorCount EntryFee ConservationScore Area	1 1 1 1	300000.00 50.00 60.00 8.00	. . . .	300000.00 50.00 60.00 8.00	300000.00 50.00 60.00 8.00
Urban_Park	2	VisitorCount EntryFee ConservationScore Area	2 2 2 2	110000.00 60.00 77.50 53.35	56568.54 28.28 10.61 71.63	70000.00 40.00 70.00 2.70	150000.00 80.00 85.00 104.00
Wildlife_Sanctuary	1	VisitorCount EntryFee ConservationScore Area	1 1 1 1	25000.00 75.00 88.00 29.00	. . . .	25000.00 75.00 88.00 29.00	25000.00 75.00 88.00 29.00

PROC: FREQUENCY OF PARK TYPES AND STATES

proc freq data=parks_india;

  tables ParkType State;

run;

Output:

The FREQ Procedure

ParkType	Frequency	Percent	Cumulative Frequency	Cumulative Percent
Adventure_Park	1	8.33	1	8.33
Biosphere_Reserve	1	8.33	2	16.67
Marine_Park	1	8.33	3	25.00
National_Park	5	41.67	8	66.67
Science_Park	1	8.33	9	75.00
Urban_Park	2	16.67	11	91.67
Wildlife_Sanctuary	1	8.33	12	100.00

State	Frequency	Percent	Cumulative Frequency	Cumulative Percent
Gujarat	1	8.33	1	8.33
Himachal_Pradesh	1	8.33	2	16.67
Karnataka	1	8.33	3	25.00
Maharashtra	2	16.67	5	41.67
Rajasthan	2	16.67	7	58.33
Tamil_Nadu	2	16.67	9	75.00
Uttarakhand	2	16.67	11	91.67
West_Bengal	1	8.33	12	100.00

PROC: PRINT SELECTED FIELDS

proc print data=parks_india;

  var ParkName ParkType VisitorCount ConservationScore Region Comments;

run;

Output:

Obs	ParkName	ParkType	VisitorCount	ConservationScore	Region	Comments
1	Jim_Corbett	National_Park	100000	95	North	First_in_India
2	Gir	National_Park	120000	94	West	Unique_lion_habitat
3	Sunderbans	National_Park	80000	92	East	UNESCO_site
4	Bannerghatta	Urban_Park	150000	85	South	Incl_Butterfly_Park
5	Nehru_Science	Science_Park	300000	60	West	Learning_hub
6	Imagica_Theme	Adventure_Park	500000	40	West	Popular_amusement
7	Keoladeo	Wildlife_Sanctuary	25000	88	North	Ramsar_site
8	Guindy	Urban_Park	70000	70	South	City_green_lung
9	Gulf_Mannar	Marine_Park	10000	98	South	Biodiversity_hotspot
10	Pin_Valley	Biosphere_Reserve	5000	90	North	High_altitude_reserve
11	Rajaji	National_Park	40000	87	North	Migration_corridor
12	Sariska	National_Park	30000	84	North	Tiger_reintroduction

PROC: CORRELATION ANALYSIS

proc corr data=parks_india;

  var Area VisitorCount EntryFee ConservationScore;

run;

Output:

The CORR Procedure

4 Variables:	Area VisitorCount EntryFee ConservationScore

Simple Statistics
Variable	N	Mean	Std Dev	Sum	Minimum	Maximum
Area	12	482.05833	502.34943	5785	2.70000	1412
VisitorCount	12	119167	144927	1430000	5000	500000
EntryFee	12	124.58333	111.75172	1495	40.00000	450.00000
ConservationScore	12	81.91667	17.05317	983.00000	40.00000	98.00000

Pearson Correlation Coefficients, N = 12 Prob > |r| under H0: Rho=0
	Area	VisitorCount	EntryFee	ConservationScore
Area	1.00000	-0.33405 0.2886	-0.06305 0.8457	0.58029 0.0479
VisitorCount	-0.33405 0.2886	1.00000	0.72982 0.0071	-0.87254 0.0002
EntryFee	-0.06305 0.8457	0.72982 0.0071	1.00000	-0.54169 0.0689
ConservationScore	0.58029 0.0479	-0.87254 0.0002	-0.54169 0.0689	1.00000

