Scribd
Upload
2 views85 pages

Modelling & Simulation

The document outlines the data collection phase in input modeling for simulation, emphasizing its importance in accurately representing system behavior. It details steps such as defining objectives, identifying input variables, collecting and validating data, and analyzing it for statistical measures. Additionally, it discusses the use of histograms for data visualization, methods for testing assumptions about probability distributions, and the generation of random variates for simulations.

Uploaded by

Spain America
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
2 views85 pages

Modelling & Simulation

The document outlines the data collection phase in input modeling for simulation, emphasizing its importance in accurately representing system behavior. It details steps such as defining objectives, identifying input variables, collecting and validating data, and analyzing it for statistical measures. Additionally, it discusses the use of histograms for data visualization, methods for testing assumptions about probability distributions, and the generation of random variates for simulations.

Uploaded by

Spain America
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
Date: 7/10/2026 HHH @) Ca) Describe data collection phase of input modeling for simulation. [6 Marks] “Data Collection Phase in Input Modeling** The data collection phase is the first and most important step in siMulazion input Modeling. It involves gathering real-world gata reGuiyed to repyesent the behaviorof a system accurately in the simulation model. #### steps in Data Collection Phase; 1. “Define Objectives™ * Identify the purpose of the simulation study. * Determine what system parameters Need to be measured. 2. “Identify Input Vayiables** * Select important variables affecting system performance. * Examples; arrival times, service times, machine preakdown times, processing times, Queue lengths. 3. *"petermine Data sources** * Historical records and databases. Date: 7/10/2026 Page: 2 * Proquction logs and reports. = " Sensors and automated monitoring systems: ” Direct observation and time studies. 4. **collect Data” * Gather sufficient data samples over a representative period. * Ensure data Covers normal, peak, and abyorMa| operating conditions. S. "Validate and Cleay Data’ * Remove errors, duplicates, and missing values. ” check data consistency and Accuracy. 6. “Analyze Data” * Calculate statistical measures such 9S mean, variance, and standard deviation. "Identify suitable probability distributions (Normal, Exponential, Weibull, etc) for random variables. 7. "*Store and Document Data™ “Organize collected data systematically, * Record assumptions, Collection methods, and data Sources for Date: 7/10/2026 Page: 3 future reference. ” HHH Importance of Data Collection * Improves mode! accuracy and reliability. * Helps identify system variability. * Provides realistic inputs for simulation experiments. * Redyces modeling errors and improves decision-making. Ht @) (b) How does a Histogram work to display data? [6 Marks] A Histogram" is a graphical representation used to display the frequency distribution of contmuous pumerica) data, it helps visualize how data values Gre spread ove different ranges. H## Working of 4 Histogram I. “Collect Data** * Gather the observations or Measyrements to be gnalyzed. 2. “divide Data into Class Intervals (Bins)** * The entire data range is givided into equal or unequal Date: 7/10/2026 . Page: 4 intervals Calleq bms, fail * Example: 9-10, 10-20, 20-30, ete. 3. “Count Frequency” * Determine how many observations fall within each class interval, 4. “Draw Axes*” * X-axis: Class intervals (bins). * y-axis: Frequency (number of obsewations)- S. "Plot Rectangles** * Draw adjacent rectangles (without gaps). * Wiath of each rectangle represents the class interval, ” Height represents the frequency of Observations in thar interval. 6. “Interpret the Distribution * The shape of the histogram indicates the nature of the data distribution (Normal, SkeWed, Uniform, etc,), HHH Example Date: 7/10/2026 Page: S | Marks Range | Frequency / [pmesenesoress Jl sererosxe] | 0-10 12 / | 10-29 1s / | 20-30 |3 | ] 30-40 110 / | 40-50 Is | Histogram: Frequency 10 | i 9] l 3] Hl 7il i i 6/ EG S| BEOE o/ BED 3] POEL 2/GN ae J/g 0-10 10-29 20. -39 30-40 40-50 Date: 7/10/2026 Page: 6 ### Advantages of Histogram * Provides 4 visual summary of large data sets. * Helps idencify distribution patterns, * Reveals skewness, centfal tendency, and spread of data. * Usefy,) for selecting probability distributions in simulation studies, ### Q) ©) Which methods are Used for testing assumptions? [S Marks] In Simulation jyput modeling, assumptions about the probability distribytion of input data are yeritied using “goodness-of-fit tests and statistica] tests. HHH Methods Used for Testing Assumptions H#HH |, Chi-square (x?) Goodness-of-Fit Test * Compares observed frequencies With expected frequencies, * Determines whether the sample data follows 4 specified probability distribution. Date: 7/10/2026 . Page: 7 * Suitable for large sample sizes. age “Decision Rule:™ "If x? caltulated < y? table value — Accept assumption. * Otherwise > Reject assumption. HHH 2. Kolmog0rov-Smimov (K-S) Test * Compares the eMpirical distribution function with the theoretical distribution function. * Suitable for continuous distributions and small sample Sizes. * Measures the maximum difference between observed and expected cumulative probabilities. ##BH 3. ANderson-Darling Test * An improved go0dness-Of- fit test. * Gives more importance to the tails of the distribution. * Commonly ysed to test Normal, Exponential, and peibull distributions, Date: 7/10/2026 Page: 8 HAHH 4. Graphical Methods * "Histogram;** Visua) comparison of sample data wjth theoretical distribution. * “Probability Plot / Q-Q Plot; Checks whether data points follow a Sttaight line corresponding to the assumed distribyrion. H#it# S. Hypothesis Testing * Null Hypothesis GH): Data follows the assumed diStribytion. * “Altemative Hypothesis (H,):"" Data does not follow the assumed distribution, * Statistical tests are ysed to accept or teject Ho at a chosen significance level. H## Q2 Ca) Destribe Identification of the Iyput Data Distribution of Input Modeling for Simulation, [6 Marks] “Identification of Input Data Distribytion”’ is the process of determining the probability distribution that best represents the Date: 7/10/2026 collected mput data of a simulation model. This helps Generate realistic randoyy values during simulation. ### steps for Identification of Input Data Distribution HHH |, Datg Collection * Collect sufficient observations from the real syStem. * Examples: arrival timeS, service times, machine Fajlures, repair times, etc. HHHH 2. Data Analysis * Calculate statistica] measures: ” Mean * Variance * Standard Deviatioy * Range * These measures provide insight into the nature of the data. #i### 3. Graphical Representation * Plot the data using: * Histogram Date: 7/10/2026 Page: 10 ” Frequency Polygon we * Cumulative Frequency Curve “The shape of the graph helps identify possible distributions. H#HH G. Select Candidate Distributions BaSed on the data pattern, choose syitable distributions such as: * “Uniform Distribution” - all values equally likely, * “Normal Distribution” — symmetric bell-shaped curve. * “Exponential Distribytion”* — mode|s iMtey-artival or waiting times, * “Weibull Distribution™ - reliability and failure analysis. * "Poisson Distribution*” — number of events occurring in a fixed interval. ###H 5. Estimate Distribution Parameters * Determine parameters of the selected distribution, * Exayple: “ Nora! Distribution > Mean (1), Standard Deviation (og) ” Exponential) Distripution _, Rate (N) * Weibull Distribution — Shape Cp), Scale Cn) #### 6. Goodness-of-FitTe

You might also like