Answer keys for Assignment 10: Measurement of study variables (The correct answer is underlined in bold text) 1. In a study, participants are asked to indicate the type of pet they have at home (ex: dog, cat) from a given list. This type of variable is classified as Ordinal Nominal Continuous Discrete 2. In a study on Hypertension, patients are categorised based on their systolic blood pressure as pre-hypertension, Hypertension stage-i and Hypertension stage-ii. What type of variable is this? Qualitative Descriptive Nominal Ordinal 3. Most commonly used measure of central tendency is Mode Median Mean Range 4. First quartile (Q1) is equivalent to percentile 25th 50th 75th 100th 5. The number of children per household is an example of a continuous variable True False 6. Find the median in the following sample of observations: 14, 25, 8, 28,45 28 45 25 24
7. A quick and easy indicator of dispersion is Arithmetic mean Variance Standard deviation Range 8. In the following set of data, what is the mean? 4,1,9,7,3,8,2,6 5 40 10 8 9. The following measure is not influenced by extreme values in a data set Arithmetic Mean Inter-quartile range Range a and c 10. Which of the following statistic does not belong with the others? Range Variance Mode Standard deviation
Answer keys for Assignment 11: Sampling methods (The correct answer is underlined in bold text) 1. The purpose of stratified random sampling is to make sure that The sample is more representative of the target population than the accessible population Every member of the population has an equal chance of being selected for the sample The sample proportionately represents individuals from different subgroups of the population a and b 2. Sampling based upon equal chance of selection is called Stratified random sampling Simple random sampling Systematic sampling Non random sampling 3. A sample needs to be representative of the population True False 4. A researcher wishing to draw a sample from sequentially numbered houses, uses a random starting point and then selects every 7th house, s/he has thus drawn a sample Sequential Systematic Simple random Stratified 5. The following statement is correct regarding sampling error Sampling error is difficult to measure in simple random sampling Sampling error is easy to measure in stratified sampling The magnitude of error can be measured in non- probability samples The magnitude of error can be measured in probability samples 6. The only sampling method that allows to draw valid conclusions about the population is Non-probability sampling Convenience sampling Probability sampling Subjective sampling
7. All the following are true regarding cluster sampling except It needs a complete list of units The sampling unit is group of subjects Sampling error is difficult to measure Resources required are less 8. A method used for selecting sampling units from the sampling frame is called Population design Sampling scheme Sampling distribution Sampling frame 9. Random sampling in probability samples removes the possibility of bias in selection of study subjects True False 10. Methods used in probability samples are Stratified sampling Multi-stage sampling Cluster sampling All the above
Answer keys for Assignment 12: Calculating sample size and power (The correct answer is underlined in bold text) 1. Statistical power is defined as the probability of Accepting a null hypothesis when it is false Rejecting a null hypothesis when it is true Rejecting a null hypothesis when it is false Failing to reject a null hypothesis when it is false 2. The following steps are part of sample size estimation except Identify major study variable Decide on the desired precision of the estimate Adjust for population size Adjust for selection bias 3. A type-ii error occurs when The null hypothesis is rejected when it is false The null hypothesis is not rejected when it is false The null hypothesis is not rejected when it is true The null hypothesis is rejected when it is true 4. Exact calculation of design effect can take place only after study completion True False 5. The power of a study Does not influence the sample size Represented as α 1-β All the above statements are true 6. Population variance can be estimated from A pilot study Reports of previous studies a and b Population variance can t be estimated
7. The recommended minimum level of power is 5% 95% 80% 25% 8. In general, sample size formula takes into account the crude association between exposure and outcome as well as the confounders True False 9. Design effect of more than 1 needs to be considered in studies involving Cluster sampling Simple random sampling Stratified random sampling Non-Probability sampling 10. Which of the following is necessary in sample size determination? Desired confidence level Desired precision Magnitude of the population variance All the above