04_Handout_1(13).pdf

IT2016 Data Measurement and Acquisition Measurement involves assigning numeric values to objects or events to make meaning and understanding of a variable. It is a way of refining our ordinary observations to assign numerical values to our observations. In measurement, the most used units d...

IT2016 Data Measurement and Acquisition Measurement involves assigning numeric values to objects or events to make meaning and understanding of a variable. It is a way of refining our ordinary observations to assign numerical values to our observations. In measurement, the most used units define quantities of length, area, volume, angular measurement, temperature, pressure, electrical/electronic units, and many more. Properties of objects that can take on different values are referred to as variables. Variable responses to individual items on these scales are combined to create a single score meant to measure variables or traits. The measurement process involves recording observations that are manifestations of the underlying element. o Precision is the degree of consistency of a group of measurements, while accuracy is the absolute nearness of measured quantities to their true values. Scales of Measurement The scale is several individual measurement items are combined to create a single, composite instrument. Measurement scales are important because they allow us to transform or substitute precise numbers for imprecise words. Nominal: Categorical data and numbers simply used as identifiers or names represent a nominal scale of measurement. o Numbers on the back of a baseball jersey. o Social security number. Ordinal: An ordinal scale of measurement represents an ordered series of relationships or rank order. o Individuals competing in a contest may be fortunate to achieve first, second, or third place. o Likert-type scales. Interval: A scale representing the quantity and has equal units but for which zero simply represents an additional point of measurement is an interval scale. There is no ‘true’ zero, only an ‘arbitrary’ zero. o The Fahrenheit scale. o Measurement of Sea Level. Ratio: The ratio scale of measurement is like the interval scale in that it also represents the quantity and has equality of units. This scale also has an absolute zero (no numbers exist below the zero). o Physical measures will represent ratio data (for example, height and weight). o The length of a piece of wood in centimeters. Indications Indications Direction Indicates Amount Absolute Zero Difference of Difference of Difference Nominal X Ordinal X X Interval X X X Ratio X X X X Reliability and Validity The goal of the measurement process is to ensure that the values assigned to variables are reliable and valid. The validity and reliability of a test are established by evidence. Validity ensures that the assignment of values truly reflects the underlying construct or concept. o Types of Validity ▪ Face Validity – Measurements appear to measure what is intended. ▪ Content Validity – Measurements are drawn from the course or program material. ▪ Concurrent Validity – Measurement is like other established measurements. ▪ Construct Validity – Series of measurement that supports a psychological concept by predicting operationally defined behavior. ▪ Predictive Validity – Measurements predicts some target behavior. 04 Handout 1 *Property of STI  [email protected] Page 1 of 3  IT2016 Reliability ensures that the assignment of values is consistent or reproducible. Essentially, the consistency of scores produced by a given instrument. A measuring instrument is reliable if measurements recorded at different times give similar results. o Types of Reliability ▪ Test-Retest Reliability – Administer the same test twice and correlate scores. ▪ Alternate Reliability – Administers two forms of test and correlate scores. ▪ Split-Half Reliability – Split test into halves and correlate scores. ▪ Inter-Rater Reliability – Compare two or more rates in a time then correlate score via agreement. Both validity and reliability are important in the measurement process because the reproducibility of a measure, as well as the trueness of a measure, is critical in research. Measurement errors It can be classified as random errors and nonrandom errors. In any measurement which includes errors, true value is impossible to find but it can be estimated through measured quantity. Gross Errors (Mistakes): Large amounts, easy to find, must be eliminated before adjustment. Systematic Errors: Follows a mathematical function, can usually be checked and adjusted, and tend to maintain the same sign. A systematic error such as confounding variables and biasing artificially “trend” the measurement in one direction or another. Random Errors: remains after eliminating gross and systematic errors. Impossible to compute or eliminate. They follow the probability laws so that they can be adjusted. Their signs are not constant. Present in all surveying measurements. More observations result in a better estimate of them. Random error is an uncontrolled “noise” that does not dramatically impact the accuracy of the measurement. Data Acquisition Parameters It is the sampling of continuous real-world information to generate data that can be manipulated by a computer. A PC can be used to provide data acquisition of real-world information such as voltage, current, temperature, pressure, or sound. Sample Rate This is a digital representation of the data, with changes in discrete steps where any step smaller than the resolution of the data acquisition device cannot be represented. All modern data acquisition digitizes the data. The data is digitized in amplitude and time. Filters A filter can be used to separate the wanted signal from noise. Since there is a possibility of frequencies higher than half the sample rate, a filter is almost always used in vibration measurement applications. Buffer Blocks To capture data rapidly and precisely timed intervals, the low-level data acquisition driver does the work, putting one sample after another into a portion of the PC’s RAM referred to as a buffer. This is used to speed up data acquisition. o Acquisition Types ▪ Polled (or asynchronous) acquisition can be used, in which the application determines when to sample data from the data acquisition device, one sample at-a-time. ▪ Interrupt driven (or synchronous or buffered) acquisition acquires data in blocks, acquiring many samples at once. Interrupt acquisition can give sample rates 10 to 1000 times faster than polled. 04 Handout 1 *Property of STI  [email protected] Page 2 of 3  IT2016 o Acquisition Modes ▪ Continuous acquisition of data at rates over 100,000 samples per second can be achieved in a certain software or hardware decoder. At these rates, data can only be streamed to disk in binary format. ▪ Burst acquisition is even faster when the data acquisition device has its own buffer. The rate of acquisition is limited only by the speed of the device and the size of its buffer. Time Delays There is an inherent delay between the reading of the data and the processing of it. There is a small delay due to the processing in the application. Noise Noise is unwanted interference that affects the signal and may distort the information. o Radiated Noise This noise travels through the air as radio waves. To couple into a circuit or pass through an enclosure efficiently, the dimensions of the circuit or the hole in the enclosure must be close to the wavelength of the noise or much larger. o Conducted Noise This noise gets into a circuit on wires. These can be the signal wires picking up the measured signal, or they can be the power supply wires. The conducting noise is reduced by shielding or filtering. References: Boylestad, R. & Nashelsky, R. (2013). Electronic devices and circuit theory (11th ed.). Pearson Fernandez-Canque, H. (2017). Analog electronics applications – Fundamentals of design and analysis. CRC Press. Schuler, C. (2019). Electronics: Principles and applications (9th ed.). McGraw-Hill. Stephan, K. (2015). Analog and mixed-signal electronics. Wiley. Storey, N. (2017). Electronics: A systems approach (6th ed.). Pearson. 04 Handout 1 *Property of STI  [email protected] Page 3 of 3