231.ANALYZING INDIAN LANGUAGES USING PROC FORMAT | PROC PRINT | PROC SORT | PROC MEANS | PROC FREQ | PROC SQL | PROC SUMMARY | PROC TABULATE | PROC UNIVARIATE | PROC REPORT | PROC TRANSPOSE | MACROS

ANALYZING INDIAN LANGUAGES USING PROC FORMAT | PROC PRINT | PROC SORT | PROC MEANS | PROC FREQ | PROC SQL | PROC SUMMARY | PROC TABULATE | PROC UNIVARIATE | PROC REPORT | PROC TRANSPOSE | MACROS

 /*Creating A Dataset Of Languages In India*/

1. Global OPTIONS and custom FORMATS

options nocenter fullstimer yearcutoff=1900

        pagesize=60 linesize=120

        missing='.' /* uniform numeric missings */

        dkricond=error; /* error on dup‑key updates */

proc format;

   value $famfmt

      'IA' = 'Indo‑Aryan'

      'DR' = 'Dravidian'

      'AST' = 'Austro‑Asiatic'

      'ST' = 'Sino‑Tibetan'

      'ISO' = 'Isolate/Other';

   value riskfmt

      1 = 'Safe'

      2 = 'Vulnerable'

      3 = 'Definitely Endangered'

      4 = 'Severely Endangered';

run;

2. DATA step

data lang_india;

   infile datalines dsd dlm='|';

   input Language :$18.

         Family   :$5.

         Lang_ID              

         Speakers_Millions     

         Official_States      

         Dialects              

         Script_Count        

         Literacy_Rate        

         Recognition_Year     

         Digital_Index        

         Endanger_Score       

         ;

format Family $famfmt. Endanger_Score riskfmt.;

datalines;

Hindi|IA|101|568|11|23|2|74|1950|88|1

Bengali|IA|102|97|2|18|2|71|1950|84|1

Marathi|IA|103|83|1|15|1|76|1950|72|1

Telugu|DR|104|82|2|21|2|70|1950|75|1

Tamil|DR|105|75|2|22|2|78|1950|80|1

Gujarati|IA|106|56|1|10|1|79|1950|65|1

Urdu|IA|107|50|2|13|2|69|1950|67|2

Kannada|DR|108|45|1|20|1|76|1950|68|1

Odia|IA|109|37|1|14|1|73|1950|60|1

Malayalam|DR|110|35|1|16|2|97|1950|77|1

Punjabi|IA|111|33|2|9|2|75|1992|70|1

Maithili|IA|112|30|1|12|1|65|2003|40|2

Santali|AST|113|8|2|7|2|55|2003|35|3

Kashmiri|IA|114|7|1|6|2|62|1950|38|3

Nepali|IA|115|6|1|5|1|68|1950|50|2

Konkani|IA|116|4|1|4|2|81|1992|55|2

Dogri|IA|117|3|1|3|2|61|2003|30|3

Sindhi|IA|118|3|0|3|1|75|1967|25|4

Bodo|ST|119|2|1|2|1|60|2003|20|2

Manipuri|ST|120|1.8|1|2|2|70|1992|30|2

Assamese|IA|121|15|1|11|2|72|1950|58|1

Tulu|DR|122|2|0|3|2|69|.|25|3

Bhili|IA|123|9|0|4|1|45|.|15|3

Gondi|DR|124|3|0|6|2|50|.|10|4

Mundari|AST|125|2|0|4|1|40|.|12|3

Khasi|AST|126|1.4|0|2|2|68|.|18|2

Lepcha|ST|127|0.05|0|2|1|55|.|5|4

Mizo|ST|128|0.83|1|2|1|91|.|40|1

Bhutia|ST|129|0.07|0|1|1|53|.|4|3

Nishi|ST|130|0.33|0|2|1|35|.|6|3

;

run;

proc print;run;

Output:

Obs	Language	Family	Lang_ID	Speakers_Millions	Official_States	Dialects	Script_Count	Literacy_Rate	Recognition_Year	Digital_Index	Endanger_Score
1	Hindi	Indo-Aryan	101	568.00	11	23	2	74	1950	88	Safe
2	Bengali	Indo-Aryan	102	97.00	2	18	2	71	1950	84	Safe
3	Marathi	Indo-Aryan	103	83.00	1	15	1	76	1950	72	Safe
4	Telugu	Dravidian	104	82.00	2	21	2	70	1950	75	Safe
5	Tamil	Dravidian	105	75.00	2	22	2	78	1950	80	Safe
6	Gujarati	Indo-Aryan	106	56.00	1	10	1	79	1950	65	Safe
7	Urdu	Indo-Aryan	107	50.00	2	13	2	69	1950	67	Vulnerable
8	Kannada	Dravidian	108	45.00	1	20	1	76	1950	68	Safe
9	Odia	Indo-Aryan	109	37.00	1	14	1	73	1950	60	Safe
10	Malayalam	Dravidian	110	35.00	1	16	2	97	1950	77	Safe
11	Punjabi	Indo-Aryan	111	33.00	2	9	2	75	1992	70	Safe
12	Maithili	Indo-Aryan	112	30.00	1	12	1	65	2003	40	Vulnerable
13	Santali	Austro-Asiatic	113	8.00	2	7	2	55	2003	35	Definitely Endangered
14	Kashmiri	Indo-Aryan	114	7.00	1	6	2	62	1950	38	Definitely Endangered
15	Nepali	Indo-Aryan	115	6.00	1	5	1	68	1950	50	Vulnerable
16	Konkani	Indo-Aryan	116	4.00	1	4	2	81	1992	55	Vulnerable
17	Dogri	Indo-Aryan	117	3.00	1	3	2	61	2003	30	Definitely Endangered
18	Sindhi	Indo-Aryan	118	3.00	0	3	1	75	1967	25	Severely Endangered
19	Bodo	Sino-Tibetan	119	2.00	1	2	1	60	2003	20	Vulnerable
20	Manipuri	Sino-Tibetan	120	1.80	1	2	2	70	1992	30	Vulnerable
21	Assamese	Indo-Aryan	121	15.00	1	11	2	72	1950	58	Safe
22	Tulu	Dravidian	122	2.00	0	3	2	69	.	25	Definitely Endangered
23	Bhili	Indo-Aryan	123	9.00	0	4	1	45	.	15	Definitely Endangered
24	Gondi	Dravidian	124	3.00	0	6	2	50	.	10	Severely Endangered
25	Mundari	Austro-Asiatic	125	2.00	0	4	1	40	.	12	Definitely Endangered
26	Khasi	Austro-Asiatic	126	1.40	0	2	2	68	.	18	Vulnerable
27	Lepcha	Sino-Tibetan	127	0.05	0	2	1	55	.	5	Severely Endangered
28	Mizo	Sino-Tibetan	128	0.83	1	2	1	91	.	40	Safe
29	Bhutia	Sino-Tibetan	129	0.07	0	1	1	53	.	4	Definitely Endangered
30	Nishi	Sino-Tibetan	130	0.33	0	2	1	35	.	6	Definitely Endangered

3. First look—PROC PRINT and PROC SORT

proc sort data=lang_india out=lang_sorted;

   by descending Speakers_Millions;

run;

title "TOP 10 LANGUAGES BY NATIVE SPEAKER POPULATION";

proc print data=lang_sorted (obs=10) label noobs;

   var Language Speakers_Millions Official_States Script_Count;

   label Speakers_Millions = "Millions of Native Speakers";

run;

title;

Output:

TOP 10 LANGUAGES BY NATIVE SPEAKER POPULATION

Language	Millions of Native Speakers	Official_States	Script_Count
Hindi	568	11	2
Bengali	97	2	2
Marathi	83	1	1
Telugu	82	2	2
Tamil	75	2	2
Gujarati	56	1	1
Urdu	50	2	2
Kannada	45	1	1
Odia	37	1	1
Malayalam	35	1	2

4. Macro #1—Reusable descriptives 

%macro meanstat(var=);

   %put NOTE‑: Descriptive statistics for &var ;

   proc means data=lang_india n mean min max maxdec=2;

      var &var ;

   run;

%mend meanstat;

%meanstat(var=Speakers_Millions)

Output:

The MEANS Procedure

Analysis Variable : Speakers_Millions
N	Mean	Minimum	Maximum
30	41.98	0.05	568.00

%meanstat(var=DialectS)         

Output:

The MEANS Procedure

Analysis Variable : Dialects
N	Mean	Minimum	Maximum
30	8.73	1.00	23.00

%meanstat(var=Digital_Index)

Output:

The MEANS Procedure

Analysis Variable : Digital_Index
N	Mean	Minimum	Maximum
30	44.07	4.00	88.00

5. Macro #2—Family filter & dynamic SQL

%macro famview(code=);

   proc sql;

      create  view fam_&code as

      select *

      from   lang_india

      where  Family = "&code";

   quit;

      title "SUMMARY FOR FAMILY &code (Auto‑generated)";

   proc summary data=fam_&code nway;

      var Speakers_Millions Official_States Dialects;

      output out=fam_sum_&code (drop=_type_ _freq_)

             sum= / autoname;

   run;

   

   proc print data=fam_sum_&code noobs label;

   run;

%mend famview;

%famview(code=IA)

Output:

SUMMARY FOR FAMILY IA (Auto-generated)

Speakers_Millions_Sum	Official_States_Sum	Dialects_Sum
1001	26	150

%famview(code=DR)

Output:

SUMMARY FOR FAMILY DR (Auto-generated)

Speakers_Millions_Sum	Official_States_Sum	Dialects_Sum
242	6	88

6. Descriptive PROC MEANS, PROC FREQ, and PROC UNIVARIATE

proc means data=lang_india mean median q1 q3 min max maxdec=1;

   var Speakers_Millions;

   class Family;

run;

Output:

The MEANS Procedure

Analysis Variable : Speakers_Millions
Family	N Obs	Mean	Median	Lower Quartile	Upper Quartile	Minimum	Maximum
Austro-Asiatic	3	3.8	2.0	1.4	8.0	1.4	8.0
Dravidian	6	40.3	40.0	3.0	75.0	2.0	82.0
Indo-Aryan	15	66.7	30.0	6.0	56.0	3.0	568.0
Sino-Tibetan	6	0.8	0.6	0.1	1.8	0.1	2.0

proc freq data=lang_india;

   tables Endanger_Score Family*Endanger_Score / nopercent norow nocol;

run;

Output:

The FREQ Procedure

Endanger_Score	Frequency	Cumulative Frequency
Safe	12	12
Vulnerable	7	19
Definitely Endangered	8	27
Severely Endangered	3	30

Frequency

Table of Family by Endanger_Score Family Endanger_Score Safe Vulnerable Definitely Endangered Severely Endangered Total Austro-Asiatic 0 1 2 0 3 Dravidian 4 0 1 1 6 Indo-Aryan 7 4 3 1 15 Sino-Tibetan 1 2 2 1 6 Total 12 7 8 3 30

proc univariate data=lang_india normal plot;

   var Digital_Index;

   histogram / midpoints=0 to 100 by 20;

   inset n mean std skewness kurtosis / position=ne;

run;

Output:

The UNIVARIATE Procedure

Variable: Digital_Index

Moments
N	30	Sum Weights	30
Mean	44.0666667	Sum Observations	1322
Std Deviation	26.6509149	Variance	710.271264
Skewness	0.02787991	Kurtosis	-1.3801751
Uncorrected SS	78854	Corrected SS	20597.8667
Coeff Variation	60.4786268	Std Error Mean	4.86576909

Basic Statistical Measures
Location		Variability
Mean	44.06667	Std Deviation	26.65091
Median	40.00000	Variance	710.27126
Mode	25.00000	Range	84.00000
		Interquartile Range	48.00000

Note: The mode displayed is the smallest of 3 modes with a count of 2.