PROC: SORT TO GET TOP CONSERVATION SCORE 

proc sort data=parks_india;

  by descending ConservationScore;

run;

proc print data=parks_india (obs=5);

  title "Top 5 Parks by Conservation Score";

  var ParkName ConservationScore Region;

run;

Output:

Top 5 Parks by Conservation Score

Obs	ParkName	ConservationScore	Region
1	Gulf_Mannar	98	South
2	Jim_Corbett	95	North
3	Gir	94	West
4	Sunderbans	92	East
5	Pin_Valley	90	North

PROC: REPORT FOR MANAGEMENT

proc report data=parks_india nowd;

  columns ParkName ParkType State VisitorCount ConservationScore EntryFee;

  define ParkName / group width=20;

  define ParkType / group;

  define State / group;

  define VisitorCount / analysis mean;

  define ConservationScore / analysis max;

  define EntryFee / analysis mean;

run;

Output:

ParkName	ParkType	State	VisitorCount	ConservationScore	EntryFee
Bannerghatta	Urban_Park	Karnataka	150000	85	80
Gir	National_Park	Gujarat	120000	94	100
Guindy	Urban_Park	Tamil_Nadu	70000	70	40
Gulf_Mannar	Marine_Park	Tamil_Nadu	10000	98	120
Imagica_Theme	Adventure_Park	Maharashtra	500000	40	450
Jim_Corbett	National_Park	Uttarakhand	100000	95	200
Keoladeo	Wildlife_Sanctuary	Rajasthan	25000	88	75
Nehru_Science	Science_Park	Maharashtra	300000	60	50
Pin_Valley	Biosphere_Reserve	Himachal_Pradesh	5000	90	60
Rajaji	National_Park	Uttarakhand	40000	87	90
Sariska	National_Park	Rajasthan	30000	84	80
Sunderbans	National_Park	West_Bengal	80000	92	150

PROC: SIMPLE BAR GRAPH 

proc sgplot data=parks_india;

  vbar ParkType / response=VisitorCount stat=sum;

  title "Aggregate Visitors by Park Type";

run;

Output:

PROC: UNIVARIATE FOR ENTRY FEE DISTRIBUTION 

proc univariate data=parks_india;

  var EntryFee;

run;

Output:

The UNIVARIATE Procedure

Variable: EntryFee

Moments
N	12	Sum Weights	12
Mean	124.583333	Sum Observations	1495
Std Deviation	111.75172	Variance	12488.447
Skewness	2.599915	Kurtosis	7.4462801
Uncorrected SS	323625	Corrected SS	137372.917
Coeff Variation	89.7003774	Std Error Mean	32.2599429

Basic Statistical Measures
Location		Variability
Mean	124.5833	Std Deviation	111.75172
Median	85.0000	Variance	12488
Mode	80.0000	Range	410.00000
		Interquartile Range	67.50000

Tests for Location: Mu0=0
Test	Statistic		p Value
Student's t	t	3.861858	Pr > |t|	0.0026
Sign	M	6	Pr >= |M|	0.0005
Signed Rank	S	39	Pr >= |S|	0.0005

Quantiles (Definition 5)
Level	Quantile
100% Max	450.0
99%	450.0
95%	450.0
90%	200.0
75% Q3	135.0
50% Median	85.0
25% Q1	67.5
10%	50.0
5%	40.0
1%	40.0
0% Min	40.0

Extreme Observations
Lowest		Highest
Value	Obs	Value	Obs
40	10	100	3
50	11	120	1
60	5	150	4
75	6	200	2
80	9	450	12

Macro: Park Summary by Type 

%macro park_summary(park_type=);

  title "Summary for &park_type Parks";

  proc means data=parks_india;

    where ParkType="&park_type";

    var VisitorCount ConservationScore Area EntryFee;

  run;

  proc print data=parks_india;

    where ParkType="&park_type";

    var ParkName State VisitorCount ConservationScore;

  run;

