396.Are high-security border checkpoints always more efficient, or do they slow down trade?A Complete Sas Analytics Data

Are high-security border checkpoints always more efficient, or do they slow down trade?A Complete Sas Analytics Data

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

HERE IN THIS PROJECT WE USED THESE SAS STATEMENTS —
DATA STEP | PROC SQL |  PROC PRINT | PROC SGPLOT | MACROS | PROC CORR | PROC MEANS | PROC FREQ | PROC UNIVARIATE | PROC TRANSPOSE | PROC DATASETS DELETE | DATA FUNCTIONS

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

TABLE OF CONTENTS

1.     Introduction

2.     Business Context

3.     Dataset Design & Variables

4.     SAS Environment Setup

5.     Raw Dataset Creation (10 Observations)

6.     Character & Numeric Data Cleaning

7.     Date Creation & Formatting (MDY, INTCK, INTNX)

8.     Utilization Classification Macro

9.     Fraud Detection Macro Logic

10.  PROC SQL Analytics

11.  PROC FREQ Analysis

12.  PROC MEANS Analysis

13.  PROC UNIVARIATE Analysis

14.  PROC CORR Analysis

15.  PROC SGPLOT Visualizations

16.  TRANSPOSE Usage

17.  PROC DATASETS 

18.  Business Insights

19.  Interview Talking Points

20.  Conclusion

1. INTRODUCTION

Border trade checkpoints are critical economic gateways between countries.
They manage:

·       Import & export goods

·       Vehicle movement

·       Customs clearance

·       Security enforcement

·       Revenue protection

Analyzing checkpoint efficiency helps governments:

·       Reduce clearance delays

·       Detect fraud

·       Improve logistics efficiency

·       Optimize security allocation

This SAS project simulates a real-world border trade analytics system.

2. BUSINESS CONTEXT

Problem Statement:
Government authorities want to evaluate:

·       How efficient each checkpoint is

·       Whether high goods value aligns with traffic volume

·       Which checkpoints show fraud risk patterns

·       Where clearance delays occur

·       How security level impacts performance

Business Users:

·       Customs Department

·       Border Security Agencies

·       Trade & Commerce Ministry

·       Logistics & Transport Authorities

3.  DATASET DESIGN & VARIABLES

Variable	Type	Description
Checkpoint_Name	Character	Border checkpoint name
Country	Character	Country where checkpoint exists
Trade_Date	Numeric (Date)	Operational date
Daily_Vehicles	Numeric	Vehicles crossing per day
Goods_Value	Numeric	Value of goods (Million USD)
Clearance_Time	Numeric	Avg clearance time (hours)
Security_Level	Character	LOW / MEDIUM / HIGH
Efficiency_Rating	Numeric	Efficiency percentage
Fraud_Flag	Character	Y / N
Utilization_Class	Character	LOW / MEDIUM / HIGH

4. SAS ENVIRONMENT SETUP

options nocenter nodate nonumber;

title;

footnote;

LOG:

69 options nocenter nodate nonumber;

70 title;

71 footnote;

• Ensures clean output • Removes distractions in reports • Professional reporting practice

5. RAW DATASET CREATION

data border_trade_raw;

    length

        Checkpoint_Name   $25

        Country           $15

        Security_Level    $8;

    format Trade_Date date9.;

    input

        Checkpoint_Name   :& $25.

        Country           :$15.

        Trade_Date        :date9.

        Daily_Vehicles

        Goods_Value

        Clearance_Time

        Security_Level    :$8.