Tests for Location: Mu0=0
Test	Statistic		p Value
Student's t	t	9.056465	Pr > |t|	<.0001
Sign	M	15	Pr >= |M|	<.0001
Signed Rank	S	232.5	Pr >= |S|	<.0001

Tests for Normality
Test	Statistic		p Value
Shapiro-Wilk	W	0.936574	Pr < W	0.0736
Kolmogorov-Smirnov	D	0.117243	Pr > D	>0.1500
Cramer-von Mises	W-Sq	0.094867	Pr > W-Sq	0.1290
Anderson-Darling	A-Sq	0.595495	Pr > A-Sq	0.1137

Quantiles (Definition 5)
Level	Quantile
100% Max	88.0
99%	88.0
95%	84.0
90%	78.5
75% Q3	68.0
50% Median	40.0
25% Q1	20.0
10%	8.0
5%	5.0
1%	4.0
0% Min	4.0

Extreme Observations
Lowest		Highest
Value	Obs	Value	Obs
4	29	75	4
5	27	77	10
6	30	80	5
10	24	84	2
12	25	88	1

7. PROC SQL jewels—derived metrics & in‑line functions

proc sql;

   create table lit_mass as

   select Language,

          Speakers_Millions * (Literacy_Rate/100) as Literate_Millions format=8.1,

          Endanger_Score label='Risk'

   from   lang_india

   order by Literate_Millions desc;

quit;

proc print;run;

Output:

Obs	Language	Literate_Millions	Endanger_Score
1	Hindi	420.3	Safe
2	Bengali	68.9	Safe
3	Marathi	63.1	Safe
4	Tamil	58.5	Safe
5	Telugu	57.4	Safe
6	Gujarati	44.2	Safe
7	Urdu	34.5	Vulnerable
8	Kannada	34.2	Safe
9	Malayalam	34.0	Safe
10	Odia	27.0	Safe
11	Punjabi	24.8	Safe
12	Maithili	19.5	Vulnerable
13	Assamese	10.8	Safe
14	Santali	4.4	Definitely Endangered
15	Kashmiri	4.3	Definitely Endangered
16	Nepali	4.1	Vulnerable
17	Bhili	4.1	Definitely Endangered
18	Konkani	3.2	Vulnerable
19	Sindhi	2.3	Severely Endangered
20	Dogri	1.8	Definitely Endangered
21	Gondi	1.5	Severely Endangered
22	Tulu	1.4	Definitely Endangered
23	Manipuri	1.3	Vulnerable
24	Bodo	1.2	Vulnerable
25	Khasi	1.0	Vulnerable
26	Mundari	0.8	Definitely Endangered
27	Mizo	0.8	Safe
28	Nishi	0.1	Definitely Endangered
29	Bhutia	0.0	Definitely Endangered
30	Lepcha	0.0	Severely Endangered

8. Wide‑to‑long pivot—PROC TRANSPOSE for longitudinal modelling

data speakers_hist;

   set lang_india;

   Speakers1951 = Speakers_Millions * 0.45;

   Speakers2001 = Speakers_Millions * 0.82;

   Speakers2011 = Speakers_Millions * 0.95;

run;

proc print;run;

Output:

Obs	Language	Family	Lang_ID	Speakers_Millions	Official_States	Dialects	Script_Count	Literacy_Rate	Recognition_Year	Digital_Index	Endanger_Score	Speakers1951	Speakers2001	Speakers2011
1	Hindi	Indo-Aryan	101	568.00	11	23	2	74	1950	88	Safe	255.600	465.760	539.600
2	Bengali	Indo-Aryan	102	97.00	2	18	2	71	1950	84	Safe	43.650	79.540	92.150
3	Marathi	Indo-Aryan	103	83.00	1	15	1	76	1950	72	Safe	37.350	68.060	78.850
4	Telugu	Dravidian	104	82.00	2	21	2	70	1950	75	Safe	36.900	67.240	77.900
5	Tamil	Dravidian	105	75.00	2	22	2	78	1950	80	Safe	33.750	61.500	71.250
6	Gujarati	Indo-Aryan	106	56.00	1	10	1	79	1950	65	Safe	25.200	45.920	53.200
7	Urdu	Indo-Aryan	107	50.00	2	13	2	69	1950	67	Vulnerable	22.500	41.000	47.500
8	Kannada	Dravidian	108	45.00	1	20	1	76	1950	68	Safe	20.250	36.900	42.750
9	Odia	Indo-Aryan	109	37.00	1	14	1	73	1950	60	Safe	16.650	30.340	35.150
10	Malayalam	Dravidian	110	35.00	1	16	2	97	1950	77	Safe	15.750	28.700	33.250
11	Punjabi	Indo-Aryan	111	33.00	2	9	2	75	1992	70	Safe	14.850	27.060	31.350
12	Maithili	Indo-Aryan	112	30.00	1	12	1	65	2003	40	Vulnerable	13.500	24.600	28.500
13	Santali	Austro-Asiatic	113	8.00	2	7	2	55	2003	35	Definitely Endangered	3.600	6.560	7.600
14	Kashmiri	Indo-Aryan	114	7.00	1	6	2	62	1950	38	Definitely Endangered	3.150	5.740	6.650
15	Nepali	Indo-Aryan	115	6.00	1	5	1	68	1950	50	Vulnerable	2.700	4.920	5.700
16	Konkani	Indo-Aryan	116	4.00	1	4	2	81	1992	55	Vulnerable	1.800	3.280	3.800
17	Dogri	Indo-Aryan	117	3.00	1	3	2	61	2003	30	Definitely Endangered	1.350	2.460	2.850
18	Sindhi	Indo-Aryan	118	3.00	0	3	1	75	1967	25	Severely Endangered	1.350	2.460	2.850
19	Bodo	Sino-Tibetan	119	2.00	1	2	1	60	2003	20	Vulnerable	0.900	1.640	1.900
20	Manipuri	Sino-Tibetan	120	1.80	1	2	2	70	1992	30	Vulnerable	0.810	1.476	1.710
21	Assamese	Indo-Aryan	121	15.00	1	11	2	72	1950	58	Safe	6.750	12.300	14.250
22	Tulu	Dravidian	122	2.00	0	3	2	69	.	25	Definitely Endangered	0.900	1.640	1.900
23	Bhili	Indo-Aryan	123	9.00	0	4	1	45	.	15	Definitely Endangered	4.050	7.380	8.550
24	Gondi	Dravidian	124	3.00	0	6	2	50	.	10	Severely Endangered	1.350	2.460	2.850
25	Mundari	Austro-Asiatic	125	2.00	0	4	1	40	.	12	Definitely Endangered	0.900	1.640	1.900
26	Khasi	Austro-Asiatic	126	1.40	0	2	2	68	.	18	Vulnerable	0.630	1.148	1.330
27	Lepcha	Sino-Tibetan	127	0.05	0	2	1	55	.	5	Severely Endangered	0.023	0.041	0.048
28	Mizo	Sino-Tibetan	128	0.83	1	2	1	91	.	40	Safe	0.374	0.681	0.789
29	Bhutia	Sino-Tibetan	129	0.07	0	1	1	53	.	4	Definitely Endangered	0.032	0.057	0.067
30	Nishi	Sino-Tibetan	130	0.33	0	2	1	35	.	6	Definitely Endangered	0.149	0.271	0.314

proc transpose data=speakers_hist out=speakers_long

   name=Census_Year prefix=Count_;

   by Lang_ID Language Family;

   var Speakers1951 Speakers2001 Speakers2011;

run;

proc print;run;

