options fmtsearch=(lib) NODATE;

libname lib "C:\Documents and Settings\Pantelis Andreou\My Documents\Pantelis\Classes\Data\Nshs";

proc format;
  value agef
  		18 - 34   = '18-34'
		35 - 64   = '35-64'
		65 - HIGH = '65+  '
  ;
  value bmif
		.             = "          "
  		0.00  - 18.49 = "Under Wt. "
		18.50 - 24.99 = "Normal Wt."
		25.00 - 29.99 = "Overweight"
		30.00 - HIGH  = "Obese     "
  ;
  value cholf
  		.           = "             "
  		0.00 - 5.19 = "Low Risk     "
		5.20 - 6.19 = "Moderate Risk"
		6.20 - HIGH = "High Risk    "
  ;
  value sexf
        . = "      "
  		1 = "Male  "
		2 = "Female"
  ;
run;

data final;
  set lib.panhs95;
  agegrp  = put(agegroup, agef.);
  bmicat  = put(bmi, bmif.);
  cvdrisk = put(chol, cholf.);
  sex2 = put(sex, sexf.);
run;


/*
Description  
Control Statistical Analysis 
AGREE requests tests and measures of classification agreement 
ALL requests tests and measures of association produced by CHISQ, MEASURES, and CMH 
ALPHA= sets the confidence level for confidence limits 
BDT requests Tarone's adjustment for the Breslow-Day test 
BINOMIAL requests binomial proportion, confidence limits and test for one-way tables 
BINOMIALC requests BINOMIAL statistics with a continuity correction 
CHISQ requests chi-square tests and measures of association based on chi-square 
CL requests confidence limits for the MEASURES statistics 
CMH requests all Cochran-Mantel-Haenszel statistics 
CMH1 requests the CMH correlation statistic, and adjusted relative risks and odds ratios 
CMH2 requests CMH correlation and row mean scores (ANOVA) statistics, and adjusted relative risks and odds ratios 
CONVERGE= specifies convergence criterion to compute polychoric correlation 
FISHER requests Fisher's exact test for tables larger than 2 ×2 
JT requests Jonckheere-Terpstra test 
MAXITER= specifies maximum number of iterations to compute polychoric correlation 
MEASURES requests measures of association and their asymptotic standard errors 
MISSING treats missing values as nonmissing 
PLCORR requests polychoric correlation 
RELRISK requests relative risk measures for 2 ×2 tables 
RISKDIFF requests risks and risk differences for 2 ×2 tables 
RISKDIFFC requests RISKDIFF statistics with a continuity correction 
SCORES= specifies the type of row and column scores 
TESTF= specifies expected frequencies for a one-way table chi-square test 
TESTP= specifies expected proportions for a one-way table chi-square test 
TREND requests Cochran-Armitage test for trend 
Control Additional Table Information 
CELLCHI2 displays each cell's contribution to the total Pearson chi-square statistic 
CUMCOL displays the cumulative column percentage in each cell 
DEVIATION displays the deviation of the cell frequency from the expected value for each cell 
EXPECTED displays the expected cell frequency for each cell 
MISSPRINT displays missing value frequencies 
SPARSE lists all possible combinations of variable levels even when a combination does not occur 
TOTPCT displays percentage of total frequency on n-way tables when n>2 
Control Displayed Output 
CONTENTS= specifies the HTML contents link for crosstabulation tables 
CROSSLIST displays crosstabulation tables in ODS column format 
FORMAT= formats the frequencies in crosstabulation tables 
LIST displays two-way to n-way tables in list format 
NOCOL suppresses display of the column percentage for each cell 
NOCUM suppresses display of cumulative frequencies and cumulative percentages in one-way frequency tables and in list format 
NOFREQ suppresses display of the frequency count for each cell 
NOPERCENT suppresses display of the percentage, row percentage, and column percentage in crosstabulation tables, or percentages and cumulative percentages in one-way frequency tables and in list format 
NOPRINT suppresses display of tables but displays statistics 
NOROW suppresses display of the row percentage for each cell 
NOSPARSE suppresses zero cell frequencies in the list display and in the OUT= data set when ZEROS is specified 
NOWARN suppresses log warning message for the chi-square test 
PRINTKWT displays kappa coefficient weights 
SCOROUT displays the row and the column scores 
Create an Output Data Set 
OUT= specifies an output data set to contain variable values and frequency counts 
OUTCUM includes the cumulative frequency and cumulative percentage in the output data set for one-way tables 
OUTEXPECT includes the expected frequency of each cell in the output data set 
OUTPCT includes the percentage of column frequency, row frequency, and two-way table frequency in the output data set 
*/
/*
Exact Statistics Computed 
AGREE  McNemar's test for 2 ×2 tables, simple kappa coefficient, and weighted kappa coefficient 
BINOMIAL  binomial proportion test for one-way tables 
CHISQ  chi-square goodness-of-fit test for one-way tables; Pearson chi-square, likelihood-ratio chi-square, and Mantel-Haenszel chi-square tests for two-way tables 
COMOR  confidence limits for the common odds ratio for h ×2 ×2 tables; common odds ratio test 
FISHER  Fisher's exact test 
JT  Jonckheere-Terpstra test 
KAPPA  test for the simple kappa coefficient 
LRCHI  likelihood-ratio chi-square test 
MCNEM  McNemar's test 
MEASURES  tests for the Pearson correlation and the Spearman correlation, and the odds ratio confidence limits for 2 ×2 tables 
MHCHI  Mantel-Haenszel chi-square test 
OR  confidence limits for the odds ratio for 2 ×2 tables 
PCHI  Pearson chi-square test 
PCORR  test for the Pearson correlation coefficient 
SCORR  test for the Spearman correlation coefficient 
TREND  Cochran-Armitage test for trend 
WTKAP  test for the weighted kappa coefficient 
*/ 

