Statistics in medicine though only a few centuries old is indispensible. Although clinicians fear statistics it is easy to understand as it only needs high school level arithmetic. A researcher should be familiar with about three dozen statistical tests. A clinician reader needs to know only about a dozen. Computer software has made our task simple. Biostatistician can work out the sample size required to be studied. Alpha or type I error is the probability of falsely rejecting a null hypothesis and is usually set at 5% while beta or type II error is the probability of wrongly accepting a null hypothesis and is usually set at 10% or even higher. Power of a study is its ability to find a difference should it actually exists and should be at least 80%. Probability is the fraction of times you expect to see an event occurring in many trials while odds are the probability of the event occurring divided by the probability of its not occurring. Most biological values are distributed equally on either side of the mean. These variable values of several individuals can be plotted as a histogram giving a normal or Gaussian distribution and two standard deviations on either side of the mean cover 95% of the values. The mean values of multiple samples studied from the same population also have a normal distribution and the standard deviation of these means is called standard error of the means. Percentiles and quartiles are commonly used for quantitative or measured data. P-values should always be accompanied by confidence intervals and confidence limits. Association is the relationship between two events. It is represented by risk and odds of the two events. Basic concepts of risk ratio and odds ratio are easy to grasp. Risk is the occurrence of an event irrespective of its nature or severity. Risk is measured by absolute risk, absolute risk reduction or risk difference, relative risk reduction, number needed to treat and number needed to harm. Correlation is relationship or association between two measurable variables and the degree of relationship is called correlation coefficient. Correlation can be positive, negative or none. Regression, a statistical tool, is employed to explore the relationship between variables. Regression can be linear, logistic or multiple. Survival studies are important in clinical medicine. They are time to event analysis and the data is presented as survival curve or as Kaplan-Meier graph. Log rank test is used to compare the outcome in two groups. Choice of an appropriate statistical test is very important.