Output:

Obs	Lang_ID	Language	Family	Census_Year	Count_1
1	101	Hindi	Indo-Aryan	Speakers1951	255.600
2	101	Hindi	Indo-Aryan	Speakers2001	465.760
3	101	Hindi	Indo-Aryan	Speakers2011	539.600
4	102	Bengali	Indo-Aryan	Speakers1951	43.650
5	102	Bengali	Indo-Aryan	Speakers2001	79.540
6	102	Bengali	Indo-Aryan	Speakers2011	92.150
7	103	Marathi	Indo-Aryan	Speakers1951	37.350
8	103	Marathi	Indo-Aryan	Speakers2001	68.060
9	103	Marathi	Indo-Aryan	Speakers2011	78.850
10	104	Telugu	Dravidian	Speakers1951	36.900
11	104	Telugu	Dravidian	Speakers2001	67.240
12	104	Telugu	Dravidian	Speakers2011	77.900
13	105	Tamil	Dravidian	Speakers1951	33.750
14	105	Tamil	Dravidian	Speakers2001	61.500
15	105	Tamil	Dravidian	Speakers2011	71.250
16	106	Gujarati	Indo-Aryan	Speakers1951	25.200
17	106	Gujarati	Indo-Aryan	Speakers2001	45.920
18	106	Gujarati	Indo-Aryan	Speakers2011	53.200
19	107	Urdu	Indo-Aryan	Speakers1951	22.500
20	107	Urdu	Indo-Aryan	Speakers2001	41.000
21	107	Urdu	Indo-Aryan	Speakers2011	47.500
22	108	Kannada	Dravidian	Speakers1951	20.250
23	108	Kannada	Dravidian	Speakers2001	36.900
24	108	Kannada	Dravidian	Speakers2011	42.750
25	109	Odia	Indo-Aryan	Speakers1951	16.650
26	109	Odia	Indo-Aryan	Speakers2001	30.340
27	109	Odia	Indo-Aryan	Speakers2011	35.150
28	110	Malayalam	Dravidian	Speakers1951	15.750
29	110	Malayalam	Dravidian	Speakers2001	28.700
30	110	Malayalam	Dravidian	Speakers2011	33.250
31	111	Punjabi	Indo-Aryan	Speakers1951	14.850
32	111	Punjabi	Indo-Aryan	Speakers2001	27.060
33	111	Punjabi	Indo-Aryan	Speakers2011	31.350
34	112	Maithili	Indo-Aryan	Speakers1951	13.500
35	112	Maithili	Indo-Aryan	Speakers2001	24.600
36	112	Maithili	Indo-Aryan	Speakers2011	28.500
37	113	Santali	Austro-Asiatic	Speakers1951	3.600
38	113	Santali	Austro-Asiatic	Speakers2001	6.560
39	113	Santali	Austro-Asiatic	Speakers2011	7.600
40	114	Kashmiri	Indo-Aryan	Speakers1951	3.150
41	114	Kashmiri	Indo-Aryan	Speakers2001	5.740
42	114	Kashmiri	Indo-Aryan	Speakers2011	6.650
43	115	Nepali	Indo-Aryan	Speakers1951	2.700
44	115	Nepali	Indo-Aryan	Speakers2001	4.920