%mend park_summary;

%park_summary(park_type=National_Park)

Output:

Summary for National_Park Parks

The MEANS Procedure

Variable	N	Mean	Std Dev	Minimum	Maximum
VisitorCount ConservationScore Area EntryFee	5 5 5 5	74000.00 90.4000000 871.2000000 124.0000000	38470.77 4.7222876 496.5044813 50.2991054	30000.00 84.0000000 273.0000000 80.0000000	120000.00 95.0000000 1412.00 200.0000000

Summary for National_Park Parks

Obs	ParkName	State	VisitorCount	ConservationScore
2	Jim_Corbett	Uttarakhand	100000	95
3	Gir	Gujarat	120000	94
4	Sunderbans	West_Bengal	80000	92
7	Rajaji	Uttarakhand	40000	87
9	Sariska	Rajasthan	30000	84

%park_summary(park_type=Urban_Park)

Output:

Summary for Urban_Park Parks

The MEANS Procedure

Variable	N	Mean	Std Dev	Minimum	Maximum
VisitorCount ConservationScore Area EntryFee	2 2 2 2	110000.00 77.5000000 53.3500000 60.0000000	56568.54 10.6066017 71.6299169 28.2842712	70000.00 70.0000000 2.7000000 40.0000000	150000.00 85.0000000 104.0000000 80.0000000

Summary for Urban_Park Parks

Obs	ParkName	State	VisitorCount	ConservationScore
8	Bannerghatta	Karnataka	150000	85
10	Guindy	Tamil_Nadu	70000	70

Macro: High Traffic Parks 

%macro report_high_traffic(min_visitors=);

  data high_traffic_parks;

    set parks_india;

    if VisitorCount >= &min_visitors;

  run;

  title "Parks with Visitors Greater Than &min_visitors";

  proc print data=high_traffic_parks; run;

%mend report_high_traffic;

%report_high_traffic(min_visitors=100000)

Output:

Parks with Visitors Greater Than 100000

Obs	ParkName	ParkType	State	KeyAttraction	Status	Region	Comments	ParkID	YearEstablished	Area	VisitorCount	EntryFee	ConservationScore
1	Jim_Corbett	National_Park	Uttarakhand	Tigers	Open	North	First_in_India	1	1936	521	100000	200	95
2	Gir	National_Park	Gujarat	Asiatic_Lions	Open	West	Unique_lion_habitat	2	1975	1412	120000	100	94
3	Bannerghatta	Urban_Park	Karnataka	Safari_Zoo	Open	South	Incl_Butterfly_Park	4	1974	104	150000	80	85
4	Nehru_Science	Science_Park	Maharashtra	Science_Models	Open	West	Learning_hub	5	1985	8	300000	50	60
5	Imagica_Theme	Adventure_Park	Maharashtra	Rides_WaterZone	Open	West	Popular_amusement	6	2013	50	500000	450	40

Macro Variables via PROC SQL 

proc sql;

  select avg(VisitorCount) into :mean_visitors from parks_india where ParkType="National_Park";

quit;

%put Average National Park Visitors: &mean_visitors;

Log:

Average National Park Visitors: 74000

proc sql;

  select count(*) into :num_parks from parks_india;

quit;

%put Total Parks in Sample: &num_parks;

Log:

Total Parks in Sample: 12

proc sql;

  select max(ConservationScore) into :top_score from parks_india;

quit;

%put Highest Conservation Score: &top_score;

Log:

Highest Conservation Score: 98

Macro for Multi-Variable Modeling 

%macro multi_model(dep_vars, ind_vars);

  %let k=1;

  %let dep=%scan(&dep_vars, &k);

  %do %while(&dep ne);

    proc reg data=parks_india;

      model &dep = &ind_vars;

    run;

    %let k = %eval(&k+1);

    %let dep = %scan(&dep_vars, &k);

  %end;

%mend multi_model;

%multi_model(dep_vars=VisitorCount ConservationScore, ind_vars=Area EntryFee)

Output:

The REG Procedure

Model: MODEL1

Dependent Variable: VisitorCount

Number of Observations Read	12
Number of Observations Used	12

Analysis of Variance
Source	DF	Sum of Squares	Mean Square	F Value	Pr > F
Model	2	1.423074E11	71153712454	7.22	0.0135
Error	9	88734241759	9859360195
Corrected Total	11	2.310417E11

Root MSE	99294	R-Square	0.6159
Dependent Mean	119167	Adj R-Sq	0.5306
Coeff Var	83.32390

Parameter Estimates
Variable	DF	Parameter Estimate	Standard Error	t Value	Pr > |t|
Intercept	1	44415	53759	0.83	0.4301
Area	1	-83.43031	59.71549	-1.40	0.1959
EntryFee	1	922.83503	268.43474	3.44	0.0074

The REG Procedure

Model: MODEL1

Dependent Variable: VisitorCount

The REG Procedure

Model: MODEL1

Dependent Variable: ConservationScore

Number of Observations Read	12
Number of Observations Used	12

Analysis of Variance
Source	DF	Sum of Squares	Mean Square	F Value	Pr > F
Model	2	1896.59135	948.29568	6.55	0.0175
Error	9	1302.32531	144.70281
Corrected Total	11	3198.91667

Root MSE	12.02925	R-Square	0.5929
Dependent Mean	81.91667	Adj R-Sq	0.5024
Coeff Var	14.68474

Parameter Estimates
Variable	DF	Parameter Estimate	Standard Error	t Value	Pr > |t|
Intercept	1	82.58478	6.51280	12.68	<.0001
Area	1	0.01861	0.00723	2.57	0.0300
EntryFee	1	-0.07739	0.03252	-2.38	0.0413

The REG Procedure

Model: MODEL1

Dependent Variable: ConservationScore

The REG Procedure

Model: MODEL1

Dependent Variable: VisitorCount

Number of Observations Read	12
Number of Observations Used	12

Analysis of Variance
Source	DF	Sum of Squares	Mean Square	F Value	Pr > F
Model	2	1.423074E11	71153712454	7.22	0.0135
Error	9	88734241759	9859360195
Corrected Total	11	2.310417E11

Root MSE	99294	R-Square	0.6159
Dependent Mean	119167	Adj R-Sq	0.5306
Coeff Var	83.32390

Parameter Estimates
Variable	DF	Parameter Estimate	Standard Error	t Value	Pr > |t|
Intercept	1	44415	53759	0.83	0.4301
Area	1	-83.43031	59.71549	-1.40	0.1959
EntryFee	1	922.83503	268.43474	3.44	0.0074

The REG Procedure

Model: MODEL1

Dependent Variable: VisitorCount

The REG Procedure

Model: MODEL1

Dependent Variable: ConservationScore

Number of Observations Read	12
Number of Observations Used	12

Analysis of Variance
Source	DF	Sum of Squares	Mean Square	F Value	Pr > F
Model	2	1896.59135	948.29568	6.55	0.0175
Error	9	1302.32531	144.70281
Corrected Total	11	3198.91667

Root MSE	12.02925	R-Square	0.5929
Dependent Mean	81.91667	Adj R-Sq	0.5024
Coeff Var	14.68474

Parameter Estimates
Variable	DF	Parameter Estimate	Standard Error	t Value	Pr > |t|
Intercept	1	82.58478	6.51280	12.68	<.0001
Area	1	0.01861	0.00723	2.57	0.0300
EntryFee	1	-0.07739	0.03252	-2.38	0.0413

The REG Procedure

Model: MODEL1

Dependent Variable: ConservationScore

To Visit My Previous Proc  Means And Nway Option:Click Here

To Visit My Previous Proc Means And CharType Option:Click Here

To Visit My Previous SAS Functions:Click Here

To Visit My Previous Length Statement Using In Many Ways:Click Here

Follow Us On : 

 

--- FOLLOW OUR BLOG FOR MORE INFORMATION.

--->PLEASE DO COMMENTS AND SHARE OUR BLOG.