SCA

Loading...

來自 University of Maryland, College Park 的課程

Framework for Data Collection and Analysis

301 個評分

University of Maryland, College Park

Framework for Data Collection and Analysis

301 個評分

課程 1（共 7 門，Specialization Survey Data Collection and Analytics ）

This course will provide you with an overview over existing data products and a good understanding of the data collection landscape. With the help of various examples you will learn how to identify which data sources likely matches your research question, how to turn your research question into measurable pieces, and how to think about an analysis plan. Furthermore this course will provide you with a general framework that allows you to not only understand each step required for a successful data collection and analysis, but also help you to identify errors associated with different data sources. You will learn some metrics to quantify each potential error, and thus you will have tools at hand to describe the quality of a data source. Finally we will introduce different large scale data collection efforts done by private industry and government agencies, and review the learned concepts through these examples. This course is suitable for beginners as well as those that know about one particular data source, but not others, and are looking for a general framework to evaluate data products.

從本節課中

Application of TSE Framework to Existing Surveys

In this module we introduce a few surveys across a variety of topics. For each we highlight data collection features. The surveys span a variety of topics. We challenge you to think about alternative data sources that can be used to gather the same information or insights.

與講師見面

Frauke Kreuter, Ph.D.
Professor, Joint Program in Survey Methodology
Adjunct Research Professor, Institute for Social Research
Mariel Leonard
Lecturer
Joint Program in Survey Methodology

The fifth one in the series is the Survey of Consumer Attitudes.

This survey has the purpose of measuring attitudes about financial matters and

with the hope to predict later behaviors.

These are measurements of attitudes towards personal and

national economic attributes, measurements of saving, borrowing behavior,

purchase intention and measurement of change over time on all of these items.

This, too would be hard to come by just looking at behaviors, although you could

imagine analyzing credit card records and getting similar information, but

you don't get the perception, and your relationship between perception and

behavior that researchers or the public policy might be interested in.

The target population for this particular survey,

again adult household members 18 years and older.

This one here though has a very different sampling frame.

It's a list-assisted random digit dial survey, so basis is a phone bank and

then the last digits will be replaced by random numbers to increase

the chance to have listed and unlisted telephone numbers.

Increasingly, as we think about frames, of course,

they need to be supplemented by cell phone numbers in order to really have

created a level playing field in a frame that covers the entire population and

gives everybody the chance to be selected into the survey.

The survey is small.

It has about 500 adults per month.

But it's running all the time.

It's a two way rotating panel survey.

So, people interviewed will be interviewed twice and

then they rotate out of the survey.

This one too is an interviewer administered survey, but

over the telephone, so CATI.

If you're interested in looking at the questionnaire from the Survey of

Consumer Attitudes, here's one snippet of it as a teaser and

the link to the SCA website.

Jobs are plentiful, this an old one out of the textbook that we recommend here.

Looking at from growth at others, but of course,

there many more reports on the data from the Survey of Consumer Attitude.

For example, in this case here,

unemployment expectation and changes in US employment rates.

How they trail each other, but there are many, many more of

course that you find linked up on these websites, or in various economic journals.

The design issues, apart from the features that we already mentioned, are that

we have really seen here an increase in non-response rates over time.

For telephone surveys, this is a huge methodological issues.

It gets harder and harder to reach people on the phone.

For a variety of reasons, not the least that it's harder to even get the contact,

particularly if you call the landline phone.

Hence, what I say earlier, the need to include several frames these days or

maybe change the way these questions are asked,

maybe move away from a long questionnaire to a single item questionnaire.

Maybe move to the Google survey that we introduced earlier,

to capture this kind of sentiments.

And an interesting and still open research question is, how important is

the probability based random digit dialing sampling frame that is used for the survey

in order to get the right estimates here, of attitudes of the entire nation?

Or could Google Survey, for example, be a good alternative source?

探索我們的目錄

免費加入並獲得個性化推薦、更新和優惠。

Coursera 致力於普及全世界最好的教育，它與全球一流大學和機構合作提供在線課程。

© 2019 Coursera Inc. 保留所有權利。

通過 App Store 下載

通過 Google Play 獲取