45	115	Nepali	Indo-Aryan	Speakers2011	5.700
46	116	Konkani	Indo-Aryan	Speakers1951	1.800
47	116	Konkani	Indo-Aryan	Speakers2001	3.280
48	116	Konkani	Indo-Aryan	Speakers2011	3.800
49	117	Dogri	Indo-Aryan	Speakers1951	1.350
50	117	Dogri	Indo-Aryan	Speakers2001	2.460
51	117	Dogri	Indo-Aryan	Speakers2011	2.850
52	118	Sindhi	Indo-Aryan	Speakers1951	1.350
53	118	Sindhi	Indo-Aryan	Speakers2001	2.460
54	118	Sindhi	Indo-Aryan	Speakers2011	2.850
55	119	Bodo	Sino-Tibetan	Speakers1951	0.900
56	119	Bodo	Sino-Tibetan	Speakers2001	1.640
57	119	Bodo	Sino-Tibetan	Speakers2011	1.900
58	120	Manipuri	Sino-Tibetan	Speakers1951	0.810
59	120	Manipuri	Sino-Tibetan	Speakers2001	1.476
60	120	Manipuri	Sino-Tibetan	Speakers2011	1.710
61	121	Assamese	Indo-Aryan	Speakers1951	6.750
62	121	Assamese	Indo-Aryan	Speakers2001	12.300
63	121	Assamese	Indo-Aryan	Speakers2011	14.250
64	122	Tulu	Dravidian	Speakers1951	0.900
65	122	Tulu	Dravidian	Speakers2001	1.640
66	122	Tulu	Dravidian	Speakers2011	1.900
67	123	Bhili	Indo-Aryan	Speakers1951	4.050
68	123	Bhili	Indo-Aryan	Speakers2001	7.380
69	123	Bhili	Indo-Aryan	Speakers2011	8.550
70	124	Gondi	Dravidian	Speakers1951	1.350
71	124	Gondi	Dravidian	Speakers2001	2.460
72	124	Gondi	Dravidian	Speakers2011	2.850
73	125	Mundari	Austro-Asiatic	Speakers1951	0.900
74	125	Mundari	Austro-Asiatic	Speakers2001	1.640
75	125	Mundari	Austro-Asiatic	Speakers2011	1.900
76	126	Khasi	Austro-Asiatic	Speakers1951	0.630
77	126	Khasi	Austro-Asiatic	Speakers2001	1.148
78	126	Khasi	Austro-Asiatic	Speakers2011	1.330
79	127	Lepcha	Sino-Tibetan	Speakers1951	0.023
80	127	Lepcha	Sino-Tibetan	Speakers2001	0.041
81	127	Lepcha	Sino-Tibetan	Speakers2011	0.048
82	128	Mizo	Sino-Tibetan	Speakers1951	0.374
83	128	Mizo	Sino-Tibetan	Speakers2001	0.681
84	128	Mizo	Sino-Tibetan	Speakers2011	0.789
85	129	Bhutia	Sino-Tibetan	Speakers1951	0.032
86	129	Bhutia	Sino-Tibetan	Speakers2001	0.057
87	129	Bhutia	Sino-Tibetan	Speakers2011	0.067
88	130	Nishi	Sino-Tibetan	Speakers1951	0.149
89	130	Nishi	Sino-Tibetan	Speakers2001	0.271
90	130	Nishi	Sino-Tibetan	Speakers2011	0.314

