Evidence-Based Practice: cram pack

Formula sheets, the key method steps for every topic and 8 practice problems, with full solutions at the back.

New problemsBack to the course

In the print window, choose “Save as PDF” to keep a copy on your device.

1Formulas and methods

Evidence-based practice statistics

Sensitivity and specificity
Se = a/(a + c), Sp = d/(b + d)
Predictive values
PPV = a/(a + b), NPV = d/(c + d)
Accuracy
(a + d)/n
Likelihood ratios
LR+ = Se/(1 − Sp), LR− = (1 − Se)/Sp
PPV at prevalence p
Se·p / (Se·p + (1 − Sp)(1 − p))
Odds
odds = p/(1 − p); p = odds/(1 + odds); post-test odds = pre-test odds × LR
Risk measures
RR = EER/CER, ARR = CER − EER, RRR = ARR/CER
Number needed to treat
NNT = 1/ARR, rounded up; NNH = 1/(EER − CER)
Odds ratio
OR = ad/(bc)
Incidence rate
new cases / person-time

Method

  1. Draw the 2 × 2 table and label a, b, c and d before you calculate.
  2. Read sensitivity and specificity down the columns, predictive values along the rows.
  3. For another prevalence, imagine 10 000 people and fill the table with Se, Sp and the prevalence.
  4. For a likelihood ratio, convert the probability to odds, multiply, and convert back.
  5. For a trial, find EER and CER first; then RR = EER/CER, ARR = CER − EER and NNT = 1/ARR rounded up.

Descriptive statistics

Mean
x̄ = Σx/n
Sample standard deviation
s = √(Σ(x − x̄)²/(n − 1))
Median
middle value of the sorted data
z-score
z = (x − μ)/σ
Normal distribution
68% within ±1σ, 95% within ±2σ

Confidence intervals

σ known
x̄ ± z·σ/√n
σ unknown
x̄ ± t·s/√n, df = n − 1
Critical z
90%: 1.645, 95%: 1.96, 99%: 2.576
Sample size
n = (z·σ/E)², rounded up

Method

  1. Decide between z (population σ known) and t (only the sample s, with n − 1 degrees of freedom).
  2. Find the critical value for the confidence level.
  3. Margin of error: E = critical value × standard deviation/√n.
  4. Interval: x̄ ± E.

Hypothesis tests & confidence intervals

z-test for a mean
z = (x̄ − μ0)/(σ/√n)
t-test for a mean
t = (x̄ − μ0)/(s/√n), df = n − 1
Two-sided at 5%
reject H0 if |z| > 1.96
Confidence interval
x̄ ± z·σ/√n

Method

  1. State H₀ and H₁ and decide whether the test is one- or two-sided.
  2. Calculate the test statistic: (x̄ − μ₀)/(σ/√n), or with s and t.
  3. Compare with the critical value, or find the p-value.
  4. Reject H₀ if the statistic is beyond the critical value (p below α), and state the conclusion in words.

2Practice problems

1.Evidence-based practice statisticsMedium
eventno eventtotaltreatment35215250abcontrol4684130cd

Practice exercise (made-up values, not clinical guidance). In a randomised trial, 250 patients received a new treatment and 130 received the control treatment. The table shows how many in each group had the outcome (an unwanted event such as a stroke). Find the number needed to treat NNT to prevent one event. Round up to a whole number of patients.

treatment: 35/250control: 46/130
NNT =
2.Evidence-based practice statisticsHard
testdisease presentdisease absenttotalpositive?negativetotal10 000

Practice exercise (made-up values, not clinical guidance). 10 000 people are screened with a test of sensitivity 75% and specificity 88%. The prevalence of the disease is 22%. How many true-positive results TP are expected?

N = 10 000p = 22%Se = 75%Sp = 88%
TP =
3.Descriptive statisticsMedium
202530354045

Find the sample standard deviation s of the data: 28, 49, 48, 20, 20.

n = 5
s =
4.Descriptive statisticsHard
z −2−1012

A quantity is normally distributed with mean 60 and standard deviation 10. What proportion P of values is above 48?

μ = 60σ = 10x = 48
P =
5.Confidence intervalsMedium
n = 7, sd​ = 6.10L = ?Ud̄ = 9.3E90%

The blood pressure of 7 patients is measured before and after a treatment. The differences d = before − after (mmHg) have mean 9.3 and standard deviation 6.1. Find the lower limit of the 90% confidence interval for the mean difference.

n = 7d̄ = 9.3sd = 6.190%t(6) = 1.943
lower limit = mmHg
6.Confidence intervalsHard
σ = 17, n = ?x̄ − Ex̄ + Ex̄E = 199%

The population standard deviation is 17. How large a sample n do you need so that a 99% confidence interval for the mean has a margin of error of at most 1?

σ = 17E = 199%
n =
7.Hypothesis tests & confidence intervalsMedium
−2.08p = ?

The mean of a population is claimed to be 500; the population standard deviation is known to be 2.5. A random sample of 25 observations has a mean of 498.96. Test H₀: μ = 500 against H₁: μ < 500. Find the p-value p.

μ₀ = 500σ = 2.5n = 25x̄ = 498.96H₁: μ < μ₀
p =
8.Hypothesis tests & confidence intervalsHard
H₀H₁μ₀x̄cμ₀ + 4α = 0.01βσ = 26, power 90%, n = ?

