Panel-ready Data Science track questions for freshers and experienced developers. Practice at Coding Cadre in Faridabad, or Online from Delhi NCR.
The mean is the arithmetic average, the median is the middle value after sorting, and the mode is the most frequent value.
Open the full page for Why, Steps, Example and Key takeaway.
Variance measures how far values spread from the mean by averaging squared deviations.
Open the full page for Why, Steps, Example and Key takeaway.
Standard deviation is the square root of variance, so it is in the same units as the original data.
Open the full page for Why, Steps, Example and Key takeaway.
A percentile is a value below which a given percentage of observations fall.
Open the full page for Why, Steps, Example and Key takeaway.
A population parameter describes the entire group of interest, such as the true mean of all customers.
Open the full page for Why, Steps, Example and Key takeaway.
Probability is a number between 0 and 1 that quantifies how likely an event is under a stated model or long-run frequency.
Open the full page for Why, Steps, Example and Key takeaway.
Independent events do not change each other's probabilities, so P(A and B) equals P(A) times P(B).
Open the full page for Why, Steps, Example and Key takeaway.
The complement of event A is the event that A does not happen, often written A-complement.
Open the full page for Why, Steps, Example and Key takeaway.
For any two events, P(A or B) equals P(A) plus P(B) minus P(A and B) so the overlap is not counted twice.
Open the full page for Why, Steps, Example and Key takeaway.
A probability of 0 means the event is treated as impossible under the model, and 1 means it is treated as certain.
Open the full page for Why, Steps, Example and Key takeaway.
The null hypothesis is the default claim you test, usually that there is no effect or no difference between groups.
Open the full page for Why, Steps, Example and Key takeaway.
The alternative hypothesis is the claim you hope the data support, such as a real lift in conversion.
Open the full page for Why, Steps, Example and Key takeaway.
A Type I error is rejecting a true null hypothesis, a false positive.
Open the full page for Why, Steps, Example and Key takeaway.
A Type II error is failing to reject a false null, a false negative.
Open the full page for Why, Steps, Example and Key takeaway.
A p-value is the probability, under the null hypothesis, of seeing a result at least as extreme as the one you observed.
Open the full page for Why, Steps, Example and Key takeaway.
Alpha is the Type I error rate you are willing to accept, commonly 0.05 in industry tests.
Open the full page for Why, Steps, Example and Key takeaway.
You reject the null at the five percent level because the p-value sits below alpha.
Open the full page for Why, Steps, Example and Key takeaway.
An A/B test randomly assigns users to a control experience and one or more variants, then compares a pre-chosen metric.
Open the full page for Why, Steps, Example and Key takeaway.
The control group estimates what would have happened without the change, including seasonality, marketing, and product-wide trends.
Open the full page for Why, Steps, Example and Key takeaway.
The treatment group receives the new experience, feature, or policy you want to evaluate.
Open the full page for Why, Steps, Example and Key takeaway.