9. PROC TABULATE & PROC REPORT

/* 9A. Summary table—average literacy by family */

proc tabulate data=lang_india f=8.1 order=data;

   class Family;

   var Literacy_Rate Digital_Index;

   table Family,

         Literacy_Rate*Mean

         Digital_Index*Mean;

   label Literacy_Rate='Avg Literacy %'

         Digital_Index='Avg Digital Index';

run;

Output:

	Avg Literacy %	Avg Digital Index
	Mean	Mean
Family	69.7	54.5
Indo-Aryan
Dravidian	73.3	55.8
Austro-Asiatic	54.3	21.7
Sino-Tibetan	60.7	17.5

/* 9B. Styled report for policy brief */

title h=12pt "LANGUAGES AT RISK SCORING ≥3";

proc report data=lang_india nowd split='*';

   column Language Family Speakers_Millions Endanger_Score Literacy_Rate;

   define Language / order width=16;

   define Family   / format=$famfmt. 'Family';

   define Endanger_Score / format=riskfmt. 'Risk';

   define Literacy_Rate / analysis mean 'Lit %';

   compute Endanger_Score;

      if Endanger_Score>=3 then call define(_col_,'style','style={background=lightred}');

   endcomp;

run;

title;

Output:

LANGUAGES AT RISK SCORING =3

Language	Family	Speakers_Millions	Risk	Lit %
Assamese	Indo-Aryan	15	Safe	72
Bengali	Indo-Aryan	97	Safe	71
Bhili	Indo-Aryan	9	Definitely Endangered	45
Bhutia	Sino-Tibetan	0.07	Definitely Endangered	53
Bodo	Sino-Tibetan	2	Vulnerable	60
Dogri	Indo-Aryan	3	Definitely Endangered	61
Gondi	Dravidian	3	Severely Endangered	50
Gujarati	Indo-Aryan	56	Safe	79
Hindi	Indo-Aryan	568	Safe	74
Kannada	Dravidian	45	Safe	76
Kashmiri	Indo-Aryan	7	Definitely Endangered	62
Khasi	Austro-Asiatic	1.4	Vulnerable	68
Konkani	Indo-Aryan	4	Vulnerable	81
Lepcha	Sino-Tibetan	0.05	Severely Endangered	55
Maithili	Indo-Aryan	30	Vulnerable	65
Malayalam	Dravidian	35	Safe	97
Manipuri	Sino-Tibetan	1.8	Vulnerable	70
Marathi	Indo-Aryan	83	Safe	76
Mizo	Sino-Tibetan	0.83	Safe	91
Mundari	Austro-Asiatic	2	Definitely Endangered	40
Nepali	Indo-Aryan	6	Vulnerable	68
Nishi	Sino-Tibetan	0.33	Definitely Endangered	35
Odia	Indo-Aryan	37	Safe	73
Punjabi	Indo-Aryan	33	Safe	75
Santali	Austro-Asiatic	8	Definitely Endangered	55
Sindhi	Indo-Aryan	3	Severely Endangered	75
Tamil	Dravidian	75	Safe	78
Telugu	Dravidian	82	Safe	70
Tulu	Dravidian	2	Definitely Endangered	69
Urdu	Indo-Aryan	50	Vulnerable	69

10. Performance tip—indexing high‑cardinality numeric key

proc datasets lib=work nolist;

   modify lang_india;

   index create Lang_ID / unique;

quit;

Output:

11. Good‑bye block—PROC MEANS with ODS EXCEL

ods excel file="&sysuserhome.\lang_summary.xlsx" options(sheet_name="RiskStats");

proc means data=lang_india n median q1 q3;

   class Endanger_Score;

   var Speakers_Millions;

run;

ods excel close;

Output:

The MEANS Procedure

Analysis Variable : Speakers_Millions
Endanger_Score	N Obs	N	Median	Lower Quartile	Upper Quartile
Safe	12	12	50.5000000	34.0000000	82.5000000
Vulnerable	7	7	4.0000000	1.8000000	30.0000000
Definitely Endangered	8	8	2.5000000	1.1650000	7.5000000
Severely Endangered	3	3	3.0000000	0.0500000	3.0000000

To Visit My Previous E-Commerce Dataset:Click Here

To Visit My Previous Length,Input,Retain Statements:Click Here

To Visit My Previous Urban Traffic Dataset:Click Here

To Visit My Previous Home Energy Consumption Dataset:Click Here

--->PLEASE FOLLOW OUR BLOG FOR MORE INFORMATION.

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

PLEASE FOLLOW OUR TELEGRAM CHANNEL CLICK HERE

PLEASE FOLLOW OUR FACEBOOK PAGE  CLICK HERE

PLEASE FOLLOW OUR INSTAGRAM PAGE CLICK HERE