ASA Connect

I apologize if this is a straight forward question, but it doesn't seem to fit into any formula that I am aware of.

I have a situation where I have a population of x observations.  I am not investigating a quantitative feature but rather something qualitative. Since there is no specific quantitative parameter or metric that I am investigating, it seems to me that effect size and standard power formulas aren't applicable.

In my particular case, upon examining these observations, we found that their time frame was much longer not only of what was expected but also what logically makes sense. We thus want to go back and dig into them to answer the question of why were they so long. It's not practical to review and research all of them, so I plan on taking a random sample.  I don't have a good hypothesis as to what the possible explanation may be and it's quite possible that there are multiple explanations. 

My question is how large do I need my random sample to be to ensure that my results are representative of my population?

In this particular case, I have 112 observations, but I'd appreciate feedback in general of how to determine the appropriate size of the random sample in such a case to be confident that it is representative of the population.

Thank you,

Jonathan Burns

I apologize if this is a straight forward question, but it doesn't seem to fit into any formula that I am aware of.

I have a situation where I have a population of x observations.  I am not investigating a quantitative feature but rather something qualitative. Since there is no specific quantitative parameter or metric that I am investigating, it seems to me that effect size and standard power formulas aren't applicable.

In my particular case, upon examining these observations, we found that their time frame was much longer not only of what was expected but also what logically makes sense. We thus want to go back and dig into them to answer the question of why were they so long. It's not practical to review and research all of them, so I plan on taking a random sample.  I don't have a good hypothesis as to what the possible explanation may be and it's quite possible that there are multiple explanations. 

My question is how large do I need my random sample to be to ensure that my results are representative of my population?

In this particular case, I have 112 observations, but I'd appreciate feedback in general of how to determine the appropriate size of the random sample in such a case to be confident that it is representative of the population.

Thank you,

Jonathan Burns

I apologize if this is a straight forward question, but it doesn't seem to fit into any formula that I am aware of.

I have a situation where I have a population of x observations.  I am not investigating a quantitative feature but rather something qualitative. Since there is no specific quantitative parameter or metric that I am investigating, it seems to me that effect size and standard power formulas aren't applicable.

In my particular case, upon examining these observations, we found that their time frame was much longer not only of what was expected but also what logically makes sense. We thus want to go back and dig into them to answer the question of why were they so long. It's not practical to review and research all of them, so I plan on taking a random sample.  I don't have a good hypothesis as to what the possible explanation may be and it's quite possible that there are multiple explanations. 

My question is how large do I need my random sample to be to ensure that my results are representative of my population?

In this particular case, I have 112 observations, but I'd appreciate feedback in general of how to determine the appropriate size of the random sample in such a case to be confident that it is representative of the population.

Thank you,

Jonathan Burns

I apologize if this is a straight forward question, but it doesn't seem to fit into any formula that I am aware of.

I have a situation where I have a population of x observations.  I am not investigating a quantitative feature but rather something qualitative. Since there is no specific quantitative parameter or metric that I am investigating, it seems to me that effect size and standard power formulas aren't applicable.

In my particular case, upon examining these observations, we found that their time frame was much longer not only of what was expected but also what logically makes sense. We thus want to go back and dig into them to answer the question of why were they so long. It's not practical to review and research all of them, so I plan on taking a random sample.  I don't have a good hypothesis as to what the possible explanation may be and it's quite possible that there are multiple explanations. 

My question is how large do I need my random sample to be to ensure that my results are representative of my population?

In this particular case, I have 112 observations, but I'd appreciate feedback in general of how to determine the appropriate size of the random sample in such a case to be confident that it is representative of the population.

Thank you,

Jonathan Burns

I apologize if this is a straight forward question, but it doesn't seem to fit into any formula that I am aware of.

I have a situation where I have a population of x observations.  I am not investigating a quantitative feature but rather something qualitative. Since there is no specific quantitative parameter or metric that I am investigating, it seems to me that effect size and standard power formulas aren't applicable.