        Efficiency_Rating

    ;

datalines;

Attari Border        India        02JAN2025  980   72   5  HIGH   82

Wagah Post           India        01JAN2025 1200   85   6  HIGH   78

Petrapole            India        03JAN2025 1500   95   8  MEDIUM 70

Moreh Checkpost      India        04JAN2025  600   40   9  LOW    55

Raxaul Border        India        05JAN2025 1100   65   7  MEDIUM 68

Benapole             Bangladesh  01JAN2025 1400   90   6  MEDIUM 75

Chittagong Port      Bangladesh  02JAN2025 1800  120   4  HIGH   88

Torkham              Pakistan    01JAN2025 1600  110   7  HIGH   80

Islam Qala           Afghanistan 02JAN2025  750   55   8  MEDIUM 65

Zamyn Uud            Mongolia    01JAN2025  650   42   9  LOW    58

;

run;

proc print data=border_trade_raw;

run;

OUTPUT:

Obs	Checkpoint_Name	Country	Security_Level	Trade_Date	Daily_Vehicles	Goods_Value	Clearance_Time	Efficiency_Rating
1	Attari Border	India	HIGH	02JAN2025	980	72	5	82
2	Wagah Post	India	HIGH	01JAN2025	1200	85	6	78
3	Petrapole	India	MEDIUM	03JAN2025	1500	95	8	70
4	Moreh Checkpost	India	LOW	04JAN2025	600	40	9	55
5	Raxaul Border	India	MEDIUM	05JAN2025	1100	65	7	68
6	Benapole	Bangladesh	MEDIUM	01JAN2025	1400	90	6	75
7	Chittagong Port	Bangladesh	HIGH	02JAN2025	1800	120	4	88
8	Torkham	Pakistan	HIGH	01JAN2025	1600	110	7	80
9	Islam Qala	Afghanistan	MEDIUM	02JAN2025	750	55	8	65
10	Zamyn Uud	Mongolia	LOW	01JAN2025	650	42	9	58

·  DATALINES simulate real operational data

·  date9. ensures proper SAS date handling

·  Realistic operational values used

6. CHARACTER & NUMERIC DATA CLEANING

data border_trade_clean;

    set border_trade_raw;

    Checkpoint_Name = propcase(strip(Checkpoint_Name));

    Country = upcase(trim(Country));

    Security_Level = upcase(Security_Level);

    Goods_Value_USD = round(Goods_Value * 1000000, 1);

    Vehicle_Load_Ratio = Daily_Vehicles / Clearance_Time;

run;

proc print data=border_trade_clean;

run;

OUTPUT:

Obs	Checkpoint_Name	Country	Security_Level	Trade_Date	Daily_Vehicles	Goods_Value	Clearance_Time	Efficiency_Rating	Goods_Value_USD	Vehicle_Load_Ratio
1	Attari Border	INDIA	HIGH	02JAN2025	980	72	5	82	72000000	196.000
2	Wagah Post	INDIA	HIGH	01JAN2025	1200	85	6	78	85000000	200.000
3	Petrapole	INDIA	MEDIUM	03JAN2025	1500	95	8	70	95000000	187.500
4	Moreh Checkpost	INDIA	LOW	04JAN2025	600	40	9	55	40000000	66.667
5	Raxaul Border	INDIA	MEDIUM	05JAN2025	1100	65	7	68	65000000	157.143
6	Benapole	BANGLADESH	MEDIUM	01JAN2025	1400	90	6	75	90000000	233.333
7	Chittagong Port	BANGLADESH	HIGH	02JAN2025	1800	120	4	88	120000000	450.000
8	Torkham	PAKISTAN	HIGH	01JAN2025	1600	110	7	80	110000000	228.571
9	Islam Qala	AFGHANISTAN	MEDIUM	02JAN2025	750	55	8	65	55000000	93.750
10	Zamyn Uud	MONGOLIA	LOW	01JAN2025	650	42	9	58	42000000	72.222

·  strip, trim → remove unwanted spaces

·  propcase, upcase → standard formatting

·  Derived metrics improve analytics depth

7. DATE FUNCTIONS (MDY, INTCK, INTNX)

data border_trade_dates;

    set border_trade_clean;

    Month_Start = intnx('month', Trade_Date, 0, 'b');

    Days_From_Start = intck('day', '01JAN2025'd, Trade_Date);

    Custom_Date = mdy(month(Trade_Date), day(Trade_Date), year(Trade_Date));

run;

proc print data=border_trade_dates;

run;

OUTPUT:

Obs	Checkpoint_Name	Country	Security_Level	Trade_Date	Daily_Vehicles	Goods_Value	Clearance_Time	Efficiency_Rating	Goods_Value_USD	Vehicle_Load_Ratio	Month_Start	Days_From_Start	Custom_Date
1	Attari Border	INDIA	HIGH	02JAN2025	980	72	5	82	72000000	196.000	23742	1	23743
2	Wagah Post	INDIA	HIGH	01JAN2025	1200	85	6	78	85000000	200.000	23742	0	23742
3	Petrapole	INDIA	MEDIUM	03JAN2025	1500	95	8	70	95000000	187.500	23742	2	23744
4	Moreh Checkpost	INDIA	LOW	04JAN2025	600	40	9	55	40000000	66.667	23742	3	23745
5	Raxaul Border	INDIA	MEDIUM	05JAN2025	1100	65	7	68	65000000	157.143	23742	4	23746
6	Benapole	BANGLADESH	MEDIUM	01JAN2025	1400	90	6	75	90000000	233.333	23742	0	23742
7	Chittagong Port	BANGLADESH	HIGH	02JAN2025	1800	120	4	88	120000000	450.000	23742	1	23743
8	Torkham	PAKISTAN	HIGH	01JAN2025	1600	110	7	80	110000000	228.571	23742	0	23742
9	Islam Qala	AFGHANISTAN	MEDIUM	02JAN2025	750	55	8	65	55000000	93.750	23742	1	23743
10	Zamyn Uud	MONGOLIA	LOW	01JAN2025	650	42	9	58	42000000	72.222	23742	0	23742

·  INTNX → reporting periods

·  INTCK → gap analysis

·  MDY → date reconstruction

8. UTILIZATION CLASSIFICATION MACRO

%macro utilization_class;

data border_trade_util;

    set border_trade_dates;

    length Utilization_Class $8.;

    if Daily_Vehicles >= 1500 then Utilization_Class = 'HIGH';

    else if Daily_Vehicles >= 900 then Utilization_Class = 'MEDIUM';

    else Utilization_Class = 'LOW';

run;

proc print data=border_trade_util;

run;

%mend;

%utilization_class;

OUTPUT:

Obs	Checkpoint_Name	Country	Security_Level	Trade_Date	Daily_Vehicles	Goods_Value	Clearance_Time	Efficiency_Rating	Goods_Value_USD	Vehicle_Load_Ratio	Month_Start	Days_From_Start	Custom_Date	Utilization_Class
1	Attari Border	INDIA	HIGH	02JAN2025	980	72	5	82	72000000	196.000	23742	1	23743	MEDIUM
2	Wagah Post	INDIA	HIGH	01JAN2025	1200	85	6	78	85000000	200.000	23742	0	23742	MEDIUM
3	Petrapole	INDIA	MEDIUM	03JAN2025	1500	95	8	70	95000000	187.500	23742	2	23744	HIGH
4	Moreh Checkpost	INDIA	LOW	04JAN2025	600	40	9	55	40000000	66.667	23742	3	23745	LOW
5	Raxaul Border	INDIA	MEDIUM	05JAN2025	1100	65	7	68	65000000	157.143	23742	4	23746	MEDIUM
6	Benapole	BANGLADESH	MEDIUM	01JAN2025	1400	90	6	75	90000000	233.333	23742	0	23742	MEDIUM
7	Chittagong Port	BANGLADESH	HIGH	02JAN2025	1800	120	4	88	120000000	450.000	23742	1	23743	HIGH
8	Torkham	PAKISTAN	HIGH	01JAN2025	1600	110	7	80	110000000	228.571	23742	0	23742	HIGH
9	Islam Qala	AFGHANISTAN	MEDIUM	02JAN2025	750	55	8	65	55000000	93.750	23742	1	23743	LOW
10	Zamyn Uud	MONGOLIA	LOW	01JAN2025	650	42	9	58	42000000	72.222	23742	0	23742	LOW

