Updated: 3/8/2019

Statistical Measures

Topic
Review Topic
0
0
Questions
11
0
0
Evidence
2
0
0
Standard Deviation vs. Standard Error
  • n = sample size
  • Sigma (σ) = standard deviation
  • SEM = standard error of the mean
    • SEM = σ/√n
    • SEM < σ
    • SEM decreases as n increases
  • z-scores
    • 1 = +/- 1 σ around mean
    • = +/- 2 σ around mean
    • = +/- 3 σ around mean

 

Confidence Interval (CI)
  • Describes the range in which the mean would be expected to fall if the study were performed again and again
    • = range from [mean - Z(SEM)] to [mean + Z(SEM)]
    • 95% CI (alpha = 0.05) is standard 
      • for 95% CI, Z = 1.96
  • Outcomes 
    • if 0 falls within the CI when calculating the difference between 2 variables, H0 is not rejected and the result is not significant
    • if 1 falls within the CI when calculating OR or RR, H0 is not rejected and the result is not significant
  • Significance 
    • statistical significance refers to whether p < 0.05
    • clinical significance requires that a statistically significant result be also clinically meaningful
T-test vs. ANOVA vs. χ2
  • T-test    
    • compares the means of 2 groups on a continuous variable  
  • ANOVA (analysis of variance) 
    • compares the means of 3 or more groups on a continuous variable
  • χ2 ("chi-squared") 
    • tests whether 2 nominal variables are associated
    • used with 2x2 tables
      • e.g., effect of treatment on disease
Correlation Coefficient (r)
  • Pearson coefficient, r, is always between -1 and +1
  • Absolute value indicates strength of correlation between 2 variables 
  • Coefficient of determination = r2
Attributable Risk (AR)
  • AR is incidence in the exposed (Ie) - incidence in the unexposed (Iu) = Ie - Iu 
    • Ie = a/(a+b)
    • Iu = c/(c+d)
    • AR = a/(a+b) - c/(c+d)
  • The AR percent (ARP) is the attributable risk divided by incidence in the exposed (Ie)
    • ARP = 100* (Ie-Iu)/Ie = 100*[a/(a+b) - c/(c+d)]/[a/(a+b)]  
    • note that relative risk (RR) = Ie/Iu = a/(a+b) DIVIDED BY c/(c+d)
    • using math tricks
      • ARP = (RR-1)/RR 
 
 

Please rate topic.

Average 3.6 of 16 Ratings

Thank you for rating! Please vote below and help us build the most advanced adaptive learning platform in medicine