In my particular case, upon examining these observations, we found that their time frame was much longer not only of what was expected but also what logically makes sense. We thus want to go back and dig into them to answer the question of why were they so long. It's not practical to review and research all of them, so I plan on taking a random sample.  I don't have a good hypothesis as to what the possible explanation may be and it's quite possible that there are multiple explanations. 

My question is how large do I need my random sample to be to ensure that my results are representative of my population?

In this particular case, I have 112 observations, but I'd appreciate feedback in general of how to determine the appropriate size of the random sample in such a case to be confident that it is representative of the population.

Thank you,

Jonathan Burns

I apologize if this is a straight forward question, but it doesn't seem to fit into any formula that I am aware of.

I have a situation where I have a population of x observations.  I am not investigating a quantitative feature but rather something qualitative. Since there is no specific quantitative parameter or metric that I am investigating, it seems to me that effect size and standard power formulas aren't applicable.

In my particular case, upon examining these observations, we found that their time frame was much longer not only of what was expected but also what logically makes sense. We thus want to go back and dig into them to answer the question of why were they so long. It's not practical to review and research all of them, so I plan on taking a random sample.  I don't have a good hypothesis as to what the possible explanation may be and it's quite possible that there are multiple explanations. 

My question is how large do I need my random sample to be to ensure that my results are representative of my population?

In this particular case, I have 112 observations, but I'd appreciate feedback in general of how to determine the appropriate size of the random sample in such a case to be confident that it is representative of the population.

Thank you,

Jonathan Burns

I apologize if this is a straight forward question, but it doesn't seem to fit into any formula that I am aware of.

I have a situation where I have a population of x observations.  I am not investigating a quantitative feature but rather something qualitative. Since there is no specific quantitative parameter or metric that I am investigating, it seems to me that effect size and standard power formulas aren't applicable.

In my particular case, upon examining these observations, we found that their time frame was much longer not only of what was expected but also what logically makes sense. We thus want to go back and dig into them to answer the question of why were they so long. It's not practical to review and research all of them, so I plan on taking a random sample.  I don't have a good hypothesis as to what the possible explanation may be and it's quite possible that there are multiple explanations. 

My question is how large do I need my random sample to be to ensure that my results are representative of my population?

In this particular case, I have 112 observations, but I'd appreciate feedback in general of how to determine the appropriate size of the random sample in such a case to be confident that it is representative of the population.

Thank you,

Jonathan Burns

I apologize if this is a straight forward question, but it doesn't seem to fit into any formula that I am aware of.

I have a situation where I have a population of x observations.  I am not investigating a quantitative feature but rather something qualitative. Since there is no specific quantitative parameter or metric that I am investigating, it seems to me that effect size and standard power formulas aren't applicable.

In my particular case, upon examining these observations, we found that their time frame was much longer not only of what was expected but also what logically makes sense. We thus want to go back and dig into them to answer the question of why were they so long. It's not practical to review and research all of them, so I plan on taking a random sample.  I don't have a good hypothesis as to what the possible explanation may be and it's quite possible that there are multiple explanations. 

My question is how large do I need my random sample to be to ensure that my results are representative of my population?

In this particular case, I have 112 observations, but I'd appreciate feedback in general of how to determine the appropriate size of the random sample in such a case to be confident that it is representative of the population.

Thank you,

Jonathan Burns

I apologize if this is a straight forward question, but it doesn't seem to fit into any formula that I am aware of.

I have a situation where I have a population of x observations.  I am not investigating a quantitative feature but rather something qualitative. Since there is no specific quantitative parameter or metric that I am investigating, it seems to me that effect size and standard power formulas aren't applicable.

In my particular case, upon examining these observations, we found that their time frame was much longer not only of what was expected but also what logically makes sense. We thus want to go back and dig into them to answer the question of why were they so long. It's not practical to review and research all of them, so I plan on taking a random sample.  I don't have a good hypothesis as to what the possible explanation may be and it's quite possible that there are multiple explanations. 

My question is how large do I need my random sample to be to ensure that my results are representative of my population?

In this particular case, I have 112 observations, but I'd appreciate feedback in general of how to determine the appropriate size of the random sample in such a case to be confident that it is representative of the population.

Thank you,

Jonathan Burns