randomly selected) samples are not subject to the bias that some of the more familiar data collection methods have. The old inventory accuracy measurement was biased because auditors would choose to measure the sites they suspected had the worst accuracy. Now the client can put any specific accusations about poor inventory management into context. His recommendations about improving inventory management are objective and considered, rather than knee-jerk reactions. Who are your squeaky wheels, how much For the last 3 years I have been helping a client take a sampling approach to measuring the accuracy of their inventory records. The measure is the net error rate, based on the size of the difference between their electronic inventory records, and the actual inventory that is held at the storage locations. you can save money and time

Sampling the inventory storage locations instead of trying to do a full stock take saves this client millions (probably more). They have thousands of storage locations, carrying many, many thousands of inventory line items. Counting them all would require an army. And even though they didn’t used to try to count them all, they are now spending less time and less money than they used to. Where can you save time and money by using samples to measure, instead of trying to measure everything?

You can improve the integrity of your data

And even though they are spending less time and money than they used to, because of the way we designed the survey, they are getting much more integrity in their data. The secret here is in segmenting the storage locations and the line items by value, designing sample sizes in each segment that accommodate the variability within each segment, and randomly selected the samples. The random selection is very important! Are you selecting samples that aren’t random? If so, your data is most likely biased, and could be misleading your decisions. you can measure more frequently

Because measuring with samples is less costly than measuring everything, you have the option to measure more frequently. Often it is just as easy to do monthly “pulse surveys” of small random samples of customers, as annual surveys of larger samples. But with annual measures, you have to wait a long time to work out if change is happening. Monthly measures (or other more frequent timeframes) more powerfully show you emerging and sudden change, and you can then respond before it’s too late.

You can refute the squeaky wheels

Well designed (and randomly selected) samples are not subject to the bias that some of the more familiar data collection methods have. The old inventory accuracy measurement was biased because auditors would choose to measure the sites they suspected had the worst accuracy. Now the client can put any specific accusations about poor inventory management into context. His recommendations about improving inventory management are objective and considered, rather than knee-jerk reactions. Who are your squeaky wheels, how much

s, carrying many, many thousands of inventory line items. Counting them all would require an army. And even though they didn’t used to try to count them all, they are now spending less time and less money than they used to. Where can you save time and money by using samples to measure, instead of trying to measure everything?

You can improve the integrity of your data

And even though they are spending less time and money than they used to, because of the way we designed the survey, they are getting much more integrity in their data. The secret here is in segmenting the storage locations and the line items by value, designing sample sizes in each segment that accommodate the variability within each segment, and randomly selected the samples. The random selection is very important! Are you selecting samples that aren’t random? If so, your data is most likely biased, and could be misleading your decisions. you can measure more frequently

Because measuring with samples is less costly than measuring everything, you have the option to measure more frequently. Often it is just as easy to do monthly “pulse surveys” of small random samples of customers, as annual surveys of larger samples. But with annual measures, you have to wait a long time to work out if change is happening. Monthly measures (or other more frequent timeframes) more powerfully show you emerging and sudden change, and you can then respond before it’s too late.

You can refute the squeaky wheels

Well designed (and randomly selected) samples are not subject to the bias that some of the more familiar data collection methods have. The old inventory accuracy measurement was biased because auditors would choose to measure the sites they suspected had the worst accuracy. Now the client can put any specific accusations about poor inventory management into context. His recommendations about improving inventory management are objective and considered, rather than knee-jerk reactions. Who are your squeaky wheels, how much

etting much more integrity in their data. The secret here is in segmenting the storage locations and the line items by value, designing sample sizes in each segment that accommodate the variability within each segment, and randomly selected the samples. The random selection is very important! Are you selecting samples that aren’t random? If so, your data is most likely biased, and could be misleading your decisions. you can measure more frequently

Because measuring with samples is less costly than measuring everything, you have the option to measure more frequently. Often it is just as easy to do monthly “pulse surveys” of small random samples of customers, as annual surveys of larger samples. But with annual measures, you have to wait a long time to work out if change is happening. Monthly measures (or other more frequent timeframes) more powerfully show you emerging and sudden change, and you can then respond before it’s too late.

You can refute the squeaky wheels

Well designed (and randomly selected) samples are not subject to the bias that some of the more familiar data collection methods have. The old inventory accuracy measurement was biased because auditors would choose to measure the sites they suspected had the worst accuracy. Now the client can put any specific accusations about poor inventory management into context. His recommendations about improving inventory management are objective and considered, rather than knee-jerk reactions. Who are your squeaky wheels, how much

measuring everything, you have the option to measure more frequently. Often it is just as easy to do monthly “pulse surveys” of small random samples of customers, as annual surveys of larger samples. But with annual measures, you have to wait a long time to work out if change is happening. Monthly measures (or other more frequent timeframes) more powerfully show you emerging and sudden change, and you can then respond before it’s too late.

You can refute the squeaky wheels

Well designed (and randomly selected) samples are not subject to the bias that some of the more familiar data collection methods have. The old inventory accuracy measurement was biased because auditors would choose to measure the sites they suspected had the worst accuracy. Now the client can put any specific accusations about poor inventory management into context. His recommendations about improving inventory management are objective and considered, rather than knee-jerk reactions. Who are your squeaky wheels, how much

randomly selected) samples are not subject to the bias that some of the more familiar data collection methods have. The old inventory accuracy measurement was biased because auditors would choose to measure the sites they suspected had the worst accuracy. Now the client can put any specific accusations about poor inventory management into context. His recommendations about improving inventory management are objective and considered, rather than knee-jerk reactions. Who are your squeaky wheels, how much do they influence decision making and resource consumption, and how could a well designed sample approach help?