·  Reusable logic

·  Consistency across datasets

·  Automation 

9. FRAUD DETECTION MACRO LOGIC

%macro fraud_logic;

data border_trade_fraud;

    set border_trade_util;

    if Goods_Value > 100 and Daily_Vehicles < 800 then Fraud_Flag='Y';

    else if Clearance_Time > 9 then Fraud_Flag='Y';

    else Fraud_Flag='N';

run;

proc print data=border_trade_fraud;

run;

%mend;

%fraud_logic;

OUTPUT:

Obs	Checkpoint_Name	Country	Security_Level	Trade_Date	Daily_Vehicles	Goods_Value	Clearance_Time	Efficiency_Rating	Goods_Value_USD	Vehicle_Load_Ratio	Month_Start	Days_From_Start	Custom_Date	Utilization_Class	Fraud_Flag
1	Attari Border	INDIA	HIGH	02JAN2025	980	72	5	82	72000000	196.000	23742	1	23743	MEDIUM	N
2	Wagah Post	INDIA	HIGH	01JAN2025	1200	85	6	78	85000000	200.000	23742	0	23742	MEDIUM	N
3	Petrapole	INDIA	MEDIUM	03JAN2025	1500	95	8	70	95000000	187.500	23742	2	23744	HIGH	N
4	Moreh Checkpost	INDIA	LOW	04JAN2025	600	40	9	55	40000000	66.667	23742	3	23745	LOW	N
5	Raxaul Border	INDIA	MEDIUM	05JAN2025	1100	65	7	68	65000000	157.143	23742	4	23746	MEDIUM	N
6	Benapole	BANGLADESH	MEDIUM	01JAN2025	1400	90	6	75	90000000	233.333	23742	0	23742	MEDIUM	N
7	Chittagong Port	BANGLADESH	HIGH	02JAN2025	1800	120	4	88	120000000	450.000	23742	1	23743	HIGH	N
8	Torkham	PAKISTAN	HIGH	01JAN2025	1600	110	7	80	110000000	228.571	23742	0	23742	HIGH	N
9	Islam Qala	AFGHANISTAN	MEDIUM	02JAN2025	750	55	8	65	55000000	93.750	23742	1	23743	LOW	N
10	Zamyn Uud	MONGOLIA	LOW	01JAN2025	650	42	9	58	42000000	72.222	23742	0	23742	LOW	N

·  High value + low volume = possible under-reporting

·  Long clearance = inspection or irregularities

10. PROC SQL ANALYTICS

proc sql;

    create table country_summary as

    select Country,

           count(*) as Checkpoints,

           avg(Daily_Vehicles) as Avg_Vehicles,

           avg(Goods_Value) as Avg_Goods_Value,

           avg(Efficiency_Rating) as Avg_Efficiency

    from border_trade_fraud

    group by Country;

quit;

proc print data=country_summary;

run;

OUTPUT:

Obs	Country	Checkpoints	Avg_Vehicles	Avg_Goods_Value	Avg_Efficiency
1	AFGHANISTAN	1	750	55.0	65.0
2	BANGLADESH	2	1600	105.0	81.5
3	INDIA	5	1076	71.4	70.6
4	MONGOLIA	1	650	42.0	58.0
5	PAKISTAN	1	1600	110.0	80.0

·  Flexible aggregation

·  Industry standard

·  Required for ADaM & reporting

11. PROC FREQ

proc freq data=border_trade_fraud;

    tables Security_Level*Fraud_Flag / norow nocol;

run;

OUTPUT:

The FREQ Procedure

Frequency Percent

Table of Security_Level by Fraud_Flag Security_Level Fraud_Flag N Total HIGH 4 40.00 4 40.00 LOW 2 20.00 2 20.00 MEDIUM 4 40.00 4 40.00 Total 10 100.00 10 100.00

·  Categorical relationships

·  Fraud vs security strength analysis

12. PROC MEANS

proc means data=border_trade_fraud mean min max std;

    var Daily_Vehicles Goods_Value Clearance_Time Efficiency_Rating;

run;

OUTPUT:

The MEANS Procedure

Variable	Mean	Minimum	Maximum	Std Dev
Daily_Vehicles Goods_Value Clearance_Time Efficiency_Rating	1158.00 77.4000000 6.9000000 71.9000000	600.0000000 40.0000000 4.0000000 55.0000000	1800.00 120.0000000 9.0000000 88.0000000	415.7670288 27.3666464 1.6633300 10.6400710

13. PROC UNIVARIATE

proc univariate data=border_trade_fraud;

    var Clearance_Time Efficiency_Rating;

    histogram Clearance_Time;

run;

OUTPUT:

The UNIVARIATE Procedure

Variable: Clearance_Time

Moments
N	10	Sum Weights	10
Mean	6.9	Sum Observations	69
Std Deviation	1.66332999	Variance	2.76666667
Skewness	-0.347684	Kurtosis	-0.7210252
Uncorrected SS	501	Corrected SS	24.9
Coeff Variation	24.1062318	Std Error Mean	0.52599113

Basic Statistical Measures
Location		Variability
Mean	6.900000	Std Deviation	1.66333
Median	7.000000	Variance	2.76667
Mode	6.000000	Range	5.00000
		Interquartile Range	2.00000

Note: The mode displayed is the smallest of 4 modes with a count of 2.

Tests for Location: Mu0=0
Test	Statistic		p Value
Student's t	t	13.11809	Pr > |t|	<.0001
Sign	M	5	Pr >= |M|	0.0020
Signed Rank	S	27.5	Pr >= |S|	0.0020

Quantiles (Definition 5)
Level	Quantile
100% Max	9.0
99%	9.0
95%	9.0
90%	9.0
75% Q3	8.0
50% Median	7.0
25% Q1	6.0
10%	4.5
5%	4.0
1%	4.0
0% Min	4.0

Extreme Observations
Lowest		Highest
Value	Obs	Value	Obs
4	7	7	8
5	1	8	3
6	6	8	9
6	2	9	4
7	8	9	10

The UNIVARIATE Procedure

The UNIVARIATE Procedure

Variable: Efficiency_Rating

Moments
N	10	Sum Weights	10
Mean	71.9	Sum Observations	719
Std Deviation	10.640071	Variance	113.211111
Skewness	-0.2208387	Kurtosis	-0.8519282
Uncorrected SS	52715	Corrected SS	1018.9
Coeff Variation	14.7984298	Std Error Mean	3.36468589

Basic Statistical Measures
Location		Variability
Mean	71.90000	Std Deviation	10.64007
Median	72.50000	Variance	113.21111
Mode	.	Range	33.00000
		Interquartile Range	15.00000

Tests for Location: Mu0=0
Test	Statistic		p Value
Student's t	t	21.36901	Pr > |t|	<.0001
Sign	M	5	Pr >= |M|	0.0020
Signed Rank	S	27.5	Pr >= |S|	0.0020

Quantiles (Definition 5)
Level	Quantile
100% Max	88.0
99%	88.0
95%	88.0
90%	85.0
75% Q3	80.0
50% Median	72.5
25% Q1	65.0
10%	56.5
5%	55.0
1%	55.0
0% Min	55.0

Extreme Observations
Lowest		Highest
Value	Obs	Value	Obs
55	4	75	6
58	10	78	2
65	9	80	8
68	5	82	1
70	3	88	7

14. PROC CORR

proc corr data=border_trade_fraud;

    var Daily_Vehicles Goods_Value Clearance_Time Efficiency_Rating;

run;

OUTPUT:

The CORR Procedure

4 Variables:	Daily_Vehicles Goods_Value Clearance_Time Efficiency_Rating

Simple Statistics
Variable	N	Mean	Std Dev	Sum	Minimum	Maximum
Daily_Vehicles	10	1158	415.76703	11580	600.00000	1800
Goods_Value	10	77.40000	27.36665	774.00000	40.00000	120.00000
Clearance_Time	10	6.90000	1.66333	69.00000	4.00000	9.00000
Efficiency_Rating	10	71.90000	10.64007	719.00000	55.00000	88.00000

