MDM_bias_measurement2

=__**Measurement Bias**__=

=What is a Measurement Bias?= A measurement bias system is a systematic bias, which leads to systematic errors, that can cause readings or data results that are consistently too high or too low. The given actual value of the measured or estimated variable is different from the result. A measurement error can lead to over as well as under estimation of the coefficient of interest. __Example: A thermostat can show temperature of ten degree higher than the normal.__

Measurement data should be accurate as possible to the decimal place. When one considers the quality of a measurement there were two aspects to consider. The first is if one were to repeat the measurement, how close would new results be to the old. __Example: how reproducible is the measurement?__

Measurement is never perfect and we all expect measurement errors in data. But people are willing to minimize the error. Random Error is called non-systematic error that is beyond control,

=Important Facts of Measurement Bias= Selection bias occurs when the subjects studied are not representative of the target population about which conclusions are to be drawn. Example: Asking the popularity of a certain rap music to a senior is a selection bias. When the information is leaked and people choose their opinion because of the risk. It is type of a bias that occurs when measurement of information differs among group. In information bias, there two types of error: systematic error and random error. Random error is caused by any factors that randomly affect measurement of the variable across the sample. __Example of random error: For instance, each person's mood can inflate or deflate their performance on any occasion. In a particular testing, some children may be feeling in a good mood and others may be depressed. If mood affects their performance on the measure, it may artificially inflate the observed scores for some children and artificially deflate them for others.__ Systematic error is caused by any factors that systematically affect measurement of the variable across the sample. __Example of systematic error: If there is loud traffic going by just outside of a classroom where students are taking a test, this noise is liable to affect all of the student's scores in this case, systematically lowering them. Unlike random error, systematic errors tend to be consistently either positive or negative -- because of this, systematic error is sometimes considered to be bias in measurement.__ These are the mistakes during the collection of data whether the error was in the incorrect recording of the response of he correct recording of the inaccurate response. When the data was repeated, was the result similar to the data before? Or is it similar to the theory? If the result was different, than, the test should be repeated to see which result appears more frequent. __Example: The statistical discrepancy will decrease as more and more tests are performed.__
 * **Selection Bias**
 * **Information Bias**
 * **Measurement/Observational Error**
 * **Repeatability**

There are 4 levels of measurement Ratio measurements can be defined as zero, negative or positive. This provide the greatest flexibility in statistical methods. Interval measurement can be defined with positive and negative but cannot define zero (such as the temperature). Ordinal measurements represents ranking like 1st, 2nd, 3rd... while Nominal measurements offer names or labels for certain characteristics
 * Nominal
 * Ordinal
 * Interval
 * Ratio

• "4. Measurement error and bias." __bmj.com: __. 27 Oct. 2009 <[]>. • Carroll, Raymond J.. "Measurement error in nonlinear ... - Google Books." __Google Books __. 28 Oct. 2009 . • "Data Measurement and Variation Session 1, Part C." __Teacher Professional Development and Teacher Resources by Annenberg Media __. 28 Oct. 2009 . • Durham, Martin. "Google Books." __Google Books __. 28 Oct. 2009 . • "Levels of Measurement." __<span style="color: black; font-family: Calibri; font-size: 11pt; language: en-CA; mso-ascii-font-family: Calibri; mso-bidi-font-family: +mn-cs; mso-color-index: 1; mso-fareast-font-family: +mn-ea; mso-font-kerning: 12.0pt;">Social Research Methods __<span style="color: black; font-family: Calibri; font-size: 11pt; language: en-CA; mso-ascii-font-family: Calibri; mso-bidi-font-family: +mn-cs; mso-color-index: 1; mso-fareast-font-family: +mn-ea; mso-font-kerning: 12.0pt;">. 27 Oct. 2009 <[]>. • <span style="color: black; font-family: Calibri; font-size: 11pt; language: en-US; mso-ascii-font-family: Calibri; mso-bidi-font-family: +mn-cs; mso-color-index: 1; mso-fareast-font-family: +mn-ea; mso-font-kerning: 12.0pt;">"Measurement Error." __<span style="color: black; font-family: Calibri; font-size: 11pt; language: en-US; mso-ascii-font-family: Calibri; mso-bidi-font-family: +mn-cs; mso-color-index: 1; mso-fareast-font-family: +mn-ea; mso-font-kerning: 12.0pt;">Social Research Methods __<span style="color: black; font-family: Calibri; font-size: 11pt; language: en-US; mso-ascii-font-family: Calibri; mso-bidi-font-family: +mn-cs; mso-color-index: 1; mso-fareast-font-family: +mn-ea; mso-font-kerning: 12.0pt;">. 28 Oct. 2009 <http://www.socialresearchmethods.net/kb/measerr.php>. • <span style="color: black; font-family: Calibri; font-size: 11pt; language: en-US; mso-ascii-font-family: Calibri; mso-bidi-font-family: +mn-cs; mso-color-index: 1; mso-fareast-font-family: +mn-ea; mso-font-kerning: 12.0pt;">"Strategies for dealing with measurement error in multiple regression | Journal of the Academy of Business and Economics | Find Articles at BNET." __<span style="color: black; font-family: Calibri; font-size: 11pt; language: en-US; mso-ascii-font-family: Calibri; mso-bidi-font-family: +mn-cs; mso-color-index: 1; mso-fareast-font-family: +mn-ea; mso-font-kerning: 12.0pt;">Find Articles at BNET | News Articles, Magazine Back Issues & Reference Articles on All Topics __<span style="color: black; font-family: Calibri; font-size: 11pt; language: en-US; mso-ascii-font-family: Calibri; mso-bidi-font-family: +mn-cs; mso-color-index: 1; mso-fareast-font-family: +mn-ea; mso-font-kerning: 12.0pt;">. 28 Oct. 2009 <http://findarticles.com/p/articles/mi_m0OGT/is_3_5/ai_n16619674/>. <span style="color: black; font-family: Calibri; font-size: 11pt; language: en-CA; mso-ascii-font-family: Calibri; mso-bidi-font-family: +mn-cs; mso-color-index: 1; mso-fareast-font-family: +mn-ea; mso-font-kerning: 12.0pt;">"Statistics Glossary - sampling." __<span style="color: black; font-family: Calibri; font-size: 11pt; language: en-CA; mso-ascii-font-family: Calibri; mso-bidi-font-family: +mn-cs; mso-color-index: 1; mso-fareast-font-family: +mn-ea; mso-font-kerning: 12.0pt;">University of Glasgow :: Statistics :: Statistics __<span style="color: black; font-family: Calibri; font-size: 11pt; language: en-CA; mso-ascii-font-family: Calibri; mso-bidi-font-family: +mn-cs; mso-color-index: 1; mso-fareast-font-family: +mn-ea; mso-font-kerning: 12.0pt;">. 27 Oct.2009 <[]>.
 * Reference**