STATISTICS

STATISTICS

1. SIGNFICANCE TESTS

   • PARAMETRIC
     • SOMETHING THAT CAN BE MEASURED, USUALLY NORMALLY DISTRIBUTED
     • STUDENT'S T-TEST
       • PAIRED OR UNPAIRED
     • PEARSON'S PRODUCT-MOMENT COEFFICIENT
       • CORRELATION
   • NON-PARAMETRIC
     • MANN-WHITNEY U TEST
       • UNPAIRED DATA
     • WILCOXON SIGNED-RANK TEST
       • COMPARES TWO SETS OF OBSERVATIONS ON A SINGLE SAMPLE
     • CHI-SQUARED TEST
       • COMPARE PROPORTIONS/ PERCENTAGES
     • SPEARMAN, KENDAL RANK
       • CORRELATION

2. NUMBERS NEEDED TO TREAT

   • HOW MANY PATIENTS WOULD REQUIRE AN INTERVENTION TO REDUCE THE EXPECTED NUMBER OF OUTCOMES BY ONE
   • 1/ (ABSOLUTE RISK REDUCTION)
     • ABSOLUTE RISK REDUCTION
       • CHANGE IN RISK OF AN OUTCOME OF GIVEN TREATMENT IN RELATION TO THE COMPARISON TREATMENT
       • EXPERIMENTAL EVENT RATE: EER= (NUMBER WHO HAD PARTICULAR OUTCOME WITH INTERVENTION) / TOTAL NUMBER WHO HAD TREATMENT
       • CONTROL EVENT RATE: CER= (NUMBER WHO HAD PARTICULAR OUTCOME WITH CONTROL) / (TOTAL NUMBER WHO HAD THE CONTROL)
       • IF OUTCOME OF STUDY IS UNDESIRABLE: CER - EER
       • IF OUTCOME OF STUDY IS DESIRABLE: EER - CER

3. CONFOUNDING

   • VARIABLE WHICH CORRELATES WITH OTHER VARIABLES IN A STUDY, LEADING TO SPURIOUS RESULTS
   • IN ANALYSIS STAGE OF EXPERIMENT: CONTROLLED BY STRATIFICATION

4. SCREENING

   • SENSITIVITY
     • TP / (TP + FN)
   • SPECIFICITY
     • TN / (TN + FP)
   • POSITIVE PREDICTIVE VALUE
     • TP / (TP + FP)
     • THE CHANCE THAT THE PATIENT HAS THE CONDITION IF THE DIAGNOSTIC TEST IS POSITIVE
   • NEGATIVE PREDICTIVE VALUE
     • THE CHANCE THE PATIENT DOES NOT HAVE THE CONDITION IF THE DIAGNOSTIC TEST IS NEGATIVE
     • TN / (TN + FN)
   • LIKELIHOOD RATIO FOR A POSITIVE TEST RESULT
     • SENSITIVITY / (1 - SPECIFICITY)
     • HOW MUCH ODDS OF DISEASE INCREASE WHEN TEST IS POSITIVE
   • LIKELIHOOD RATIO FOR A NEGATIVE TEST RESULT
     • HOW MUCH THE ODDS OF THE DISEASE DECREASE WHEN A TEST IS NEGATIVE
     • 1 - SENSITIVITY) / SPECIFICITY
   • WILSON AND JUNGER CRITERIA
     • CONDITION SHOULD BE IMPORTANT PUBLIC HEALTH PROBLEM
     • SHOULD BE ACCEPTABLE TREATMENT FOR PATIENTS
     • FACILITIES FOR DIAGNOSIS AND TREATMENT SHOULD BE AVAILABLE
     • SHOULD BE A RECOGNISED LATENT OR EARLY SYMPTOMATIC STAGE
     • NATURAL HISTORY OF DISEASE UNDERSTOOD
     • TEST OR EXAMINATION ACCEPTABLE TO POPULATION
     • AGREED POLICY ON WHOM TO TREAT
     • COST EFFICIENT
     • CASE FINDING SHOULD BE CONTINUOUS, NOT ONCE AND FOR ALL

5. SKEWED DATA

   • NORMAL DISTRIBUTION: MODE=MEAN=MEDIAN
   • POSITIVELY (RIGHT) SKEWED DATA: MEAN>MEDIAN>MODE
   • NEGATIVELY(LEFT) SKEWED DATA: MODE>MEDIAN>MEAN

6. SCREENING