A one-sided z test at α = 0.01 must detect a shift of the mean of 4 units with a power of 90%. The standard deviation is 26. Find the minimum sample size n.

α = 0.01power = 90%δ = 4σ = 26zα = 2.326zβ = 1.282
n =

3Solutions

1.Evidence-based practice statistics

Answer: NNT = 5

Likelihood ratios and risk measures: LR+ = sensitivity/(1 − specificity), LR− = (1 − sensitivity)/specificity. In a trial, EER and CER are the event rates with and without treatment: RR = EER/CER, ARR = CER − EER, RRR = ARR/CER and NNT = 1/ARR, rounded up. In a case-control study only the odds ratio OR = ad/(bc) can be used. An incidence rate = new cases/person-time.

Event rates

EER = 35/250 = 0.14
CER = 46/130 = 0.3538

Number needed to treat

ARR = 0.3538 − 0.14 = 0.2138
NNT = 1/0.2138 = 4.676 → 5

Answer

NNT = 5

Treating 5 patients prevents about one event.

2.Evidence-based practice statistics

Answer: TP = 1650

Predictive values depend on prevalence: PPV = Se·p/(Se·p + (1 − Sp)(1 − p)) and NPV = Sp(1 − p)/(Sp(1 − p) + (1 − Se)p). With likelihood ratios: pre-test odds = p/(1 − p), post-test odds = pre-test odds × LR, probability = odds/(1 + odds). For a population of N, true positives = N·p·Se and false positives = N·(1 − p)·(1 − Sp). NNT = 1/(CER × RRR), rounded up.

With and without the disease

10 000·0.22 = 2200
10 000 − 2200 = 7800

True positives

TP = 2200·0.75 = 1650

Answer

TP = 1650
3.Descriptive statistics

Answer: s = 14.53

Descriptive statistics: the mean is the sum divided by n; the median is the middle value of the sorted data (the average of the two middle values when n is even). The sample standard deviation is s = √(Σ(x − x̄)²/(n − 1)). A z-score z = (x − μ)/σ says how many standard deviations a value lies from the mean.

Mean

x̄ = 165/5 = 33

Squared deviations

Σ(x − x̄)² = (−5)² + 16² + 15² + (−13)² + (−13)² = 844

Standard deviation

s = √(844/4) = 14.53

Answer

s = 14.53
4.Descriptive statistics

Answer: P = 0.8849

Descriptive statistics: the mean is the sum divided by n; the median is the middle value of the sorted data (the average of the two middle values when n is even). The sample standard deviation is s = √(Σ(x − x̄)²/(n − 1)). A z-score z = (x − μ)/σ says how many standard deviations a value lies from the mean.

Standardise

z = −1.2

Standard normal table

Φ(−1.2) = 0.1151
P = 1 − 0.1151 = 0.8849

Answer

P = 0.8849
5.Confidence intervals

Answer: lower limit = 4.82 mmHg

Interval for a difference: estimate ± critical value × standard error. For two independent means with known σ: SE = √(σ₁²/n₁ + σ₂²/n₂) and z. With equal unknown variances: pooled s_p and t with n₁ + n₂ − 2 degrees of freedom. For paired data, work with the differences: d̄ ± t·s_d/√n.

Critical value

df = 6, t = 1.943

Margin of error

E = 1.943·6.1/√7 = 4.48

Interval

9.3 ± 4.48 → [4.82, 13.78]

Answer

lower limit = 4.82 mmHg
6.Confidence intervals

Answer: n = 1918

Confidence interval for a mean: x̄ ± margin of error. With a known population σ the margin is z·σ/√n; with only the sample standard deviation s, use t with n − 1 degrees of freedom: t·s/√n. Critical values: z = 1.645 (90%), 1.96 (95%), 2.576 (99%). To get a margin E or smaller, you need n ≥ (z·σ/E)², rounded up.

Solve for n

n = (2.576·17/1)² = 1918

Round up

A sample size is a whole number, and rounding down would make the margin too large.

n = 1918

Answer

n = 1918
7.Hypothesis tests & confidence intervals

Answer: p = 0.01876

Hypothesis test: the test statistic = (estimate − value under H₀)/(standard error under H₀). The p-value is the probability, assuming H₀ is true, of a statistic at least as extreme as the one observed: the area in one tail for a one-sided H₁, twice the tail area for a two-sided H₁. Reject H₀ when p ≤ α.

Test statistic

SE = σ/√n = 2.5/√25 = 0.5
z = (498.96 − 500)/0.5 = −2.08

Tail area

Φ(2.08) = 0.9812
1 − Φ(2.08) = 0.0188

p-value

p = 0.01876

Answer

p = 0.01876

p ≤ 0.05, so H₀ is rejected at the 5% level.

8.Hypothesis tests & confidence intervals

Answer: n = 550

Sample size for a test: to detect a true shift δ with power 1 − β in a one-sided z test at level α, the standard error must satisfy δ = (z_α + z_β)·σ/√n, so n = ((z_α + z_β)·σ/δ)², rounded up.

Solve for n

n = ((2.326 + 1.282)·26/4)² = 550

Round up

n = 550

Answer

n = 550

ExamProblems · examproblems.com/courses/evidence-based-practice