Pearson Correlation Coefficients, N = 10 Prob > |r| under H0: Rho=0
	Daily_Vehicles	Goods_Value	Clearance_Time	Efficiency_Rating
Daily_Vehicles	1.00000	0.98452 <.0001	-0.65103 0.0415	0.80394 0.0051
Goods_Value	0.98452 <.0001	1.00000	-0.70201 0.0236	0.86788 0.0011
Clearance_Time	-0.65103 0.0415	-0.70201 0.0236	1.00000	-0.92980 <.0001
Efficiency_Rating	0.80394 0.0051	0.86788 0.0011	-0.92980 <.0001	1.00000

·  Efficiency vs clearance time

·  Vehicles vs goods value dependency

15. PROC SGPLOT

proc sgplot data=border_trade_fraud;

    scatter x=Daily_Vehicles y=Efficiency_Rating;

    reg x=Daily_Vehicles y=Efficiency_Rating;

run;

OUTPUT:

16. TRANSPOSE

proc transpose data=country_summary 

               out=country_transposed;

run;

proc print data=country_transposed;

run;

OUTPUT:

Obs	_NAME_	COL1	COL2	COL3	COL4	COL5
1	Checkpoints	1	2.0	5.0	1	1
2	Avg_Vehicles	750	1600.0	1076.0	650	1600
3	Avg_Goods_Value	55	105.0	71.4	42	110
4	Avg_Efficiency	65	81.5	70.6	58	80

17. PROC DATASETS

proc datasets lib=work nolist;

    delete border_trade_raw;

quit;

LOG:

NOTE: Deleting WORK.BORDER_TRADE_RAW (memtype=DATA).

18.  BUSINESS INSIGHTS

·       High security does not always mean lower fraud

·       Clearance time strongly affects efficiency

·       Some low-volume checkpoints handle high-value goods

·       Automation improves monitoring accuracy

19.  INTERVIEW TALKING POINTS

·       Why macros over hard coding

·       Fraud detection logic explanation

·       Date function differences

·       PROC SQL vs DATA STEP

·       Visualization interpretation

20. CONCLUSION

This Border Trade Checkpoints Analytics project shows how SAS can turn raw border movement data into meaningful business insights.
By analyzing vehicles, goods value, clearance time, security level, and efficiency, we can identify delays, detect possible fraud patterns, and measure checkpoint performance.

Using PROC SQL, statistical procedures, macros, and date functions, this project demonstrates how data-driven decisions can improve border security, trade efficiency, and revenue protection.
Overall, it proves that smart analytics leads to safer borders and faster trade.

INTERVIEW QUESTIONS FOR YOU

·  What is CALL EXECUTE?

·  What is SAS Metadata?

·  What is SAS Grid?

 

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

About the Author:

SAS Learning Hub is a data analytics and SAS programming platform focused on clinical, financial, and real-world data analysis. The content is created by professionals with academic training in Pharmaceutics and hands-on experience in Base SAS, PROC SQL, Macros, SDTM, and ADaM, providing practical and industry-relevant SAS learning resources.

Disclaimer:

The datasets and analysis in this article are created for educational and demonstration purposes only. They do not represent BORDER CHECKPOINTS data.

Our Mission:

This blog provides industry-focused SAS programming tutorials and analytics projects covering finance, healthcare, and technology.

This project is suitable for:

·  Students learning SAS

·  Data analysts building portfolios

·  Professionals preparing for SAS interviews

·  Bloggers writing about analytics and smart cities

·  EV and energy industry professionals

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

Follow Us On : 

 

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

--->Follow our blog for more SAS-based analytics projects and industry data models.

---> Support Us By Following Our Blog..

To deepen your understanding of SAS analytics, please refer to our other data science and industry-focused projects listed below:

1.Is there a strong relationship between employment rate and poverty reduction across states?A Complete Sas Study

2.Which mobile payment apps handle the highest number of transactions, and are they truly the most reliable?

3.Which namkeen products sell the most, and what does SAS data creation reveal about customer taste?A Sas Study

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

About Us | Contact | Privacy Policy