Summary: Advanced Statistics Drug Innovation

Read the summary and the most important questions on Advanced statistics DRUG INNOVATION

• 1 Refresher: hypothesis testing, t-procedures (t-tests and confidence interval estimation)

  This is a preview. There are 12 more flashcards available for chapter 1
  Show more cards here

• What does the p-value represent under a distribution curve

  The p-value is the area under the sampling distribution curve in the tail(s) beyond the observed test statistic, assuming the null hypothesis is true.

• 2 Sample size calculations for 1-sample, 2-sample or paired data studies using t-procedures; Wilcoxon's non-parametric tests

  This is a preview. There are 10 more flashcards available for chapter 2
  Show more cards here

• What is 1-alfa interval for the population mean my?

  Zie afbeelding

• What is the difference between a wilcoxon rank sum test and a wilcoxon signed rank test?

  The wilcoxon  rank-sum test (also called Mann-Whitney U test) compares two independent groups. The wilcoxon signed-rank test compares two paired samples

• 3 One proportion: Binomial test, confidence interval for one proportion (+required sample size) Comparing two proportions: Fisher's exact test, confidence interval for proportion difference

  This is a preview. There are 9 more flashcards available for chapter 3
  Show more cards here

• What is a Fisher exact test?

  De Fisher exact test is een statistische toets die je gebruikt om te onderzoeken of er een verband is tussen twee categorische variabelen, meestal in een 2×2 tabel.

• 4 Chi-squared tests for goodness of fit, for independence/association, and for homogeneity. Correlation.

  This is a preview. There are 7 more flashcards available for chapter 4
  Show more cards here

• What is the checked with following diagnostic plot? Would you say the assumption is reasonably met?

  ssumption of constant variance/spread/standard deviation
  assumption is reasonable, because the spread in residuals is similar across the

• 5 Simple linear regression: model, meaning of model parameters, estimation, testing, goodness of fit, checking model assumptions.

  This is a preview. There are 10 more flashcards available for chapter 5
  Show more cards here

• What does epsilon stand for in a simple linear regression?

  Epsilon in a simple linear regression stands for all the factors that influence y but are not predicted by the model

• What means absolute t in r studio output?

  Absolute t in r studio output indicates 2 tailed p-value

• 6 Multiple linear regression I: as simple linear regression and more (F-test for model, t-test / confidence interval for one regression coefficient)

  This is a preview. There are 14 more flashcards available for chapter 6
  Show more cards here

• What is multiple linear regression?

  Multiple linear regression is a statistical technique for studying relationships, usually between quantitative variables. The variation in measurements on a response variable y is explained by variation in a number of x-variables
  
  One y, multiple x

• Waarvoor staat de epsilon in de formula for multiple regression?

  De epsilon in de formula for multiple regression staat voor random error term. Random error term staat voor alles wat het model niet kan uitleggen, such as unknown variabels or natural randomness

• What is the standard assumption in multiple regression?

  Each observation has a random error term that is independent and normally distributed around zero with equal variance. I.i.d. Means independent and identically distributed