The complexity of this topic is appropriate for?
How important is this topic for board examinations?
How important is this topic for clinical practice?
Questions (11)
Lab Values
Blood, Plasma, Serum Reference Range
ALT 8-20 U/L
Amylase, serum 25-125 U/L
AST 8-20 U/L
Bilirubin, serum (adult) Total // Direct 0.1-1.0 mg/dL // 0.0-0.3 mg/dL
Calcium, serum (Ca2+) 8.4-10.2 mg/dL
Cholesterol, serum Rec: < 200 mg/dL
Cortisol, serum 0800 h: 5-23 μg/dL //1600 h:
3-15 μg/dL
2000 h: ≤ 50% of 0800 h
Creatine kinase, serum Male: 25-90 U/L
Female: 10-70 U/L
Creatinine, serum 0.6-1.2 mg/dL
Electrolytes, serum  
Sodium (Na+) 136-145 mEq/L
Chloride (Cl-) 95-105 mEq/L
Potassium (K+) 3.5-5.0 mEq/L
Bicarbonate (HCO3-) 22-28 mEq/L
Magnesium (Mg2+) 1.5-2.0 mEq/L
Estriol, total, serum (in pregnancy)  
24-28 wks // 32-36 wks 30-170 ng/mL // 60-280 ng/mL
28-32 wk // 36-40 wks 40-220 ng/mL // 80-350 ng/mL
Ferritin, serum Male: 15-200 ng/mL
Female: 12-150 ng/mL
Follicle-stimulating hormone, serum/plasma Male: 4-25 mIU/mL
Female: premenopause: 4-30 mIU/mL
midcycle peak: 10-90 mIU/mL
postmenopause: 40-250
pH 7.35-7.45
PCO2 33-45 mmHg
PO2 75-105 mmHg
Glucose, serum Fasting: 70-110 mg/dL
2-h postprandial:<120 mg/dL
Growth hormone - arginine stimulation Fasting: <5 ng/mL
Provocative stimuli: > 7ng/mL
Immunoglobulins, serum  
IgA 76-390 mg/dL
IgE 0-380 IU/mL
IgG 650-1500 mg/dL
IgM 40-345 mg/dL
Iron 50-170 μg/dL
Lactate dehydrogenase, serum 45-90 U/L
Luteinizing hormone, serum/plasma Male: 6-23 mIU/mL
Female: follicular phase: 5-30 mIU/mL
midcycle: 75-150 mIU/mL
postmenopause 30-200 mIU/mL
Osmolality, serum 275-295 mOsmol/kd H2O
Parathyroid hormone, serume, N-terminal 230-630 pg/mL
Phosphatase (alkaline), serum (p-NPP at 30° C) 20-70 U/L
Phosphorus (inorganic), serum 3.0-4.5 mg/dL
Prolactin, serum (hPRL) < 20 ng/mL
Proteins, serum  
Total (recumbent) 6.0-7.8 g/dL
Albumin 3.5-5.5 g/dL
Globulin 2.3-3.5 g/dL
Thyroid-stimulating hormone, serum or plasma .5-5.0 μU/mL
Thyroidal iodine (123I) uptake 8%-30% of administered dose/24h
Thyroxine (T4), serum 5-12 μg/dL
Triglycerides, serum 35-160 mg/dL
Triiodothyronine (T3), serum (RIA) 115-190 ng/dL
Triiodothyronine (T3) resin uptake 25%-35%
Urea nitrogen, serum 7-18 mg/dL
Uric acid, serum 3.0-8.2 mg/dL
Hematologic Reference Range
Bleeding time 2-7 minutes
Erythrocyte count Male: 4.3-5.9 million/mm3
Female: 3.5-5.5 million mm3
Erythrocyte sedimentation rate (Westergren) Male: 0-15 mm/h
Female: 0-20 mm/h
Hematocrit Male: 41%-53%
Female: 36%-46%
Hemoglobin A1c ≤ 6 %
Hemoglobin, blood Male: 13.5-17.5 g/dL
Female: 12.0-16.0 g/dL
Hemoglobin, plasma 1-4 mg/dL
Leukocyte count and differential  
Leukocyte count 4,500-11,000/mm3
Segmented neutrophils 54%-62%
Bands 3%-5%
Eosinophils 1%-3%
Basophils 0%-0.75%
Lymphocytes 25%-33%
Monocytes 3%-7%
Mean corpuscular hemoglobin 25.4-34.6 pg/cell
Mean corpuscular hemoglobin concentration 31%-36% Hb/cell
Mean corpuscular volume 80-100 μm3
Partial thromboplastin time (activated) 25-40 seconds
Platelet count 150,000-400,000/mm3
Prothrombin time 11-15 seconds
Reticulocyte count 0.5%-1.5% of red cells
Thrombin time < 2 seconds deviation from control
Volume  
Plasma Male: 25-43 mL/kg
Female: 28-45 mL/kg
Red cell Male: 20-36 mL/kg
Female: 19-31 mL/kg
Cerebrospinal Fluid Reference Range
Cell count 0-5/mm3
Chloride 118-132 mEq/L
Gamma globulin 3%-12% total proteins
Glucose 40-70 mg/dL
Pressure 70-180 mm H2O
Proteins, total < 40 mg/dL
Sweat Reference Range
Chloride 0-35 mmol/L
Urine  
Calcium 100-300 mg/24 h
Chloride Varies with intake
Creatinine clearance Male: 97-137 mL/min
Female: 88-128 mL/min
Estriol, total (in pregnancy)  
30 wks 6-18 mg/24 h
35 wks 9-28 mg/24 h
40 wks 13-42 mg/24 h
17-Hydroxycorticosteroids Male: 3.0-10.0 mg/24 h
Female: 2.0-8.0 mg/24 h
17-Ketosteroids, total Male: 8-20 mg/24 h
Female: 6-15 mg/24 h
Osmolality 50-1400 mOsmol/kg H2O
Oxalate 8-40 μg/mL
Potassium Varies with diet
Proteins, total < 150 mg/24 h
Sodium Varies with diet
Uric acid Varies with diet
Body Mass Index (BMI) Adult: 19-25 kg/m2
Calculator

Question locked
Sorry, this question is for
PEAK Premium Subscribers only
Upgrade to PEAK
Question locked
Sorry, this question is for
PEAK Premium Subscribers only
Upgrade to PEAK
Question locked
Sorry, this question is for
PEAK Premium Subscribers only
Upgrade to PEAK

(M1.ST.62) A prospective cohort study was conducted to assess the relationship between LDL and the incidence of heart disease. The patients were selected at random. Results showed a 10-year relative risk (RR) of 3.0 for people with elevated LDL levels compared to individuals with normal LDL levels. The p-value was 0.04 with a 95% confidence interval of 2.0-4.0. According to the study results, what percent of heart disease in these patients can be attributed to elevated LDL? Review Topic

QID: 106444
1

25%

5%

(8/157)

2

33%

22%

(34/157)