/*
Procedures That Support the WEIGHT Statement 
CORR
FREQ
MEANS/SUMMARY
REPORT
STANDARD
TABULATE
UNIVARIATE
Note:   In PROC FREQ, the value of the variable in the WEIGHT statement represents the frequency of 
occurrence for each observation. See the PROC FREQ documentation for more information.  
*/



/*
Descriptive statistic keywords 
COLPCTN PCTSUM 
COLPCTSUM RANGE 
CSS REPPCTN 
CV REPPCTSUM 
KURTOSIS | KURT ROWPCTN 
LCLM ROWPCTSUM 
MAX SKEWNESS | SKEW 
MEAN STDDEV|STD 
MIN STDERR 
N SUM 
NMISS SUMWGT 
PAGEPCTN UCLM 
PAGEPCTSUM USS 
PCTN VAR 
Quantile statistic keywords 
MEDIAN|P50 Q3|P75 
P1 P90 
P5 P95 
P10 P99 
Q1|P25 QRANGE 
Hypothesis testing keywords 
PROBT T 
*/

ods pdf file="C:\Documents and Settings\Pantelis Andreou\My Documents\Biostats\Bcs\Shrug\Proc Frequency Examples.pdf";

proc tabulate data=final order=data;
  class hyper region;
  weight pwgtq;
  tables hyper, region="Region of Residence (%)"*pctn<hyper>=""  / row=float rts=25;
TITLE1 "Example 1:  Simple";
TITLE2 "Hypertension risk by region - showing column percent/Wrong weights";
run;

proc freq data=final order=data;
weight pwgtq;
tables hyper*region/chisq nofreq norow nopercent;
exact chisq;
label region="Region of Residence (%)";
TITLE1 "Example 1:  Simple";
TITLE2 "Hypertension risk by region - showing column percent";
run;

proc tabulate data=final order=data;
  class hyper region;
  freq   pwgtq;
  weight pwgtq;
  tables hyper, region="Region of Residence (%)"*pctn<hyper>=""  / row=float rts=25;
TITLE1 "Example 1:  Simple";
TITLE2 "Hypertension risk by region - showing column percent/Right weights";
run;

proc tabulate data=final order=data;
  class bmicat sex2 agegrp;
  freq pwgtq;
  weight pwgtq;
  tables sex2=""*agegrp=""*pctn<bmicat>="", bmicat="BMI Distribution (%)" / row=float rts=25;
TITLE1 "Example 2: A little more complicated";
TITLE2 "Body mass index distribution by sex and age group - showing row percent/Right weights";
run;

proc freq data=final order=data;
weight pwgtq;
tables sex2*agegrp*bmicat/ nofreq nocol nopercent out=ex2 sparse outpct;
label bmicat="BMI Distribution (%)";
TITLE1 "Example 2: A little more complicated";
TITLE2 "Body mass index distribution by sex and age group - showing row percent";
run;

proc print data=ex2;
run;

*title1;
*title2;

ods pdf close;