342.DISTRIBUTION ANALYSIS OF WAR OUTCOMES USING DATA STEP | PROQ MEANS | PROC UNIVARIATE | MACROS | PROC SQL | PROC GCHART | PROC FREQ FOR GRAPHICAL AND FREQUENCY-BASED SUMMARIZATION

DISTRIBUTION ANALYSIS OF WAR OUTCOMES USING DATA STEP | PROQ MEANS | PROC UNIVARIATE | MACROS | PROC SQL | PROC GCHART | PROC FREQ FOR GRAPHICAL AND FREQUENCY-BASED SUMMARIZATION

options nocenter;

1.HISTORICAL WARS DATASET CREATION

data historical_wars;

    length War_Name $40 Outcome $25;

    format Start_Date End_Date date9.;

    input War_Name $ Start_Date :date9. End_Date :date9.

          Countries_Involved Casualties Outcome $;

          

    Year = year(Start_Date);

    Duration_Days = intck('day', Start_Date, End_Date);

    

datalines;

World_War_I       28JUL1914 11NOV1918 30 20000000 Allied_Victory

World_War_II      01SEP1939 02SEP1945 50 70000000 Allied_Victory

Cold_War          12MAR1947 26DEC1991 45 2000000 Ideological_End

Vietnam_War       01NOV1955 30APR1975 10 3000000 Communist_Victory

Korean_War        25JUN1950 27JUL1953 20 1500000 Armistice

Gulf_War          02AUG1990 28FEB1991 35 25000 Coalition_Victory

Afghan_War_US     07OCT2001 30AUG2021 40 240000 Taliban_Victory

Iran_Iraq_War     22SEP1980 20AUG1988 2 1000000 Stalemate

Napoleonic_Wars   18MAY1803 20NOV1815 25 6000000 Coalition_Victory

Crimean_War       16OCT1853 30MAR1856 6 500000 Allied_Victory

Franco_Prussian   19JUL1870 28JAN1871 2 180000 German_Victory

Russo_Japanese    08FEB1904 05SEP1905 2 150000 Japanese_Victory

;

run;

proc print data=historical_wars;

run;

OUTPUT:

Obs	War_Name	Outcome	Start_Date	End_Date	Countries_Involved	Casualties	Year	Duration_Days
1	World_War_I	Allied_Victory	28JUL1914	11NOV1918	30	20000000	1914	1567
2	World_War_II	Allied_Victory	01SEP1939	02SEP1945	50	70000000	1939	2193
3	Cold_War	Ideological_End	12MAR1947	26DEC1991	45	2000000	1947	16360
4	Vietnam_War	Communist_Victory	01NOV1955	30APR1975	10	3000000	1955	7120
5	Korean_War	Armistice	25JUN1950	27JUL1953	20	1500000	1950	1128
6	Gulf_War	Coalition_Victory	02AUG1990	28FEB1991	35	25000	1990	210
7	Afghan_War_US	Taliban_Victory	07OCT2001	30AUG2021	40	240000	2001	7267
8	Iran_Iraq_War	Stalemate	22SEP1980	20AUG1988	2	1000000	1980	2889
9	Napoleonic_Wars	Coalition_Victory	18MAY1803	20NOV1815	25	6000000	1803	4569
10	Crimean_War	Allied_Victory	16OCT1853	30MAR1856	6	500000	1853	896
11	Franco_Prussian	German_Victory	19JUL1870	28JAN1871	2	180000	1870	193
12	Russo_Japanese	Japanese_Victory	08FEB1904	05SEP1905	2	150000	1904	575

2.PROC SQL – DATA EXTRACTION AND DERIVED COLUMNS

proc sql;

    create table wars_sql as

    select War_Name,Year,Countries_Involved,Casualties,Duration_Days,Outcome,

           intnx('year', Start_Date, 1) as Next_Year_Start format=date9.

    from historical_wars;

quit;

proc print data=wars_sql;

run;

OUTPUT:

Obs	War_Name	Year	Countries_Involved	Casualties	Duration_Days	Outcome	Next_Year_Start
1	World_War_I	1914	30	20000000	1567	Allied_Victory	01JAN1915
2	World_War_II	1939	50	70000000	2193	Allied_Victory	01JAN1940
3	Cold_War	1947	45	2000000	16360	Ideological_End	01JAN1948
4	Vietnam_War	1955	10	3000000	7120	Communist_Victory	01JAN1956
5	Korean_War	1950	20	1500000	1128	Armistice	01JAN1951
6	Gulf_War	1990	35	25000	210	Coalition_Victory	01JAN1991
7	Afghan_War_US	2001	40	240000	7267	Taliban_Victory	01JAN2002
8	Iran_Iraq_War	1980	2	1000000	2889	Stalemate	01JAN1981
9	Napoleonic_Wars	1803	25	6000000	4569	Coalition_Victory	01JAN1804
10	Crimean_War	1853	6	500000	896	Allied_Victory	01JAN1854
11	Franco_Prussian	1870	2	180000	193	German_Victory	01JAN1871
12	Russo_Japanese	1904	2	150000	575	Japanese_Victory	01JAN1905

3.PROC FREQ – OUTCOME DISTRIBUTION

proc freq data=historical_wars;

    tables Outcome / nocum nopercent;

run;

OUTPUT:

The FREQ Procedure

Outcome	Frequency
Allied_Victory	3
Armistice	1
Coalition_Victory	2
Communist_Victory	1
German_Victory	1
Ideological_End	1
Japanese_Victory	1
Stalemate	1
Taliban_Victory	1

4.PROC MEANS – DESCRIPTIVE STATISTICS

proc means data=historical_wars mean min max sum;

    var Casualties Duration_Days Countries_Involved;

run;

OUTPUT:

The MEANS Procedure

Variable	Mean	Minimum	Maximum	Sum
Casualties Duration_Days Countries_Involved	8716250.00 3747.25 22.2500000	25000.00 193.0000000 2.0000000	70000000.00 16360.00 50.0000000	104595000 44967.00 267.0000000

5.PROC UNIVARIATE – DISTRIBUTION ANALYSIS

proc univariate data=historical_wars;

    var Casualties;

    histogram Casualties;

run;

OUTPUT:

The UNIVARIATE Procedure

Variable: Casualties

Moments
N	12	Sum Weights	12
Mean	8716250	Sum Observations	104595000
Std Deviation	20092823.1	Variance	4.03722E14
Skewness	3.0552289	Kurtosis	9.65331645
Uncorrected SS	5.35261E15	Corrected SS	4.44094E15
Coeff Variation	230.521418	Std Error Mean	5800298.42

Basic Statistical Measures
Location		Variability
Mean	8716250	Std Deviation	20092823
Median	1250000	Variance	4.03722E14
Mode	.	Range	69975000
		Interquartile Range	4290000

Tests for Location: Mu0=0
Test	Statistic		p Value
Student's t	t	1.502724	Pr > |t|	0.1611
Sign	M	6	Pr >= |M|	0.0005
Signed Rank	S	39	Pr >= |S|	0.0005

Quantiles (Definition 5)
Level	Quantile
100% Max	70000000
99%	70000000
95%	70000000
90%	20000000
75% Q3	4500000
50% Median	1250000
25% Q1	210000
10%	150000
5%	25000
1%	25000
0% Min	25000

Extreme Observations
Lowest		Highest
Value	Obs	Value	Obs
25000	6	2000000	3
150000	12	3000000	4
180000	11	6000000	9
240000	7	20000000	1
500000	10	70000000	2

The UNIVARIATE Procedure

6.PROC SGPLOT – VISUALIZATION 

proc sgplot data=historical_wars;

    vbar War_Name / response=Casualties datalabel;

    xaxis display=(nolabel);

    yaxis label="Number of Casualties";

run;

OUTPUT:

7.MACRO – WAR IMPACT CLASSIFICATION

%macro impact_classification;

    data war_impact;

        set historical_wars;

        length Impact_Level $15;

        

        if Casualties >= 20000000 then Impact_Level = 'Very Severe';

        else if Casualties >= 5000000 then Impact_Level = 'Severe';

        else if Casualties >= 1000000 then Impact_Level = 'Moderate';

        else Impact_Level = 'Low';

    run;

    proc print data=war_impact;

    run;

%mend;

%impact_classification;

OUTPUT:

Obs	War_Name	Outcome	Start_Date	End_Date	Countries_Involved	Casualties	Year	Duration_Days	Impact_Level
1	World_War_I	Allied_Victory	28JUL1914	11NOV1918	30	20000000	1914	1567	Very Severe
2	World_War_II	Allied_Victory	01SEP1939	02SEP1945	50	70000000	1939	2193	Very Severe
3	Cold_War	Ideological_End	12MAR1947	26DEC1991	45	2000000	1947	16360	Moderate
4	Vietnam_War	Communist_Victory	01NOV1955	30APR1975	10	3000000	1955	7120	Moderate
5	Korean_War	Armistice	25JUN1950	27JUL1953	20	1500000	1950	1128	Moderate
6	Gulf_War	Coalition_Victory	02AUG1990	28FEB1991	35	25000	1990	210	Low
7	Afghan_War_US	Taliban_Victory	07OCT2001	30AUG2021	40	240000	2001	7267	Low
8	Iran_Iraq_War	Stalemate	22SEP1980	20AUG1988	2	1000000	1980	2889	Moderate
9	Napoleonic_Wars	Coalition_Victory	18MAY1803	20NOV1815	25	6000000	1803	4569	Severe
10	Crimean_War	Allied_Victory	16OCT1853	30MAR1856	6	500000	1853	896	Low
11	Franco_Prussian	German_Victory	19JUL1870	28JAN1871	2	180000	1870	193	Low
12	Russo_Japanese	Japanese_Victory	08FEB1904	05SEP1905	2	150000	1904	575	Low

8.DATE FUNCTION (INTCK)

data war_years;

    set historical_wars;

    Duration_Years = intck('year', Start_Date, End_Date);

run;

proc print data=war_years;

run;

OUTPUT:

Obs	War_Name	Outcome	Start_Date	End_Date	Countries_Involved	Casualties	Year	Duration_Days	Duration_Years
1	World_War_I	Allied_Victory	28JUL1914	11NOV1918	30	20000000	1914	1567	4
2	World_War_II	Allied_Victory	01SEP1939	02SEP1945	50	70000000	1939	2193	6
3	Cold_War	Ideological_End	12MAR1947	26DEC1991	45	2000000	1947	16360	44
4	Vietnam_War	Communist_Victory	01NOV1955	30APR1975	10	3000000	1955	7120	20
5	Korean_War	Armistice	25JUN1950	27JUL1953	20	1500000	1950	1128	3
6	Gulf_War	Coalition_Victory	02AUG1990	28FEB1991	35	25000	1990	210	1
7	Afghan_War_US	Taliban_Victory	07OCT2001	30AUG2021	40	240000	2001	7267	20
8	Iran_Iraq_War	Stalemate	22SEP1980	20AUG1988	2	1000000	1980	2889	8
9	Napoleonic_Wars	Coalition_Victory	18MAY1803	20NOV1815	25	6000000	1803	4569	12
10	Crimean_War	Allied_Victory	16OCT1853	30MAR1856	6	500000	1853	896	3
11	Franco_Prussian	German_Victory	19JUL1870	28JAN1871	2	180000	1870	193	1
12	Russo_Japanese	Japanese_Victory	08FEB1904	05SEP1905	2	150000	1904	575	1

9.ADDITIONAL PROC – PROC PRINT (DATA REVIEW)

proc print data=war_impact(obs=5);

    title "Sample Output with Impact Classification";

run;

OUTPUT:

Sample Output with Impact Classification

Obs	War_Name	Outcome	Start_Date	End_Date	Countries_Involved	Casualties	Year	Duration_Days	Impact_Level
1	World_War_I	Allied_Victory	28JUL1914	11NOV1918	30	20000000	1914	1567	Very Severe
2	World_War_II	Allied_Victory	01SEP1939	02SEP1945	50	70000000	1939	2193	Very Severe
3	Cold_War	Ideological_End	12MAR1947	26DEC1991	45	2000000	1947	16360	Moderate
4	Vietnam_War	Communist_Victory	01NOV1955	30APR1975	10	3000000	1955	7120	Moderate
5	Korean_War	Armistice	25JUN1950	27JUL1953	20	1500000	1950	1128	Moderate

10.PIE PLOT – DISTRIBUTION OF WAR OUTCOMES

proc gchart data=historical_wars;

    pie Outcome / percent=inside value=inside;

    title "DISTRIBUTION OF WAR OUTCOMES USING PIE CHART";

run;

quit;

OUTPUT:

To Visit My Previous Online Streaming Flatform Dataset:Click Here
To Visit My Previous Statistical Evaluation Of Clinical Trials:Click Here
To Visit My Previous Unlocking Retail Insights Dataset:Click Here
To Visit My Previous Sas Interview Questions-1:Click Here


Follow Us On : 


 

--- FOLLOW OUR BLOG FOR MORE INFORMATION.
--->PLEASE DO COMMENTS AND SHARE OUR BLOG.