3

50%

11%

(17/157)

4

67%

48%

(75/157)

5

100%

10%

(15/157)

M1

Select Answer to see Preferred Response

PREFERRED RESPONSE 4

(M1.ST.62) A prospective cohort study was conducted to assess the relationship between LDL-C and the incidence of heart disease. The patients were selected at random. Results showed a 10-year relative risk (RR) of 2.30 for people with elevated LDL-C levels compared to individuals with normal LDL levels. The p value was 0.04. This study is most likely to have which of the following 95% confidence intervals? Review Topic

QID: 106440
1

1.01-3.70

49%

(19/39)

2

1.00-3.60

10%

(4/39)

3

0.09-3.50

15%

(6/39)

4

0.08-3.40

13%

(5/39)

5

0.07-3.30

3%

(1/39)

M1

Select Answer to see Preferred Response

PREFERRED RESPONSE 1
Question locked
Sorry, this question is for
PEAK Premium Subscribers only
Upgrade to PEAK

(M1.ST.71) A study comparing the efficacy of four different weight loss diets is conducted. The primary outcome is change in weight (in kilograms) after two years. Prior to the study, there was insufficient evidence to conclude that any of the diets were effective. Figure A reports the mean weight change and the 95% confidence intervals (CI) for each of the four diets. Which of the following diets would have a p value < 0.05? Review Topic

QID: 103888
FIGURES:
1

Atkins diet

27%

(10/37)

2

Low fat diet

24%

(9/37)

3

Low carbohydrate diet

8%

(3/37)

4

Zone diet

3%

(1/37)

5

Both the Atkins and the low fat diets

27%

(10/37)

M1

Select Answer to see Preferred Response

PREFERRED RESPONSE 5

(M1.ST.76) You are conducting a systematic review on the effect of a new sulfonylurea for the treatment of type II diabetes. For your systematic review you would like to include 95% confidence intervals for the mean of blood glucose levels in the treatment groups. What further information is necessary to abstract from each of the original papers in order to calculate a 95% confidence interval for each study? Review Topic

QID: 103893
1

Power, standard deviation, mean

12%

(7/57)

2

Power, mean, sample size

2%

(1/57)

3

Power, standard deviation, sample size

16%

(9/57)

4

Standard deviation, mean, sample size

47%

(27/57)

5

Standard deviation, mean, sample size, power

16%

(9/57)

M1

Select Answer to see Preferred Response

PREFERRED RESPONSE 4

(M1.ST.70) Confident of your performance on Step 1 given your extensive utilization of Medbullets, you preemptively start to ponder your future specialty choice. You come across an analysis of lifestyle factors and how they affect medical student specialty choices. Image A depicts two scatter plots comparing the relationship between median income and weekly work hours on the difficulty of matching into specific specialties. Both associations are statistically significant. Which statement best describes the results? Review Topic

QID: 103887
FIGURES:
1

The harder the specialty is to match into, the higher the weekly work hours

0%

(0/13)

2

The easier the specialty is to match into, the higher the median income

0%

(0/13)

3

Weekly work hours has a stronger correlation with matching difficulty than median income

8%

(1/13)

4

Median income has a stronger correlation with matching difficulty than weekly work hours

85%

(11/13)

5

The higher the median income of a specialty the shorter the weekly work hours

8%

(1/13)

M1

Select Answer to see Preferred Response

PREFERRED RESPONSE 4

(M1.ST.78) An investigator is measuring the blood calcium level in a sample of female cross country runners and a control group of sedentary females. If she would like to compare the means of the two groups, which statistical test should she use? Review Topic

QID: 103895
1

t-test

100%

(14/14)

2

ANOVA (Analysis of Variance)

0%

(0/14)

3

Linear regression

0%

(0/14)

4

Chi-square test

0%

(0/14)

5

F-test

0%

(0/14)

M1

Select Answer to see Preferred Response

PREFERRED RESPONSE 1

(M1.ST.74) A cross-sectional study is conducted investigating the effects of low salt diet on blood pressure. Five hundred patients identified as having a low salt diet and 500 patients identified as having a normal (control) diet were enrolled. All participants have their systolic blood pressure measured and the results are presented in Figure A. If the distribution of systolic blood pressure in each group is normal, what is the most appropriate test to determine whether patients on low salt diet have different systolic blood pressure than those on control diet? Review Topic

QID: 103891
FIGURES:
1

Analysis of variance (ANOVA)

0%

(0/21)

2

One-sample t-test

10%

(2/21)

3

Two-sample t-test

67%

(14/21)

4

Paired t-test

19%

(4/21)

5

Chi Square test

5%

(1/21)

M1

Select Answer to see Preferred Response

PREFERRED RESPONSE 3
ARTICLES (2)
Topic COMMENTS (27)
Private Note